Revert "Clean up repository for apps.odoo.com sharing: Remove non-18.0 addons and document them in README.md"

Addons were butchered by this commit. This reverts commit b33f25c688.
2025-05-29 21:35:39 -04:00 · 2025-05-29 21:35:39 -04:00 · 4b2b53caa7
commit 4b2b53caa7
parent 1ef0102dd2
977 changed files with 49159 additions and 106 deletions
--- a/README.md
+++ b/README.md
@ -1,108 +1,2 @@
 # bemade-addons
 Odoo Addons made by Bemade
-
-## Addons Ported to 18.0
-
-The following addons have been ported to Odoo 18.0 and are available in this repository:
-
- account_email_to_pdf (18.0.1.0.0)
- batch_picking_create_one_bill (18.0.1.0.1)
- caldav_sync (18.0.0.7.0)
- customer_product_code_search (18.0.1.0.0)
- delivery_carrier_partner_account (18.0.0.1.2)
- incrementing_sequence_mixin (18.0.1.0.0)
- portal_partner_manager (18.0.1.0.0)
- preamble_on_quotation (18.0.0.1.0)
- product_supplierinfo_tracking (18.0.2.0.5)
- purchase_delivery_carrier (18.0.1.0.0)
- reception_purchase_total (18.0.1.0.0)
- sale_mandatory_customer_reference (18.0.1.0.0)
- sale_order_show_delivery_address (18.0.1.0.0)
- shipping_information_on_customer_invoice (18.0.0.1)
- st_laurent_portal_vendor (18.0.1.0.0)
- st_laurent_vendor_orders (18.0.1.0.0)
- unifi_integration (18.0.1.0.1)
-
-## Addons To Be Ported from 17.0 to 18.0
-
-The following addons need to be ported from Odoo 17.0 to 18.0. They have been temporarily removed from this branch but can be reintegrated following the OCA methodology (creating a patch from 17.0 to bring the code in with its history):
-
- account_credit_hold (17.0.1.1.1)
- aged_partner_balance_na
- ai_integration (1.0)
- ai_integration_ollama_api
- ai_integration_openai_api (1.0)
- bemade_add_follower_no_sendmail_default (17.0.0.0.1)
- bemade_attachments_cleanup
- bemade_documents_portal
- bemade_fetchmail_only_production (17.0.0.0.1)
- bemade_fix_quality_report
- bemade_fsm (17.0.0.4.2)
- bemade_full_formview_from_modal
- bemade_git_repos_addons
- bemade_helpdesk_mailcow_blacklist
- bemade_helpdesk_one_ticket_per_email
- bemade_hide_decimal_on_unit (17.0.0.1.1)
- bemade_l10n_ca_payroll
- bemade_mailcow_integration
- bemade_margin_vendor_pricelist
- bemade_module_linker
- bemade_multiple_billing_contacts
- bemade_odoo_partner_scrapper
- bemade_odoo_partner_scrapper_js_only
- bemade_open_project_details
- bemade_packing_wizard
- bemade_partner_email_domain
- bemade_partner_root_ancestor
- bemade_payslip_done_as_not_paid
- bemade_picking_upstream
- bemade_purchase_warn_supplier_overdue (1.0)
- bemade_pwa_config
- bemade_quotation_alternative
- bemade_reordering_rules_chatter (17.0.0.0.1)
- bemade_sale_order_line_number
- bemade_search_supplier_code
- bemade_so_and_po_only_company (17.0.0.0.1)
- bemade_so_followers_to_picking (17.0.0.0.1)
- bemade_sports_clinic
- bemade_stock_quant_valuation
- bemade_time_off_follower (17.0.0.0.3)
- bemade_total_show_currency
- bemade_update_validity_date_when_send_so (17.0.0.0.1)
- bemade_user_custom_apps_order
- bemade_user_password_bundle
- bemade_utils
- client_name_on_manufacturing_orders (17.0.2.0.0)
- commercial_invoice
- confirm_many2one_create (17.0.1.0.0)
- current_user_as_invoice_user
- customer_applications (17.0.1.0.0)
- customer_itch_cycle
- fsm_equipment (17.0.0.2.0)
- fsm_visit_confirmation (17.0.0.1.0)
- impersonate_user (17.0.0.0.1)
- improved_mo_origin (17.0.1.0.0)
- interactive_discuss_ai
- l10n_ca_pst_reports
- mo_back_to_draft
- msg_attachments_to_mail_message
- msg_viewer
- multi_account_statement_import
- odoo_proxmox_manager
- odoo_rsync_backup
- odoo_to_odoo_bemade
- odoo_to_odoo_bemade_customer
- odoo_to_odoo_sync
- partner_equipment_applications (17.0.1.0.0)
- picking_policy_per_customer
- portal_hide_draft_order_details (17.0.1.0.0)
- price_update_notifications (17.0.1.0.0)
- purchase_customer_requisition (1.0)
- qc_partner_default_lang
- recursive_tree_view (17.0.0.0.2)
- replace_invoicing_user
- stock_valuation_location (17.0.1.0.0)
- temporary_change_image_size
- theme_durpro
- wazo_integration
- website_geoip_extended
--- a/account_credit_hold/init.py
+++ b/account_credit_hold/init.py
@ -0,0 +1 @@
+from . import models
--- a/account_credit_hold/manifest.py
+++ b/account_credit_hold/manifest.py
@ -0,0 +1,20 @@
+{
+    "name": "Account Credit Hold",
+    "version": "17.0.1.1.1",
+    "summary": "Allows setting clients on credit hold, blocking the ability confirm a new sales order.",
+    "category": "Accounting/Accounting",
+    "author": "Bemade Inc.",
+    "maintainer": "Marc Durepos <marc@bemade.org>",
+    "website": "http://www.bemade.org",
+    "license": "LGPL-3",
+    "depends": ["sale", "account_followup", "stock"],
+    "data": [
+        "views/account_followup_views.xml",
+        "views/sale_order_views.xml",
+        "views/res_partner_views.xml",
+        "views/stock_picking_views.xml",
+    ],
+    "demo": [],
+    "installable": True,
+    "auto_install": False,
+}
--- a/account_credit_hold/migration18.md
+++ b/account_credit_hold/migration18.md
@ -0,0 +1,246 @@
+# Migration vers Odoo 18.0 - Module account_credit_hold
+
+## Fonctionnalités
+- Ajoute un champ "Place on Credit Hold" sur les lignes de suivi de compte (account_followup.followup.line)
+- Ajoute des champs et fonctionnalités sur les partenaires:
+  - postpone_hold_until: Date de report du blocage
+  - hold_bg: Champ technique pour le statut de blocage
+  - on_hold: État calculé du blocage de crédit
+- Bloque la confirmation des commandes de vente si le client est en blocage de crédit
+- Ajoute des indicateurs visuels (ruban rouge) sur:
+  - Commandes de vente
+  - Fiches partenaires
+  - Transferts de stock
+- Ajoute des boutons pour mettre/lever le blocage de crédit dans la vue de suivi des comptes
+
+## Analyse pour la Migration
+
+### Dépendances
+- sale
+- account_followup
+- stock
+
+### Changements Techniques Requis
+1. Mettre à jour la version dans __manifest__.py vers 18.0
+2. Vérifier la compatibilité des vues XML avec Odoo 18.0
+3. Vérifier si des changements dans l'API account_followup en 18.0
+
+### Points d'Attention
+1. Le module utilise l'héritage de vues et de modèles standard d'Odoo:
+   - account_followup.followup.line
+   - res.partner
+   - sale.order
+   - stock.picking
+   - account.followup.report
+
+2. Fonctionnalités critiques à tester après migration:
+   - Calcul automatique du statut on_hold
+   - Blocage de la confirmation des commandes
+   - Nettoyage automatique des reports de blocage expirés (@api.autovacuum)
+   - Affichage correct des rubans d'avertissement
+   - Propagation du statut hold aux contacts liés (commercial_partner_id)
+
+3. Implémentation Technique:
+   - Utilisation de champs computed avec store=True et compute_sudo=True
+   - Mécanisme de nettoyage automatique via @api.autovacuum
+   - Héritage de _execute_followup_partner pour automatisation du hold
+   - Messages de chatter automatiques lors des changements de statut
+
+4. Points Spécifiques aux Vues:
+   - Utilisation du widget web_ribbon pour les indicateurs visuels
+   - Boutons conditionnels dans la vue de suivi des comptes
+   - Champs invisibles pour la logique d'affichage (hold_bg, on_hold)
+   - Groupes de sécurité sur le champ postpone_hold_until
+
+## Questions et Considérations
+
+1. Vérifier si Odoo 18.0 n'a pas introduit des fonctionnalités natives similaires dans account_followup:
+   - Système de blocage automatique des clients
+   - Gestion des périodes de grâce
+   - Indicateurs visuels de blocage
+
+2. Points à valider:
+   - La structure des vues héritées est-elle identique en 18.0?
+   - Les champs related et computed fonctionnent-ils de la même manière?
+   - Le système de suivi des comptes (account_followup) a-t-il évolué?
+   - Le décorateur @api.autovacuum est-il toujours supporté?
+   - Le widget web_ribbon utilise-t-il toujours la même API?
+
+3. Considérations d'Architecture:
+   - Le mécanisme de propagation du statut hold via commercial_partner_id est-il optimal?
+   - Possibilité de simplifier la logique de calcul du statut hold?
+   - Pertinence de stocker le champ hold_bg vs calcul à la demande
+
+4. Alternatives Potentielles:
+   - Utiliser le système de credit limit natif d'Odoo avec des règles personnalisées?
+   - Intégrer avec le système de blocage des partenaires d'Odoo?
+   - Utiliser les étapes de facturation (invoice_status) plutôt qu'un champ séparé?
+
+## Alternatives Natives Odoo 18.0
+
+### Système de Crédit Natif
+1. Odoo 18.0 inclut des fonctionnalités natives de gestion de crédit:
+   - Champ `credit_limit` sur res.partner
+   - Configuration du blocage au niveau de la société
+   - Règles de blocage basées sur:
+     - Montant de crédit maximum
+     - Factures échues
+     - Âge des factures
+
+2. Possibilités d'utilisation des fonctionnalités natives:
+   - Utiliser `credit_limit` au lieu de `on_hold`
+   - Configurer les règles de blocage dans la configuration de la comptabilité
+   - Utiliser les notifications natives de dépassement de crédit
+
+### Améliorations Possibles
+1. Intégration avec le système natif:
+   - Synchroniser notre `on_hold` avec le système natif de blocage
+   - Utiliser les API natives de vérification de crédit
+   - Conserver uniquement les fonctionnalités non disponibles nativement
+
+2. Simplification du code:
+   - Remplacer les champs custom par des champs natifs quand possible
+   - Utiliser le système d'alertes natif pour les rubans
+   - Intégrer avec le système de workflow natif
+
+## Recommandations pour la Migration
+
+### Approche "Vanilla First"
+1. Évaluer chaque fonctionnalité custom:
+   - Est-elle disponible nativement dans Odoo 18.0?
+   - Peut-elle être remplacée par une configuration native?
+   - Le besoin business existe-t-il toujours?
+
+2. Prioriser l'utilisation des fonctionnalités natives:
+   - Système de crédit natif
+   - Système de workflow natif
+   - API de notification standard
+   - Widgets standards de l'interface
+
+### Modifications Techniques Recommandées
+1. Remplacer les attributs obsolètes:
+   - Supprimer les `attrs` dans les vues (Odoo 16.0+)
+   - Utiliser `list` au lieu de `tree` (Odoo 17.0+)
+   - Adapter les widgets aux nouvelles conventions
+
+2. Optimisation des performances:
+   - Utiliser les indexes de base de données appropriés
+   - Optimiser les recherches et calculs
+   - Implémenter le lazy loading quand possible
+
+### Plan de Test Approfondi
+1. Tests fonctionnels:
+   - Validation du comportement avec le système natif
+   - Tests de régression sur les fonctionnalités custom
+   - Vérification des performances
+
+2. Tests d'intégration:
+   - Interaction avec le workflow de vente
+   - Synchronisation avec la comptabilité
+   - Comportement avec les autres modules
+
+## État de la Migration
+⚪ En analyse préliminaire
+
+## Plan de Migration
+
+### Étape 1: Analyse des Changements Odoo 18.0
+- [ ] Examiner les changements dans account_followup
+- [ ] Vérifier les nouvelles fonctionnalités de gestion de crédit
+- [ ] Analyser les modifications des vues héritées
+
+### Étape 2: Adaptation Technique
+- [ ] Mise à jour du manifeste
+- [ ] Vérification de la compatibilité des décorateurs
+- [ ] Adaptation des vues XML si nécessaire
+- [ ] Test des champs computed et related
+
+### Étape 3: Tests Fonctionnels
+- [ ] Validation du mécanisme de hold
+- [ ] Test de la propagation aux contacts
+- [ ] Vérification des nettoyages automatiques
+- [ ] Test des indicateurs visuels
+
+### Étape 4: Optimisation
+- [ ] Évaluation des alternatives natives
+- [ ] Simplification potentielle du code
+- [ ] Amélioration des performances
+
+## Notes de Version
+- Version originale: 17.0.1.1.1
+- Dernière analyse: 26/01/2025
+
+## Fonctionnalités Natives dans Odoo 18.0
+
+Odoo 18.0 inclut nativement plusieurs fonctionnalités de gestion du crédit :
+
+1. **Gestion des Limites de Crédit**
+   - Champ `credit_limit` sur les partenaires
+   - Champ `use_partner_credit_limit` pour activer/désactiver par partenaire
+   - Configuration globale `account_use_credit_limit` au niveau de la société
+   - Champ `credit` pour le total des créances
+   - Champ `trust` pour le niveau de confiance du débiteur
+
+2. **Visibilité et Contrôle**
+   - Champ `show_credit_limit` basé sur la configuration de la société
+   - Groupes de sécurité pour la gestion des limites de crédit
+
+### Différences avec Notre Module
+
+1. **Fonctionnalités à Migrer**
+   - [ ] Indicateurs visuels spécifiques pour les clients en dépassement
+   - [ ] Blocage automatique des commandes en dépassement
+   - [ ] Workflow d'approbation personnalisé
+
+2. **Fonctionnalités à Adapter**
+   - [ ] Utiliser les champs natifs plutôt que nos champs customs
+   - [ ] Intégrer nos règles de blocage avec le système natif
+   - [ ] Adapter les rapports et vues pour utiliser les champs natifs
+
+## Plan de Migration
+
+### Phase 1 : Préparation
+1. **Analyse des Données**
+   - [ ] Identifier les clients avec des limites de crédit
+   - [ ] Mapper les champs actuels vers les champs natifs
+   - [ ] Lister les règles de blocage personnalisées
+
+2. **Configuration**
+   - [ ] Activer la gestion du crédit dans la configuration de la société
+   - [ ] Configurer les groupes de sécurité appropriés
+   - [ ] Préparer les scripts de migration des données
+
+### Phase 2 : Migration
+1. **Migration des Données**
+   - [ ] Transférer les limites de crédit vers le champ natif
+   - [ ] Migrer les configurations de blocage
+   - [ ] Mettre à jour les vues et rapports
+
+2. **Développement**
+   - [ ] Adapter le code de blocage des commandes
+   - [ ] Implémenter les indicateurs visuels manquants
+   - [ ] Ajouter les fonctionnalités spécifiques non disponibles nativement
+
+### Phase 3 : Tests
+1. **Validation Fonctionnelle**
+   - [ ] Tester les limites de crédit
+   - [ ] Vérifier le blocage des commandes
+   - [ ] Valider les workflows d'approbation
+
+2. **Tests d'Intégration**
+   - [ ] Tester avec les autres modules
+   - [ ] Vérifier la compatibilité avec les processus existants
+
+## État de la Migration
+🟡 En cours d'analyse - Utilisation partielle des fonctionnalités natives
+
+## Notes Importantes
+- La gestion du crédit est maintenant une fonctionnalité native d'Odoo
+- Certaines fonctionnalités spécifiques devront être maintenues
+- L'approche recommandée est d'utiliser au maximum les fonctionnalités natives et de ne conserver que les extensions nécessaires
+
+## Prochaines Étapes
+1. Valider l'approche avec l'équipe
+2. Créer les scripts de migration des données
+3. Développer les fonctionnalités manquantes
+4. Planifier la formation des utilisateurs
--- a/account_credit_hold/models/init.py
+++ b/account_credit_hold/models/init.py
@ -0,0 +1,5 @@
+from . import account_followup
+from . import res_partner
+from . import sale_order
+from . import stock_picking
+from . import account_followup_report
--- a/account_credit_hold/models/account_followup.py
+++ b/account_credit_hold/models/account_followup.py
@ -0,0 +1,8 @@
+from odoo import fields, models, api
+
+
+class FollowupLine(models.Model):
+    _inherit = 'account_followup.followup.line'
+
+    account_hold = fields.Boolean(string="Place on Credit Hold",
+                                  help="Place clients on account hold, restricting confirmation of new orders.")
--- a/account_credit_hold/models/account_followup_report.py
+++ b/account_credit_hold/models/account_followup_report.py
@ -0,0 +1,12 @@
+from odoo import models, fields, api, _
+
+
+class FollowUpReport(models.AbstractModel):
+    _inherit = 'account.followup.report'
+
+    def _get_line_info(self, followup_line):
+        res = super()._get_line_info(followup_line)
+        res.update({
+            'credit_hold': followup_line.account_hold
+        })
+        return res
--- a/account_credit_hold/models/res_partner.py
+++ b/account_credit_hold/models/res_partner.py
@ -0,0 +1,80 @@
+from odoo import fields, models, api, _
+from datetime import date
+
+
+class Partner(models.Model):
+    _inherit = "res.partner"
+
+    postpone_hold_until = fields.Date(
+        string="Postpone Hold",
+        help="Grace period specific to this partner despite unpaid invoices.",
+        tracking=True,
+    )
+
+    hold_bg = fields.Boolean(
+        string="Hold (technical)",
+        compute="_compute_hold_bg",
+        store=True,
+        default=False,
+        compute_sudo=True,
+        tracking=True,
+    )
+    on_hold = fields.Boolean(
+        string="Account on Hold",
+        help="Client account is on hold for unpaid overdue invoices.",
+        compute="_compute_on_hold",
+        compute_sudo=True,
+    )
+
+    @api.depends("postpone_hold_until", "hold_bg")
+    def _compute_on_hold(self):
+        # manually re-compute hold_bg since followup_status doesn't get updated in Python but gets recalculated
+        # by an SQL query every time
+        self._compute_hold_bg()
+        for rec in self:
+            # If the parent company is on hold, so are all its sub-contacts and subsidiaries
+            if rec.commercial_partner_id and rec.commercial_partner_id.on_hold:
+                rec.on_hold = True
+                return
+            # If there is no parent company or the parent is not on hold, we compute for ourselves
+            if rec.hold_bg and not (
+                rec.postpone_hold_until and rec.postpone_hold_until > date.today()
+            ):
+                rec.on_hold = True
+            else:
+                if rec.on_hold:
+                    rec.message_post(_("Credit hold lifted."))
+                rec.on_hold = False
+
+    @api.autovacuum
+    def _cleanup_expired_hold_postponements(self):
+        expired_holds = self.search([("postpone_hold_until", "<=", date.today())])
+        expired_holds.write({"postpone_hold_until": False})
+
+    def action_credit_hold(self):
+        for rec in self:
+            rec.hold_bg = True
+            rec.message_post(body=_("Placed on credit hold."))
+
+    def action_lift_credit_hold(self):
+        for rec in self:
+            rec.hold_bg = False
+            rec.message_post(body=_("Credit hold lifted."))
+
+    def _execute_followup_partner(self, options=None):
+        res = super()._execute_followup_partner(options)
+        if self.followup_status == "in_need_of_action":
+            if self.followup_line_id.account_hold:
+                self.action_credit_hold()
+        return res
+
+    @api.depends("followup_status", "followup_line_id")
+    def _compute_hold_bg(self):
+        first_followup_level = self._get_first_followup_level()
+        for rec in self:
+            prev_hold_bg = rec.hold_bg
+            level = rec.followup_line_id
+            if rec.followup_status == "no_action_needed" and not level:
+                rec.hold_bg = False
+            else:
+                rec.hold_bg = prev_hold_bg
--- a/account_credit_hold/models/sale_order.py
+++ b/account_credit_hold/models/sale_order.py
@ -0,0 +1,17 @@
+from odoo import fields, models, api, _
+from odoo.exceptions import UserError
+
+
+class SaleOrder(models.Model):
+    _inherit = "sale.order"
+
+    client_on_hold = fields.Boolean(string='Client on Hold',
+                                    help="Whether or not a client has been put on hold due to unpaid invoices.",
+                                    related="partner_id.on_hold")
+
+    @api.depends('client_on_hold')
+    def action_confirm(self):
+        if any(self.mapped('client_on_hold')):
+            raise UserError(_("This client is on credit hold. No new orders can be confirmed until past-due invoices "
+                              "are paid or the accounting team postpones the hold."))
+        super().action_confirm()
--- a/account_credit_hold/models/stock_picking.py
+++ b/account_credit_hold/models/stock_picking.py
@ -0,0 +1,9 @@
+from odoo import fields, models, api
+
+
+class ModelName(models.Model):
+    _inherit = "stock.picking"
+
+    client_on_hold = fields.Boolean(string='Client on Hold',
+                                    help="Whether or not a client has been put on hold due to unpaid invoices.",
+                                    related="partner_id.on_hold")
--- a/account_credit_hold/readme.md
+++ b/account_credit_hold/readme.md
@ -0,0 +1,40 @@
+# Overview
+
+This module adds the notion of placing clients on credit hold to the followup levels from the Odoo Enterprise 
+account_followup module. It adds an option to followup levels to mark clients matching the followup criteria as on 
+credit hold. This hold restricts the confirmation of new sales orders for these clients.
+
+Accountant and admin users can set a date until which the account hold will be
+postponed on a specific partner's form view. This effectively gives clients an extra
+grace period, allowing orders to be confirmed until the period ends.
+
+# Change Log
+
+## 17.0.1.0.0 (2024-05-15)
+
+Various modifications to adapt code to Odoo 17.0
+
+## 15.0.2.0.0 (2023-05-04)
+
+Complete remake of the module, making the "Credit Hold" an action that is either manually or
+automatically triggered from the Accounting > Followup Reports section or by setting the automatic application field
+on followup levels.
+
+## 15.0.1.1.0 (2023-05-03)
+
+Adds a ribbon to stock pickings for clients on hold, and therefore a dependency on stock.
+
+## 15.0.1.0.2 (2023-05-03)
+
+Fix to sale order view and sale order confirmation for clients not on hold.
+
+## 15.0.1.0.1 (2023-05-03) 
+
+Fix clients on hold when status is "outstanding_invoices".
+
+## 15.0.1.0.0 (2023-05-02) Initial Release
+
+Initial release of the module, including a setting on follow-up levels to toggle placing on credit hold. Blocks
+the confirmation of sales orders for clients on credit hold. Red "Credit Hold" banner appears on sales orders and
+partner form view when a client is on credit hold. Credit hold can be postponed by setting the "Postpone Hold" field
+on the partner form view.
--- a/account_credit_hold/views/account_followup_views.xml
+++ b/account_credit_hold/views/account_followup_views.xml
@ -0,0 +1,49 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<odoo>
+        <record id="account_followup_followup_line_form_inherit" model="ir.ui.view">
+            <field name="name">account_credit_hold.account_followup_line.form</field>
+            <field name="model">account_followup.followup.line</field>
+            <field
+      name="inherit_id"
+      ref="account_followup.view_account_followup_followup_line_form"
+    />
+            <field name="arch" type="xml">
+                <xpath expr="//field[@name='send_email']" position="before">
+                    <field name="account_hold" />
+                </xpath></field>
+        </record>
+        <record id="customer_statements_form_view_inherit" model="ir.ui.view">
+            <field name="name">customer.statements.form.view.inherit</field>
+            <field name="model">res.partner</field>
+            <field
+      name="inherit_id"
+      ref="account_followup.customer_statements_form_view"
+    />
+            <field name="arch" type="xml">
+                <xpath expr="//button[last()]" position="after">
+                    <field invisible="1" name="hold_bg" />
+                    <button
+          class="button btn-secondary"
+          invisible="hold_bg == True"
+          name="action_credit_hold"
+          string="Credit Hold"
+          type="object"
+        />
+                    <button
+          class="button btn-secondary"
+          invisible="hold_bg == False"
+          name="action_lift_credit_hold"
+          string="Lift Credit Hold"
+          type="object"
+        />
+                </xpath></field>
+        </record>
+        <record id="action_credit_hold" model="ir.actions.server">
+            <field name="name">action_credit_hold</field>
+            <field name="model_id" ref="base.model_res_partner" />
+            <field name="binding_model_id" ref="base.model_res_partner" />
+            <field name="binding_view_types">list,form</field>
+            <field name="state">code</field>
+            <field name="code">records.action_credit_hold()</field>
+        </record>
+</odoo>
--- a/account_credit_hold/views/res_partner_views.xml
+++ b/account_credit_hold/views/res_partner_views.xml
@ -0,0 +1,34 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<odoo>
+        <record id="res_partner_form_inherit" model="ir.ui.view">
+            <field name="name">account_credit_hold.res_partner.form</field>
+            <field name="model">res.partner</field>
+            <field name="inherit_id" ref="base.view_partner_form" />
+            <field name="arch" type="xml">
+                <xpath expr="//div[@name='button_box']" position="before">
+                    <field invisible="True" name="hold_bg" />
+                    <field invisible="True" name="on_hold" />
+                    <widget
+          bg_color="bg-danger"
+          invisible="on_hold == False"
+          name="web_ribbon"
+          title="Credit Hold"
+        />
+                </xpath></field>
+        </record>
+        <record id="view_partner_property_form_inherit" model="ir.ui.view">
+            <field name="name">account_credit_hold.view_partner_property_form</field>
+            <field name="model">res.partner</field>
+            <field name="inherit_id" ref="account.view_partner_property_form" />
+            <field name="arch" type="xml">
+                <xpath expr="//group[@name='banks']" position="before">
+                    <group string="Credit Hold">
+                        <field
+            groups="account.group_account_manager,account.group_account_user"
+            name="postpone_hold_until"
+            readonly="hold_bg == False and postpone_hold_until == False"
+          />
+                    </group>
+                </xpath></field>
+        </record>
+</odoo>
--- a/account_credit_hold/views/sale_order_views.xml
+++ b/account_credit_hold/views/sale_order_views.xml
@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<odoo>
+        <record id="sale_order_form_inherit" model="ir.ui.view">
+            <field name="name">account_credit_hold.sale_order.form</field>
+            <field name="model">sale.order</field>
+            <field name="inherit_id" ref="sale.view_order_form" />
+            <field name="arch" type="xml">
+                <xpath expr="//div[@name='button_box']" position="before">
+                    <field invisible="True" name="client_on_hold" />
+                    <widget
+          bg_color="bg-danger"
+          invisible="client_on_hold == False"
+          name="web_ribbon"
+          title="Credit Hold"
+        />
+                </xpath></field>
+        </record>
+</odoo>
--- a/account_credit_hold/views/stock_picking_views.xml
+++ b/account_credit_hold/views/stock_picking_views.xml
@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<odoo>
+        <record id="stock_picking_form_inherit" model="ir.ui.view">
+            <field name="name">account_credit_hold.stock_picking.form</field>
+            <field name="model">stock.picking</field>
+            <field name="inherit_id" ref="stock.view_picking_form" />
+            <field eval="8" name="priority" />
+            <field name="arch" type="xml">
+                <xpath expr="//div[@name='button_box']" position="before">
+                    <field invisible="True" name="client_on_hold" />
+                    <widget
+          bg_color="bg-danger"
+          invisible="client_on_hold == False"
+          name="web_ribbon"
+          title="Credit Hold"
+        />
+                </xpath></field>
+        </record>
+</odoo>
--- a/aged_partner_balance_na/init.py
+++ b/aged_partner_balance_na/init.py
@ -0,0 +1,33 @@
+from . import models
+
+
+def post_init(env):
+    env['account.report'].search([('name', 'ilike', 'Aged % - North America')]).unlink()
+    new_receivable_report =  env.ref('account_reports.aged_receivable_report').copy()
+    new_payable_report = env.ref('account_reports.aged_payable_report').copy()
+    new_receivable_report.line_ids.mapped('expression_ids').write({
+        'formula': '_report_custom_engine_aged_receivable_na'
+    })
+    new_payable_report.line_ids.mapped('expression_ids').write({'formula': '_report_custom_engine_aged_payable_na'})
+    new_receivable_report.write({
+        'name': 'Aged Receivable - North America',
+        'root_report_id': env.ref('account_reports.aged_receivable_report').id,
+        'availability_condition': 'always',
+    })
+    new_payable_report.write({
+        'name': 'Aged Payable - North America',
+        'root_report_id': env.ref('account_reports.aged_payable_report').id,
+        'availability_condition': 'always',
+    })
+    col_name_mapping = [
+        ('At Date', 'Overdue'),
+        ('1-30', '0-29'),
+        ('31-60', '30-59'),
+        ('61-90', '60-89'),
+        ('91-120', '90-119'),
+        ('Older', 'Later'),
+    ]
+    for old_name, new_name in col_name_mapping:
+        ((new_payable_report | new_receivable_report)
+         .mapped('column_ids')
+         .filtered(lambda col: col.name == old_name)).write({'name': new_name})
--- a/aged_partner_balance_na/manifest.py
+++ b/aged_partner_balance_na/manifest.py
@ -0,0 +1,32 @@
+#
+#    Bemade Inc.
+#
+#    Copyright (C) 2023-June Bemade Inc. (<https://www.bemade.org>).
+#    Author: Marc Durepos (Contact : marc@bemade.org)
+#
+#    This program is under the terms of the Odoo Proprietary License v1.0 (OPL-1)
+#    It is forbidden to publish, distribute, sublicense, or sell copies of the Software
+#    or modified copies of the Software.
+#
+#    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+#    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+#    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+#    IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+#    DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+#    ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+#    DEALINGS IN THE SOFTWARE.
+#
+{
+    'name': 'Aged Partner Balance (North American Style)',
+    'version': '17.0.1.0.0',
+    'summary': 'Present aged partner balance as predictive rather than past due.',
+    'category': 'Accounting',
+    'author': 'Bemade Inc.',
+    'website': 'http://www.bemade.org',
+    'license': 'LGPL-3',
+    'depends': ['account_reports'],
+    'assets': {},
+    'installable': True,
+    'auto_install': False,
+    'post_init_hook': 'post_init',
+}
--- a/aged_partner_balance_na/models/init.py
+++ b/aged_partner_balance_na/models/init.py
@ -0,0 +1 @@
+from . import aged_partner_balance
--- a/aged_partner_balance_na/models/aged_partner_balance.py
+++ b/aged_partner_balance_na/models/aged_partner_balance.py
@ -0,0 +1,245 @@
+from odoo import models, fields
+from itertools import chain
+from dateutil.relativedelta import relativedelta
+
+
+class AgedPartnerBalanceCustomHandler(models.AbstractModel):
+    _inherit = "account.aged.partner.balance.report.handler"
+
+    def _report_custom_engine_aged_receivable_na(
+            self,
+            expressions,
+            options,
+            date_scope,
+            current_groupby,
+            next_groupby,
+            offset=0,
+            limit=None,
+            warnings=None
+    ):
+        return self._aged_partner_report_custom_engine_common_na(
+            options,
+            'asset_receivable',
+            current_groupby,
+            next_groupby,
+            offset=offset,
+            limit=limit
+        )
+
+    def _report_custom_engine_aged_payable_na(
+            self,
+            expressions,
+            options,
+            date_scope,
+            current_groupby,
+            next_groupby,
+            offset=0,
+            limit=None,
+            warnings=None
+    ):
+        return self._aged_partner_report_custom_engine_common_na(
+            options,
+            'liability_payable',
+            current_groupby,
+            next_groupby,
+            offset=offset,
+            limit=limit
+        )
+
+    def _aged_partner_report_custom_engine_common_na(self, options, internal_type, current_groupby, next_groupby, offset=0, limit=None):
+        report = self.env['account.report'].browse(options['report_id'])
+        report._check_groupby_fields((next_groupby.split(',') if next_groupby else []) + ([current_groupby] if current_groupby else []))
+
+        def plus_days(date_obj, days):
+            return fields.Date.to_string(date_obj + relativedelta(days=days))
+
+        def minus_days(date_obj, days):
+            return fields.Date.to_string(date_obj - relativedelta(days=days))
+
+        date_to = fields.Date.from_string(options['date']['date_to'])
+        periods = [
+            (False, minus_days(date_to, 1)),
+            (date_to, plus_days(date_to, 29)),
+            (plus_days(date_to, 30), plus_days(date_to, 59)),
+            (plus_days(date_to, 60), plus_days(date_to, 89)),
+            (plus_days(date_to, 90), plus_days(date_to, 119)),
+            (plus_days(date_to, 120), False),
+        ]
+
+        def build_result_dict(report, query_res_lines):
+            rslt = {f'period{i}': 0 for i in range(len(periods))}
+
+            for query_res in query_res_lines:
+                for i in range(len(periods)):
+                    period_key = f'period{i}'
+                    rslt[period_key] += query_res[period_key]
+
+            if current_groupby == 'id':
+                query_res = query_res_lines[0] # We're grouping by id, so there is only 1 element in query_res_lines anyway
+                currency = self.env['res.currency'].browse(query_res['currency_id'][0]) if len(query_res['currency_id']) == 1 else None
+                expected_date = len(query_res['expected_date']) == 1 and query_res['expected_date'][0] or len(query_res['due_date']) == 1 and query_res['due_date'][0]
+                rslt.update({
+                    'invoice_date': query_res['invoice_date'][0] if len(query_res['invoice_date']) == 1 else None,
+                    'due_date': query_res['due_date'][0] if len(query_res['due_date']) == 1 else None,
+                    'amount_currency': query_res['amount_currency'],
+                    'currency_id': query_res['currency_id'][0] if len(query_res['currency_id']) == 1 else None,
+                    'currency': currency.display_name if currency else None,
+                    'account_name': query_res['account_name'][0] if len(query_res['account_name']) == 1 else None,
+                    'expected_date': expected_date or None,
+                    'total': None,
+                    'has_sublines': query_res['aml_count'] > 0,
+
+                    # Needed by the custom_unfold_all_batch_data_generator, to speed-up unfold_all
+                    'partner_id': query_res['partner_id'][0] if query_res['partner_id'] else None,
+                })
+            else:
+                rslt.update({
+                    'invoice_date': None,
+                    'due_date': None,
+                    'amount_currency': None,
+                    'currency_id': None,
+                    'currency': None,
+                    'account_name': None,
+                    'expected_date': None,
+                    'total': sum(rslt[f'period{i}'] for i in range(len(periods))),
+                    'has_sublines': False,
+                })
+
+            return rslt
+
+        # Build period table
+        period_table_format = ('(VALUES %s)' % ','.join("(%s, %s, %s)" for period in periods))
+        params = list(chain.from_iterable(
+            (period[0] or None, period[1] or None, i)
+            for i, period in enumerate(periods)
+        ))
+        period_table = self.env.cr.mogrify(period_table_format, params).decode(self.env.cr.connection.encoding)
+
+        # Build query
+        tables, where_clause, where_params = report._query_get(options, 'strict_range', domain=[('account_id.account_type', '=', internal_type)])
+
+        currency_table = report._get_query_currency_table(options)
+        always_present_groupby = "period_table.period_index, currency_table.rate, currency_table.precision"
+        if current_groupby:
+            select_from_groupby = f"account_move_line.{current_groupby} AS grouping_key,"
+            groupby_clause = f"account_move_line.{current_groupby}, {always_present_groupby}"
+        else:
+            select_from_groupby = ''
+            groupby_clause = always_present_groupby
+        select_period_query = ','.join(
+            f"""
+                CASE WHEN period_table.period_index = {i}
+                THEN %s * (
+                    SUM(ROUND(account_move_line.balance * currency_table.rate, currency_table.precision))
+                    - COALESCE(SUM(ROUND(part_debit.amount * currency_table.rate, currency_table.precision)), 0)
+                    + COALESCE(SUM(ROUND(part_credit.amount * currency_table.rate, currency_table.precision)), 0)
+                )
+                ELSE 0 END AS period{i}
+            """
+            for i in range(len(periods))
+        )
+
+        tail_query, tail_params = report._get_engine_query_tail(offset, limit)
+        query = f"""
+            WITH period_table(date_start, date_stop, period_index) AS ({period_table})
+
+            SELECT
+                {select_from_groupby}
+                %s * (
+                    SUM(account_move_line.amount_currency)
+                    - COALESCE(SUM(part_debit.debit_amount_currency), 0)
+                    + COALESCE(SUM(part_credit.credit_amount_currency), 0)
+                ) AS amount_currency,
+                ARRAY_AGG(DISTINCT account_move_line.partner_id) AS partner_id,
+                ARRAY_AGG(account_move_line.payment_id) AS payment_id,
+                ARRAY_AGG(DISTINCT move.invoice_date) AS invoice_date,
+                ARRAY_AGG(DISTINCT COALESCE(account_move_line.date_maturity, account_move_line.date)) AS report_date,
+                ARRAY_AGG(DISTINCT account_move_line.expected_pay_date) AS expected_date,
+                ARRAY_AGG(DISTINCT account.code) AS account_name,
+                ARRAY_AGG(DISTINCT COALESCE(account_move_line.date_maturity, account_move_line.date)) AS due_date,
+                ARRAY_AGG(DISTINCT account_move_line.currency_id) AS currency_id,
+                COUNT(account_move_line.id) AS aml_count,
+                ARRAY_AGG(account.code) AS account_code,
+                {select_period_query}
+
+            FROM {tables}
+
+            JOIN account_journal journal ON journal.id = account_move_line.journal_id
+            JOIN account_account account ON account.id = account_move_line.account_id
+            JOIN account_move move ON move.id = account_move_line.move_id
+            JOIN {currency_table} ON currency_table.company_id = account_move_line.company_id
+
+            LEFT JOIN LATERAL (
+                SELECT
+                    SUM(part.amount) AS amount,
+                    SUM(part.debit_amount_currency) AS debit_amount_currency,
+                    part.debit_move_id
+                FROM account_partial_reconcile part
+                WHERE part.max_date <= %s AND part.debit_move_id = account_move_line.id
+                GROUP BY part.debit_move_id
+            ) part_debit ON TRUE
+
+            LEFT JOIN LATERAL (
+                SELECT
+                    SUM(part.amount) AS amount,
+                    SUM(part.credit_amount_currency) AS credit_amount_currency,
+                    part.credit_move_id
+                FROM account_partial_reconcile part
+                WHERE part.max_date <= %s AND part.credit_move_id = account_move_line.id
+                GROUP BY part.credit_move_id
+            ) part_credit ON TRUE
+
+            JOIN period_table ON
+                (
+                    period_table.date_start IS NULL
+                    OR COALESCE(account_move_line.date_maturity, account_move_line.date) >= DATE(period_table.date_start)
+                )
+                AND
+                (
+                    period_table.date_stop IS NULL
+                    OR COALESCE(account_move_line.date_maturity, account_move_line.date) <= DATE(period_table.date_stop)
+                )
+
+            WHERE {where_clause}
+
+            GROUP BY {groupby_clause}
+
+            HAVING
+                (
+                    SUM(ROUND(account_move_line.debit * currency_table.rate, currency_table.precision))
+                    - COALESCE(SUM(ROUND(part_debit.amount * currency_table.rate, currency_table.precision)), 0)
+                ) != 0
+                OR
+                (
+                    SUM(ROUND(account_move_line.credit * currency_table.rate, currency_table.precision))
+                    - COALESCE(SUM(ROUND(part_credit.amount * currency_table.rate, currency_table.precision)), 0)
+                ) != 0
+            {tail_query}
+        """
+
+        multiplicator = -1 if internal_type == 'liability_payable' else 1
+        params = [
+            multiplicator,
+            *([multiplicator] * len(periods)),
+            date_to,
+            date_to,
+            *where_params,
+            *tail_params,
+        ]
+        self._cr.execute(query, params)
+        query_res_lines = self._cr.dictfetchall()
+
+        if not current_groupby:
+            return build_result_dict(report, query_res_lines)
+        else:
+            rslt = []
+
+            all_res_per_grouping_key = {}
+            for query_res in query_res_lines:
+                grouping_key = query_res['grouping_key']
+                all_res_per_grouping_key.setdefault(grouping_key, []).append(query_res)
+
+            for grouping_key, query_res_lines in all_res_per_grouping_key.items():
+                rslt.append((grouping_key, build_result_dict(report, query_res_lines)))
+
+            return rslt
--- a/ai_integration/init.py
+++ b/ai_integration/init.py
@ -0,0 +1 @@
+from . import models
--- a/ai_integration/manifest.py
+++ b/ai_integration/manifest.py
@ -0,0 +1,39 @@
+{
+    'name': 'AI Integration Base',
+    'version': '1.0',
+    'category': 'Technical',
+    'summary': 'Base module for AI integration',
+    'description': """
+AI Integration Base
+===================
+This module provides the base framework for integrating various AI providers
+into Odoo. It includes:
+
+* Abstract interfaces for AI providers
+* Base configuration for AI models
+* Common utilities for AI integration
+""",
+    'author': 'Bemade',
+    'website': 'https://www.bemade.org',
+    'depends': [
+        'base',
+        'web',
+        'mail',
+    ],
+    'data': [
+        'security/ai_security.xml',
+        'security/ir_rule.xml',
+        'security/ir.model.access.csv',
+        'views/res_company_views.xml',
+        'views/res_config_settings_views.xml',
+        'views/ai_provider_views.xml',
+        'views/ai_provider_instance_views.xml',
+        'views/ai_model_views.xml',
+        'views/ai_model_stats_views.xml',
+        'views/menu.xml',
+    ],
+    'installable': True,
+    'application': False,
+    'auto_install': False,
+    'license': 'LGPL-3',
+}
--- a/ai_integration/models/init.py
+++ b/ai_integration/models/init.py
@ -0,0 +1,9 @@
+from .mixins.ai_base_mixin import AIBaseMixin
+from . import ai_generation_params
+from . import ai_model
+from . import ai_provider_interface
+from . import ai_provider
+from . import ai_provider_instance
+from . import res_config_settings
+from . import res_company
+from . import ai_model_stats
--- a/ai_integration/models/ai_generation_params.py
+++ b/ai_integration/models/ai_generation_params.py
@ -0,0 +1,42 @@
+from odoo import models, fields, api, _
+
+class AIGenerationParams(models.AbstractModel):
+    _name = 'ai.generation.params'
+    _description = 'AI Generation Parameters'
+
+    # Base Generation Parameters
+    temperature = fields.Float(
+        string='Temperature',
+        help='Controls randomness in generation. Higher values make output more random, lower values more deterministic.',
+        default=0.7
+    )
+    
+    repeat_penalty = fields.Float(
+        string='Repeat Penalty',
+        help='Penalty for repeating tokens. Higher values make repetition less likely.',
+        default=1.1
+    )
+    
+    max_tokens = fields.Integer(
+        string='Max Tokens',
+        help='Maximum number of tokens to generate.',
+        default=2048
+    )
+    
+    stop_sequences = fields.Char(
+        string='Stop Sequences',
+        help='Comma-separated list of sequences where generation should stop.',
+        default=''
+    )
+    
+    frequency_penalty = fields.Float(
+        string='Frequency Penalty',
+        help='Penalty for using frequent tokens. Higher values encourage using less frequent tokens.',
+        default=0.0
+    )
+    
+    presence_penalty = fields.Float(
+        string='Presence Penalty',
+        help='Penalty for using tokens already in the text. Higher values encourage using new tokens.',
+        default=0.0
+    )
--- a/ai_integration/models/ai_model.py
+++ b/ai_integration/models/ai_model.py
@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+
+
+class AIModel(models.Model):
+    _name = 'ai.model'
+    _description = 'AI Model'
+    _order = 'sequence, name'
+    _check_company = False  # Disable automatic company checks
+
+    active = fields.Boolean(
+        string='Active',
+        default=True,
+        help='Whether this model is active and available for use')
+
+    name = fields.Char(
+        string='Name',
+        required=True,
+        help='Name of the AI model'
+    )
+    
+    identifier = fields.Char(
+        string='Identifier',
+        required=True,
+        help='Technical identifier of the model (e.g., gpt-3.5-turbo, mistral-7b)'
+    )
+    
+    provider_instance_id = fields.Many2one(
+        'ai.provider.instance',
+        string='Provider Instance',
+        required=True,
+        ondelete='cascade',
+        help='Provider instance this model belongs to'
+    )
+    
+    provider_type = fields.Selection(
+        related='provider_instance_id.provider_type',
+        string='Provider Type',
+        store=True,
+        readonly=True,
+        help='Type of AI provider'
+    )
+    
+    description = fields.Text(
+        string='Description',
+        help='Description of the model and its capabilities'
+    )
+    
+    sequence = fields.Integer(
+        string='Sequence',
+        default=10,
+        help='Sequence for ordering models in lists and dropdowns'
+    )
+    
+    is_active = fields.Boolean(
+        string='Model Active',
+        default=True,
+        help='Whether this model is currently active and available for use'
+    )
+    
+    context_window = fields.Integer(
+        string='Context Window',
+        default=2048,
+        help='Maximum number of tokens in the context window'
+    )
+    
+    _sql_constraints = [
+        ('unique_identifier_provider',
+         'unique(identifier, provider_instance_id)',
+         'The model identifier must be unique per provider instance!')
+    ]
+    
+    def name_get(self):
+        """Custom name_get to include provider instance in display name."""
+        result = []
+        for model in self:
+            name = f"{model.name} ({model.provider_instance_id.name})"
+            result.append((model.id, name))
+        return result
--- a/ai_integration/models/ai_model_stats.py
+++ b/ai_integration/models/ai_model_stats.py
@ -0,0 +1,94 @@
+from odoo import models, fields, api
+from datetime import datetime, timedelta
+
+class AIModelStats(models.Model):
+    _name = 'ai.model.stats'
+    _description = 'AI Model Usage Statistics'
+    _order = 'date desc'
+
+    @api.model
+    def _has_provider_modules(self):
+        """Check if any AI provider modules are installed."""
+        modules = ['ollama_ai_integration', 'chatgpt_ai_integration']
+        return any(self.env['ir.module.module'].search([('name', 'in', modules), ('state', '=', 'installed')]))
+
+    @api.model
+    def default_get(self, fields_list):
+        """Override default_get to prevent creation if no provider modules are installed."""
+        if not self._has_provider_modules():
+            raise UserError(_('No AI provider modules are installed. Please install at least one provider module (e.g., Ollama or ChatGPT) before creating model statistics.'))
+        return super().default_get(fields_list)
+
+    model_id = fields.Many2one('ai.model', string='Model', required=True, ondelete='cascade')
+    provider_instance_id = fields.Many2one(
+        related='model_id.provider_instance_id', 
+        string='Provider Instance',
+        store=True)
+        
+    date = fields.Date(string='Date', required=True, default=fields.Date.context_today)
+    request_count = fields.Integer(string='Number of Requests', default=0)
+    token_count = fields.Integer(string='Total Tokens', default=0)
+    avg_response_time = fields.Float(string='Average Response Time (ms)', digits=(10, 2), default=0)
+    error_count = fields.Integer(string='Number of Errors', default=0)
+    version = fields.Char(string='Model Version', help='Version of the model when stats were recorded')
+
+    _sql_constraints = [
+        ('unique_model_date', 'unique(model_id, date)', 'Only one stat entry per model per day is allowed.')
+    ]
+
+    def _update_stats(self, model, tokens, response_time, error=False, version=None):
+        """Update statistics for a model."""
+        today = fields.Date.context_today(self)
+        stats = self.search([
+            ('model_id', '=', model.id),
+            ('date', '=', today)
+        ])
+
+        if not stats:
+            stats = self.create({
+                'model_id': model.id,
+                'date': today,
+                'version': version
+            })
+
+        # Update statistics
+        new_count = stats.request_count + 1
+        new_tokens = stats.token_count + tokens
+        new_time = ((stats.avg_response_time * stats.request_count) + response_time) / new_count
+        new_errors = stats.error_count + (1 if error else 0)
+
+        stats.write({
+            'request_count': new_count,
+            'token_count': new_tokens,
+            'avg_response_time': new_time,
+            'error_count': new_errors,
+            'version': version or stats.version  # Update version if provided
+        })
+
+    @api.model
+    def get_model_stats(self, model_id, days=30):
+        """Get statistics for a model over the specified number of days."""
+        start_date = fields.Date.today() - timedelta(days=days)
+        stats = self.search([
+            ('model_id', '=', model_id),
+            ('date', '>=', start_date)
+        ])
+        
+        return {
+            'daily_stats': [{
+                'date': stat.date,
+                'requests': stat.request_count,
+                'tokens': stat.token_count,
+                'response_time': stat.avg_response_time,
+                'errors': stat.error_count,
+                'version': stat.version
+            } for stat in stats],
+            'summary': {
+                'total_requests': sum(stat.request_count for stat in stats),
+                'total_tokens': sum(stat.token_count for stat in stats),
+                'avg_response_time': sum(stat.avg_response_time * stat.request_count for stat in stats) / 
+                                   (sum(stat.request_count for stat in stats) if stats else 1),
+                'total_errors': sum(stat.error_count for stat in stats),
+                'versions_used': list(set(stat.version for stat in stats if stat.version))
+            }
+        }
--- a/ai_integration/models/ai_provider.py
+++ b/ai_integration/models/ai_provider.py
@ -0,0 +1,73 @@
+# -*- coding: utf-8 -*-
+import logging
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+
+_logger = logging.getLogger(__name__)
+
+
+class AIProvider(models.Model):
+    _name = 'ai.provider'
+    _description = 'AI Provider'
+    _inherit = ['ai.provider.interface']
+
+    name = fields.Char(string='Name', required=True)
+    code = fields.Char(string='Code', required=True)
+    description = fields.Text(string='Description')
+    default_host = fields.Char(string='Default Host')
+    active = fields.Boolean(string='Active', default=True)
+
+    @api.model
+    def send_message(self, message, **kwargs):
+        """Send a message to the AI provider and get a response.
+        
+        Args:
+            message (dict): The message to send
+            **kwargs: Additional provider-specific parameters
+            
+        Returns:
+            str: The response from the AI provider
+            
+        Raises:
+            NotImplementedError: Must be implemented by specific providers
+        """
+        raise NotImplementedError(_("Method send_message must be implemented by specific AI providers"))
+
+    @api.model
+    def get_models(self):
+        """Get the list of available models from the provider.
+        
+        Returns:
+            list: List of model information dictionaries
+            
+        Raises:
+            NotImplementedError: Must be implemented by specific providers
+        """
+        raise NotImplementedError(_("Method get_models must be implemented by specific AI providers"))
+    
+    @api.model
+    def test_connection(self):
+        """Test the connection to the AI provider.
+        
+        Returns:
+            bool: True if connection is successful
+            
+        Raises:
+            NotImplementedError: Must be implemented by specific providers
+        """
+        raise NotImplementedError(_("Method test_connection must be implemented by specific AI providers"))
+    
+    def _handle_error(self, error, context=''):
+        """Common error handling for AI provider operations.
+        
+        Args:
+            error (Exception): The error that occurred
+            context (str): Additional context about where the error occurred
+            
+        Returns:
+            tuple: (success, message)
+        """
+        error_msg = str(error)
+        log_msg = f"AI Provider Error{' in ' + context if context else ''}: {error_msg}"
+        _logger.error(log_msg)
+        return False, error_msg
--- a/ai_integration/models/ai_provider_instance.py
+++ b/ai_integration/models/ai_provider_instance.py
@ -0,0 +1,106 @@
+# -*- coding: utf-8 -*-
+from odoo import models, fields, api, _
+from odoo.addons.mail.models.mail_thread import MailThread
+from odoo.exceptions import UserError
+
+
+class BaseAIProviderInstance(models.Model):
+    _name = 'ai.provider.instance'
+    _description = 'AI Provider Instance'
+    _order = 'name'
+    _check_company = False  # Disable automatic company checks
+    _inherit = ['mail.thread', 'ai.base.mixin']
+
+    @api.model
+    def default_get(self, fields_list):
+        """Override default_get to prevent creation if no provider modules are installed."""
+        defaults = super().default_get(fields_list)
+        if defaults.get('provider_type', 'none') == 'none':
+            defaults['provider_type'] = 'ollama'
+        return defaults
+
+    active = fields.Boolean(
+        string='Active',
+        default=True,
+        help='Whether this provider instance is active and available for use')
+
+    name = fields.Char(
+        string='Name',
+        required=True,
+        help='Name of this provider instance (e.g., "OpenWebUI Production", "Ollama Local")'
+    )
+    
+    provider_type = fields.Selection(
+        [('none', 'None')],  # Base selection, will be extended by provider modules
+        string='Provider Type',
+        required=True,
+        default='none',
+        help='The type of AI provider for this instance',
+        ondelete={'none': lambda r: r.write({'provider_type': 'none'})}
+    )
+    
+    host = fields.Char(
+        string='Host',
+        required=True,
+        help='Host address (e.g., "http://localhost:8080" or "https://api.example.com")'
+    )
+    
+    api_key = fields.Char(
+        string='API Key',
+        help='API key if required by the provider',
+        invisible="[('provider_type', '=', 'ollama')]"  # Hide when provider type is ollama
+    )
+    
+    @api.model
+    def get_default_instance(self):
+        """Get the default AI provider instance to use.
+        
+        Returns:
+            ai.provider.instance: The default instance to use, or raises UserError if none found
+        """
+        instance = self.env['ai.provider.instance'].search([('active', '=', True)], limit=1)
+        if not instance:
+            raise UserError(_('No active AI provider instance found. Please configure one in the settings.'))
+        return instance
+    
+    model_ids = fields.One2many(
+        'ai.model',
+        'provider_instance_id',
+        copy=True,
+        string='Available Models'
+    )
+    
+    timeout = fields.Integer(
+        string='Timeout',
+        default=60,
+        help='Maximum wait time for API calls (in seconds)'
+    )
+    
+    max_retries = fields.Integer(
+        string='Max Retries',
+        default=3,
+        help='Maximum number of retry attempts for failed API calls'
+    )
+    
+    @api.model
+    def _valid_field_parameter(self, field, name):
+        return name == 'invisible' or super()._valid_field_parameter(field, name)
+    
+    _sql_constraints = [
+        ('name_uniq',
+         'unique(name)',
+         'Provider instance name must be unique!')
+    ]
+    
+    def test_connection(self):
+        """Test the connection to this provider instance."""
+        self.ensure_one()
+        if self.provider_type == 'none':
+            raise UserError(_('Please select a provider type'))
+        return {'type': 'ir.actions.act_window_close'}
+    
+    def sync_models(self):
+        """Synchronize models from this provider instance."""
+        self.ensure_one()
+        if self.provider_type == 'none':
+            raise UserError(_('Please select a provider type'))
--- a/ai_integration/models/ai_provider_interface.py
+++ b/ai_integration/models/ai_provider_interface.py
@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+import logging
+from odoo import models, api, _
+from odoo.exceptions import UserError
+
+_logger = logging.getLogger(__name__)
+
+
+class AIProviderInterface(models.AbstractModel):
+    _name = 'ai.provider.interface'
+    _description = 'AI Provider Interface'
+
+    @api.model
+    def send_message(self, message, **kwargs):
+        """Send a message to the AI provider and get a response.
+        
+        Args:
+            message (dict): The message to send
+            **kwargs: Additional provider-specific parameters
+            
+        Returns:
+            dict: The response from the AI provider
+        """
+        raise NotImplementedError()
+
+    def _get_provider_type(self):
+        """Get the provider type code.
+        
+        Returns:
+            str: The provider type code
+        """
+        raise NotImplementedError()
+
+    def _get_model_info(self, instance, model_name):
+        """Get detailed information about a specific model.
+        
+        Args:
+            instance (ai.provider.instance): The provider instance
+            model_name (str): Name of the model
+            
+        Returns:
+            dict: Model information
+        """
+        raise NotImplementedError()
+
+    def _list_models(self, instance):
+        """List available models for this provider instance.
+        
+        Args:
+            instance (ai.provider.instance): The provider instance
+            
+        Returns:
+            list: List of available models
+        """
+        raise NotImplementedError()
--- a/ai_integration/models/doc_models.md
+++ b/ai_integration/models/doc_models.md
@ -0,0 +1,90 @@
+# Documentation des Modèles AI Integration
+
+## Vue d'ensemble
+
+Le module AI Integration fournit une infrastructure flexible pour intégrer différents fournisseurs d'IA dans Odoo. Il est conçu pour être extensible et permettre l'ajout facile de nouveaux fournisseurs.
+
+## Modèles Principaux
+
+### 1. AI Provider (`ai.provider`)
+- **Description**: Configuration de base des fournisseurs d'IA
+- **Champs principaux**:
+  - `name`: Nom du fournisseur
+  - `code`: Code technique unique
+  - `description`: Description détaillée
+  - `default_host`: Hôte par défaut
+  - `active`: État actif/inactif
+
+### 2. AI Provider Instance (`ai.provider.instance`)
+- **Description**: Instance spécifique d'un fournisseur d'IA
+- **Héritage**: `mail.thread`, `ai.base.mixin`
+- **Champs principaux**:
+  - `name`: Nom de l'instance (ex: "OpenWebUI Production", "Ollama Local")
+  - `provider_id`: Fournisseur associé
+  - `provider_type`: Type de fournisseur (extensible par modules)
+  - `active`: État actif/inactif
+- **Validation**:
+  - Vérifie la présence d'au moins un module fournisseur installé
+
+### 3. AI Model (`ai.model`)
+- **Description**: Modèles d'IA disponibles
+- **Champs principaux**:
+  - `name`: Nom du modèle
+  - `identifier`: Identifiant technique (ex: gpt-3.5-turbo, mistral-7b)
+  - `provider_instance_id`: Instance du fournisseur (cascade)
+  - `provider_type`: Type de fournisseur (relié à l'instance)
+  - `active`: État actif/inactif
+  - `sequence`: Ordre d'affichage
+- **Validation**:
+  - Vérifie la présence d'au moins un module fournisseur installé
+
+### 4. AI Generation Parameters (`ai.generation.params`)
+- **Description**: Paramètres de génération pour les modèles d'IA
+- **Type**: Modèle abstrait
+- **Champs principaux**:
+  - `temperature`: Contrôle de l'aléatoire (défaut: 0.7)
+  - `repeat_penalty`: Pénalité de répétition (défaut: 1.1)
+  - `max_tokens`: Nombre maximum de tokens (défaut: 2048)
+  - `stop_sequences`: Séquences d'arrêt
+  - `frequency_penalty`: Pénalité de fréquence (défaut: 0.0)
+  - `presence_penalty`: Pénalité de présence (défaut: 0.0)
+
+## Configuration et Interfaces
+
+### 1. Res Config Settings
+- **Description**: Paramètres de configuration globaux
+- **Champs principaux**:
+  - `default_provider_instance_id`: Instance de fournisseur par défaut
+  - `default_model_id`: Modèle par défaut
+  - `ai_batch_size`: Taille du lot pour le traitement
+
+### 2. Res Company
+- **Description**: Extensions des paramètres de société
+- **Méthodes principales**:
+  - `_get_default_provider_instance`: Obtenir l'instance par défaut
+
+### 3. AI Provider Interface (`ai.provider.interface`)
+- **Description**: Interface abstraite pour les fournisseurs d'IA
+- **Méthodes requises**:
+  - `send_message`: Envoyer un message
+  - `get_models`: Obtenir la liste des modèles
+  - `test_connection`: Tester la connexion
+
+## Notes d'Implémentation
+
+1. **Architecture Modulaire**:
+   - Modules fournisseurs disponibles: `ollama_ai_integration`, `chatgpt_ai_integration`
+   - Vérification de la présence d'au moins un module fournisseur avant création d'instances
+
+2. **Héritage et Extensions**:
+   - Les instances de fournisseur héritent de `mail.thread` et `ai.base.mixin`
+   - Les paramètres de génération sont définis dans le modèle abstrait `ai.generation.params`
+
+3. **Configuration Hiérarchique**:
+   - Configuration globale > Paramètres société > Instance
+   - Paramètres de génération personnalisables à plusieurs niveaux
+
+4. **Sécurité et Validation**:
+   - Vérifications de sécurité intégrées
+   - Validation des modules requis
+   - Gestion des paramètres de génération avec valeurs par défaut
--- a/ai_integration/models/mixins/init.py
+++ b/ai_integration/models/mixins/init.py
@ -0,0 +1 @@
+from . import ai_base_mixin
--- a/ai_integration/models/mixins/ai_base_mixin.py
+++ b/ai_integration/models/mixins/ai_base_mixin.py
@ -0,0 +1,167 @@
+# -*- coding: utf-8 -*-
+from typing import List, Dict, Any, Optional
+from odoo import models, api, fields, _
+from odoo.exceptions import UserError
+import logging
+
+_logger = logging.getLogger(__name__)
+
+class AIBaseMixin(models.AbstractModel):
+    """Base mixin for AI integration providing both provider interaction and generation parameters.
+    
+    This mixin combines the functionality of message handling and generation parameters
+    into a single, cohesive interface for AI integration.
+    """
+    _name = 'ai.base.mixin'
+    _description = 'AI Integration Base Mixin'
+
+    # Basic Generation Parameters
+    temperature = fields.Float(
+        string='Temperature',
+        help='Sampling temperature. Range: [0.0 - 2.0]. Higher values make output more random, '
+             'lower values more deterministic.',
+        default=0.7,
+        digits=(3, 2))
+    
+    top_p = fields.Float(
+        string='Top P',
+        help='Nucleus sampling: limits cumulative probability of tokens to sample from. '
+             'Range: [0.0 - 1.0].',
+        default=0.9,
+        digits=(3, 2))
+    
+    max_tokens = fields.Integer(
+        string='Max Tokens',
+        help='Maximum number of tokens to generate. Range: [1 - 32768].',
+        default=2048)
+    
+    stop_sequences = fields.Char(
+        string='Stop Sequences',
+        help='Comma-separated list of sequences where the model should stop generating')
+
+    # System Settings
+    timeout = fields.Integer(
+        string='Timeout',
+        help='Request timeout in seconds. Range: [1 - 300].',
+        default=30)
+    
+    retry_count = fields.Integer(
+        string='Retry Count',
+        help='Number of times to retry failed requests. Range: [0 - 5].',
+        default=3)
+    
+    stream_response = fields.Boolean(
+        string='Stream Response',
+        help='Enable response streaming for real-time output.',
+        default=False)
+
+    def _get_base_generation_params(self):
+        """Get common generation parameters as a dictionary.
+        
+        Returns:
+            dict: Dictionary containing all generation parameters
+        """
+        self.ensure_one()
+        return {
+            'temperature': self.temperature,
+            'top_p': self.top_p,
+            'max_tokens': self.max_tokens,
+            'stop_sequences': self.stop_sequences.split(',') if self.stop_sequences else None,
+            'timeout': self.timeout,
+            'retry_count': self.retry_count,
+            'stream_response': self.stream_response,
+        }
+
+    def _get_ai_provider_instance(self, provider_instance_id=None):
+        """Get the AI provider instance to use.
+        
+        Args:
+            provider_instance_id: Optional specific provider instance to use
+            
+        Returns:
+            ai.provider.instance: The provider instance to use
+            
+        Raises:
+            UserError: If no provider instance is configured or available
+        """
+        if provider_instance_id:
+            instance = self.env['ai.provider.instance'].browse(provider_instance_id)
+            if not instance.exists():
+                raise UserError(_("Invalid provider instance"))
+        else:
+            provider_id = self.env['ir.config_parameter'].sudo().get_param(
+                'ai_integration.default_provider_instance_id')
+            if not provider_id:
+                raise UserError(_("No default AI provider instance configured"))
+            instance = self.env['ai.provider.instance'].browse(int(provider_id))
+            if not instance.exists():
+                raise UserError(_("Default provider instance not found"))
+        
+        if not instance.is_active:
+            raise UserError(_("The selected AI provider instance is not active"))
+            
+        return instance
+
+    def _get_ai_model(self, model_id=None, provider_instance=None):
+        """Get the AI model to use.
+        
+        Args:
+            model_id: Optional specific model to use
+            provider_instance: Optional provider instance (to avoid duplicate lookup)
+            
+        Returns:
+            ai.model: The model to use
+            
+        Raises:
+            UserError: If no model is configured or available
+        """
+        if not provider_instance:
+            provider_instance = self._get_ai_provider_instance()
+            
+        if model_id:
+            model = self.env['ai.model'].browse(model_id)
+            if not model.exists():
+                raise UserError(_("Invalid model"))
+            if model.provider_instance_id != provider_instance:
+                raise UserError(_("Model does not belong to the selected provider instance"))
+        else:
+            model_id = self.env['ir.config_parameter'].sudo().get_param(
+                'ai_integration.default_model_id')
+            if not model_id:
+                raise UserError(_("No default AI model configured"))
+            model = self.env['ai.model'].browse(int(model_id))
+            if not model.exists():
+                raise UserError(_("Default model not found"))
+                
+        if not model.is_active:
+            raise UserError(_("The selected AI model is not active"))
+            
+        return model
+
+    def send_ai_message(self, message: Dict[str, Any], provider_instance_id: Optional[int] = None,
+                       model_id: Optional[int] = None, **kwargs):
+        """Send a message to an AI provider instance.
+        
+        Args:
+            message: The message to send
+            provider_instance_id: Optional specific provider instance to use
+            model_id: Optional specific model to use
+            **kwargs: Additional provider-specific parameters
+            
+        Returns:
+            str: The response from the AI provider
+            
+        Raises:
+            UserError: If there's an error with the AI provider
+        """
+        provider_instance = self._get_ai_provider_instance(provider_instance_id)
+        model = self._get_ai_model(model_id, provider_instance)
+        
+        # Merge generation parameters with provider-specific parameters
+        params = {**self._get_base_generation_params(), **kwargs}
+        
+        try:
+            return provider_instance.send_message(message, model=model, **params)
+        except Exception as e:
+            _logger.error("Error sending message to AI provider: %s", str(e))
+            raise UserError(_("Failed to send message to AI provider: %s") % str(e))
--- a/ai_integration/models/res_company.py
+++ b/ai_integration/models/res_company.py
@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+
+
+class ResCompany(models.Model):
+    _inherit = 'res.company'
+
+    def _get_default_provider_instance(self):
+        """Get the default AI provider instance from config parameters"""
+        provider_id = self.env['ir.config_parameter'].sudo().get_param('ai_integration.default_provider_instance_id')
+        return self.env['ai.provider.instance'].browse(int(provider_id)) if provider_id else False
+
+    def _get_default_model(self):
+        """Get the default AI model from config parameters"""
+        model_id = self.env['ir.config_parameter'].sudo().get_param('ai_integration.default_model_id')
+        return self.env['ai.model'].browse(int(model_id)) if model_id else False
+
+    def _get_ai_batch_size(self):
+        """Get the AI batch size from config parameters"""
+        return int(self.env['ir.config_parameter'].sudo().get_param('ai_integration.ai_batch_size', '100'))
--- a/ai_integration/models/res_config_settings.py
+++ b/ai_integration/models/res_config_settings.py
@ -0,0 +1,22 @@
+from odoo import api, fields, models
+
+class ResConfigSettings(models.TransientModel):
+    _inherit = 'res.config.settings'
+
+    default_provider_instance_id = fields.Many2one(
+        'ai.provider.instance',
+        string='Default AI Provider Instance',
+        config_parameter='ai_integration.default_provider_instance_id',
+        default_model='ai.provider.instance')
+    
+    default_model_id = fields.Many2one(
+        'ai.model',
+        string='Default AI Model',
+        config_parameter='ai_integration.default_model_id',
+        default_model='ai.model')
+    
+    ai_batch_size = fields.Integer(
+        string='AI Batch Processing Size',
+        config_parameter='ai_integration.ai_batch_size',
+        default=100,
+        default_model='ai.provider.instance')
--- a/ai_integration/security/ai_security.xml
+++ b/ai_integration/security/ai_security.xml
@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="0">
+        <!-- AI User Group -->
+        <record id="group_ai_user" model="res.groups">
+            <field name="name">AI User</field>
+            <field name="category_id" ref="base.module_category_services"/>
+            <field name="comment">Users can use AI services but cannot configure them.</field>
+        </record>
+
+        <!-- AI Manager Group -->
+        <record id="group_ai_manager" model="res.groups">
+            <field name="name">AI Manager</field>
+            <field name="category_id" ref="base.module_category_services"/>
+            <field name="implied_ids" eval="[(4, ref('group_ai_user'))]"/>
+            <field name="comment">Full access to AI configuration and usage.</field>
+            <field name="users" eval="[(4, ref('base.user_admin'))]"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration/security/ir.model.access.csv
+++ b/ai_integration/security/ir.model.access.csv
@ -0,0 +1,11 @@
+id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink
+access_ai_model_user,ai.model.user,model_ai_model,base.group_user,1,0,0,0
+access_ai_model_system,ai.model.system,model_ai_model,base.group_system,1,1,1,1
+access_ai_provider_instance_user,ai.provider.instance.user,model_ai_provider_instance,base.group_user,1,0,0,0
+access_ai_provider_instance_system,ai.provider.instance.system,model_ai_provider_instance,base.group_system,1,1,1,1
+access_ai_model_stats_user,ai.model.stats.user,model_ai_model_stats,base.group_user,1,0,0,0
+access_ai_model_stats_system,ai.model.stats.system,model_ai_model_stats,base.group_system,1,1,1,1
+access_ai_generation_params_user,ai.generation.params.user,model_ai_generation_params,base.group_user,1,0,0,0
+access_ai_generation_params_system,ai.generation.params.system,model_ai_generation_params,base.group_system,1,1,1,1
+access_ai_provider_user,ai.provider.user,model_ai_provider,base.group_user,1,0,0,0
+access_ai_provider_system,ai.provider.system,model_ai_provider,base.group_system,1,1,1,1
--- a/ai_integration/security/ir_rule.xml
+++ b/ai_integration/security/ir_rule.xml
@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="0">
+        <!-- Global Provider Instance Rule -->
+        <record id="ai_provider_instance_global_rule" model="ir.rule">
+            <field name="name">AI Provider Instance: Global Access</field>
+            <field name="model_id" ref="model_ai_provider_instance"/>
+            <field name="domain_force">[(1, '=', 1)]</field>
+            <field name="groups" eval="[(4, ref('base.group_user'))]"/>
+            <field name="perm_read" eval="True"/>
+            <field name="perm_write" eval="True"/>
+            <field name="perm_create" eval="True"/>
+            <field name="perm_unlink" eval="True"/>
+        </record>
+
+        <!-- Global Model Rule -->
+        <record id="ai_model_global_rule" model="ir.rule">
+            <field name="name">AI Model: Global Access</field>
+            <field name="model_id" ref="model_ai_model"/>
+            <field name="domain_force">[(1, '=', 1)]</field>
+            <field name="groups" eval="[(4, ref('base.group_user'))]"/>
+            <field name="perm_read" eval="True"/>
+            <field name="perm_write" eval="True"/>
+            <field name="perm_create" eval="True"/>
+            <field name="perm_unlink" eval="True"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration/views/ai_model_stats_views.xml
+++ b/ai_integration/views/ai_model_stats_views.xml
@ -0,0 +1,118 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Tree View -->
+    <record id="view_ai_model_stats_list" model="ir.ui.view">
+        <field name="name">ai.model.stats.list</field>
+        <field name="model">ai.model.stats</field>
+        <field name="arch" type="xml">
+            <list string="Model Statistics" create="false">
+                <field name="date"/>
+                <field name="model_id"/>
+                <field name="provider_instance_id"/>
+                <field name="version"/>
+                <field name="request_count"/>
+                <field name="token_count"/>
+                <field name="avg_response_time"/>
+                <field name="error_count"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Form View -->
+    <record id="view_ai_model_stats_form" model="ir.ui.view">
+        <field name="name">ai.model.stats.form</field>
+        <field name="model">ai.model.stats</field>
+        <field name="arch" type="xml">
+            <form string="Model Statistics">
+                <sheet>
+                    <group>
+                        <group>
+                            <field name="date"/>
+                            <field name="model_id"/>
+                            <field name="provider_instance_id"/>
+                            <field name="version"/>
+                        </group>
+                        <group>
+                            <field name="request_count"/>
+                            <field name="token_count"/>
+                            <field name="avg_response_time"/>
+                            <field name="error_count"/>
+                        </group>
+                    </group>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="view_ai_model_stats_search" model="ir.ui.view">
+        <field name="name">ai.model.stats.search</field>
+        <field name="model">ai.model.stats</field>
+        <field name="arch" type="xml">
+            <search string="Search Model Statistics">
+                <field name="model_id"/>
+                <field name="provider_instance_id"/>
+                <field name="version"/>
+                <field name="date"/>
+                <filter string="Today" name="today" domain="[('date','=',context_today().strftime('%Y-%m-%d'))]"/>
+                <filter string="Last 7 Days" name="last_week" domain="[('date','>=', (context_today() - datetime.timedelta(days=7)).strftime('%Y-%m-%d'))]"/>
+                <filter string="Last 30 Days" name="last_month" domain="[('date','>=', (context_today() - datetime.timedelta(days=30)).strftime('%Y-%m-%d'))]"/>
+                <group expand="0" string="Group By">
+                    <filter string="Model" name="group_by_model" context="{'group_by': 'model_id'}"/>
+                    <filter string="Provider Instance" name="group_by_provider" context="{'group_by': 'provider_instance_id'}"/>
+                    <filter string="Version" name="group_by_version" context="{'group_by': 'version'}"/>
+                    <filter string="Date" name="group_by_date" context="{'group_by': 'date'}"/>
+                </group>
+            </search>
+        </field>
+    </record>
+
+    <!-- Graph View -->
+    <record id="view_ai_model_stats_graph" model="ir.ui.view">
+        <field name="name">ai.model.stats.graph</field>
+        <field name="model">ai.model.stats</field>
+        <field name="arch" type="xml">
+            <graph string="Model Statistics" type="line" sample="1">
+                <field name="date" type="row"/>
+                <field name="request_count" type="measure"/>
+                <field name="token_count" type="measure"/>
+                <field name="error_count" type="measure"/>
+            </graph>
+        </field>
+    </record>
+
+    <!-- Pivot View -->
+    <record id="view_ai_model_stats_pivot" model="ir.ui.view">
+        <field name="name">ai.model.stats.pivot</field>
+        <field name="model">ai.model.stats</field>
+        <field name="arch" type="xml">
+            <pivot string="Model Statistics" sample="1">
+                <field name="model_id" type="row"/>
+                <field name="provider_instance_id" type="row"/>
+                <field name="date" type="col"/>
+                <field name="request_count" type="measure"/>
+                <field name="token_count" type="measure"/>
+                <field name="avg_response_time" type="measure"/>
+                <field name="error_count" type="measure"/>
+            </pivot>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="action_ai_model_stats" model="ir.actions.act_window">
+        <field name="name">Model Statistics</field>
+        <field name="res_model">ai.model.stats</field>
+        <field name="view_mode">list,form,graph,pivot</field>
+        <field name="context">{'search_default_last_month': 1}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                No statistics recorded yet
+            </p>
+            <p>
+                Statistics will be automatically recorded as you use your AI models.
+            </p>
+        </field>
+    </record>
+
+
+</odoo>
--- a/ai_integration/views/ai_model_views.xml
+++ b/ai_integration/views/ai_model_views.xml
@ -0,0 +1,96 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Tree View -->
+    <record id="ai_model_view_list" model="ir.ui.view">
+        <field name="name">ai.model.list</field>
+        <field name="model">ai.model</field>
+        <field name="type">list</field>
+        <field name="arch" type="xml">
+            <list string="AI Models" create="false">
+                <field name="sequence" widget="handle"/>
+                <field name="name"/>
+                <field name="provider_instance_id"/>
+                <field name="provider_type"/>
+                <field name="identifier"/>
+                <field name="context_window"/>
+                <field name="active"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Form View -->
+    <record id="ai_model_view_form" model="ir.ui.view">
+        <field name="name">ai.model.form</field>
+        <field name="model">ai.model</field>
+        <field name="arch" type="xml">
+            <form string="AI Model">
+                <sheet>
+                    <div class="oe_button_box" name="button_box">
+                        <button name="toggle_active" type="object" class="oe_stat_button" icon="fa-archive">
+                            <field name="active" widget="boolean_button" options="{'terminology': 'archive'}"/>
+                        </button>
+                    </div>
+                    <div class="oe_title">
+                        <label for="name" class="oe_edit_only"/>
+                        <h1><field name="name" placeholder="e.g. GPT-3.5 Turbo"/></h1>
+                    </div>
+                    <group>
+                        <group>
+                            <field name="provider_instance_id" options="{'no_create': True}"/>
+                            <field name="provider_type"/>
+                            <field name="identifier"/>
+                            <field name="context_window"/>
+                        </group>
+                        <group>
+                            <field name="sequence"/>
+                        </group>
+                    </group>
+                    <notebook>
+                        <page string="Description" name="description">
+                            <field name="description" placeholder="Enter a description of the model and its capabilities..."/>
+                        </page>
+                    </notebook>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="ai_model_view_search" model="ir.ui.view">
+        <field name="name">ai.model.search</field>
+        <field name="model">ai.model</field>
+        <field name="arch" type="xml">
+            <search string="Search AI Models">
+                <field name="name"/>
+                <field name="identifier"/>
+                <field name="provider_instance_id"/>
+                <field name="provider_type"/>
+                <filter string="Archived" name="inactive" domain="[('is_active', '=', False)]"/>
+                <group expand="0" string="Group By">
+                    <filter string="Provider Instance" name="group_by_provider" context="{'group_by': 'provider_instance_id'}"/>
+                    <filter string="Provider Type" name="group_by_type" context="{'group_by': 'provider_type'}"/>
+
+                </group>
+            </search>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="ai_model_action" model="ir.actions.act_window">
+        <field name="name">AI Models</field>
+        <field name="res_model">ai.model</field>
+        <field name="view_mode">list,form</field>
+        <field name="search_view_id" ref="ai_model_view_search"/>
+        <field name="context">{'search_default_group_by_provider': 1}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                No AI models found
+            </p>
+            <p>
+                AI models will be automatically synchronized when you configure and sync a provider instance.
+            </p>
+        </field>
+    </record>
+
+
+</odoo>
--- a/ai_integration/views/ai_provider_instance_views.xml
+++ b/ai_integration/views/ai_provider_instance_views.xml
@ -0,0 +1,107 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Tree View -->
+    <record id="ai_provider_instance_view_list" model="ir.ui.view">
+        <field name="name">ai.provider.instance.list</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="arch" type="xml">
+            <list name="ai_instance" string="AI Provider Instances" create="true">
+                <field name="name"/>
+                <field name="provider_type"/>
+                <field name="host"/>
+                <field name="active"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Form View -->
+    <record id="ai_provider_instance_view_form" model="ir.ui.view">
+        <field name="name">ai.provider.instance.form</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="arch" type="xml">
+            <form string="AI Provider Instance">
+                <header>
+                    <button name="test_connection" 
+                            string="Test Connection" 
+                            type="object" 
+                            class="oe_highlight"/>
+                    <button name="sync_models" 
+                            string="Sync Models" 
+                            type="object" 
+                            class="btn-primary"/>
+                </header>
+                <sheet>
+                    <div class="oe_button_box" name="button_box">
+                        <button name="toggle_active" type="object" class="oe_stat_button" icon="fa-archive">
+                            <field name="active" widget="boolean_button" options="{'terminology': 'archive'}"/>
+                        </button>
+                    </div>
+                    <div class="oe_title">
+                        <label for="name" class="oe_edit_only"/>
+                        <h1><field name="name" placeholder="e.g. OpenWebUI Production"/></h1>
+                    </div>
+                    <group>
+                        <group>
+                            <field name="provider_type"/>
+                            <field name="host"/>
+                            <field name="api_key"/>
+                        </group>
+                        <group>
+                            <field name="timeout"/>
+                            <field name="max_retries"/>
+                        </group>
+                    </group>
+                    <notebook>
+                        <page string="Models" name="models">
+                            <field name="model_ids" nolabel="1">
+                                <list>
+                                    <field name="sequence" widget="handle"/>
+                                    <field name="name"/>
+                                    <field name="identifier"/>
+                                    <field name="context_window"/>
+                                    <field name="active"/>
+                                </list>
+                            </field>
+                        </page>
+                    </notebook>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="ai_provider_instance_view_search" model="ir.ui.view">
+        <field name="name">ai.provider.instance.search</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="arch" type="xml">
+            <search string="Search AI Provider Instances">
+                <field name="name"/>
+                <field name="provider_type"/>
+                <field name="host"/>
+                <filter string="Archived" name="inactive" domain="[('active', '=', False)]"/>
+                <group expand="0" string="Group By">
+                    <filter string="Provider Type" name="group_by_type" context="{'group_by': 'provider_type'}"/>
+                </group>
+            </search>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="ai_provider_instance_action" model="ir.actions.act_window">
+        <field name="name">AI Provider Instances</field>
+        <field name="res_model">ai.provider.instance</field>
+        <field name="view_mode">list,form</field>
+        <field name="search_view_id" ref="ai_provider_instance_view_search"/>
+        <field name="context">{'company_id': False}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                Create your first AI provider instance
+            </p>
+            <p>
+                Configure AI provider instances to connect to different AI services.
+            </p>
+        </field>
+    </record>
+
+
+</odoo>
--- a/ai_integration/views/ai_provider_views.xml
+++ b/ai_integration/views/ai_provider_views.xml
@ -0,0 +1,88 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Tree View -->
+    <record id="ai_provider_view_tree" model="ir.ui.view">
+        <field name="name">ai.provider.tree</field>
+        <field name="model">ai.provider</field>
+        <field name="type">list</field>
+        <field name="arch" type="xml">
+            <list string="AI Providers" create="false">
+                <field name="name"/>
+                <field name="code"/>
+                <field name="default_host"/>
+                <field name="active"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Form View -->
+    <record id="ai_provider_view_form" model="ir.ui.view">
+        <field name="name">ai.provider.form</field>
+        <field name="model">ai.provider</field>
+        <field name="type">form</field>
+        <field name="arch" type="xml">
+            <form string="AI Provider">
+                <sheet>
+                    <div class="oe_button_box" name="button_box">
+                        <button name="test_connection" type="object"
+                                string="Test Connection" class="oe_stat_button"
+                                icon="fa-plug"/>
+                        <button name="get_models" type="object"
+                                string="Get Models" class="oe_stat_button"
+                                icon="fa-list"/>
+                    </div>
+                    <div class="oe_title">
+                        <label for="name" class="oe_edit_only"/>
+                        <h1><field name="name" placeholder="e.g. Ollama"/></h1>
+                    </div>
+                    <group>
+                        <group>
+                            <field name="code"/>
+                            <field name="default_host"/>
+                        </group>
+                        <group>
+                            <field name="active"/>
+                        </group>
+                    </group>
+                    <notebook>
+                        <page string="Description" name="description">
+                            <field name="description" nolabel="1" placeholder="Enter a description..."/>
+                        </page>
+                    </notebook>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="ai_provider_view_search" model="ir.ui.view">
+        <field name="name">ai.provider.search</field>
+        <field name="model">ai.provider</field>
+        <field name="type">search</field>
+        <field name="arch" type="xml">
+            <search string="Search AI Providers">
+                <field name="name"/>
+                <field name="code"/>
+                <filter string="Active" name="active" domain="[('active', '=', True)]"/>
+                <filter string="Archived" name="inactive" domain="[('active', '=', False)]"/>
+            </search>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="ai_provider_action" model="ir.actions.act_window">
+        <field name="name">AI Providers</field>
+        <field name="res_model">ai.provider</field>
+        <field name="view_mode">list,form</field>
+        <field name="context">{'search_default_active': 1}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                No AI providers found
+            </p>
+            <p>
+                AI providers are automatically created when you install AI integration modules.
+            </p>
+        </field>
+    </record>
+
+</odoo>
--- a/ai_integration/views/menu.xml
+++ b/ai_integration/views/menu.xml
@ -0,0 +1,51 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Top level menu -->
+    <menuitem id="menu_ai_root"
+              name="AI Integration"
+              web_icon="ai_integration,static/description/icon.png"
+              sequence="50"/>
+
+    <!-- Configuration menu -->
+    <menuitem id="menu_ai_config"
+              name="Configuration"
+              parent="menu_ai_root"
+              sequence="10"/>
+              
+    <!-- Settings menu -->
+    <menuitem id="menu_ai_settings"
+              name="Settings"
+              parent="menu_ai_config"
+              action="ai_integration.action_ai_integration_configuration"
+              sequence="10"
+              groups="base.group_system"/>
+              
+    <!-- Provider Types menu -->
+    <menuitem id="menu_ai_provider_types"
+              name="Provider Types"
+              parent="menu_ai_config"
+              action="ai_provider_action"
+              sequence="10"
+              groups="base.group_system"/>
+              
+    <!-- Provider Instances menu -->
+    <menuitem id="menu_ai_provider_instances"
+              name="Provider Instances"
+              parent="menu_ai_config"
+              action="ai_provider_instance_action"
+              sequence="20"/>
+              
+    <!-- AI Models menu -->
+    <menuitem id="menu_ai_models"
+              name="AI Models"
+              parent="menu_ai_config"
+              action="ai_model_action"
+              sequence="30"/>
+              
+    <!-- Statistics menu -->
+    <menuitem id="menu_ai_stats"
+              name="Model Statistics"
+              parent="menu_ai_config"
+              action="action_ai_model_stats"
+              sequence="40"/>
+</odoo>
--- a/ai_integration/views/res_company_views.xml
+++ b/ai_integration/views/res_company_views.xml
@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Add AI Integration to Settings Menu -->
+    <record id="action_ai_integration_configuration" model="ir.actions.act_window">
+        <field name="name">AI Integration</field>
+        <field name="type">ir.actions.act_window</field>
+        <field name="res_model">res.config.settings</field>
+        <field name="view_mode">form</field>
+        <field name="target">inline</field>
+        <field name="context">{'module': 'ai_integration'}</field>
+    </record>
+
+
+</odoo>
--- a/ai_integration/views/res_config_settings_views.xml
+++ b/ai_integration/views/res_config_settings_views.xml
@ -0,0 +1,66 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Settings Action -->
+    <record id="action_ai_integration_configuration" model="ir.actions.act_window">
+        <field name="name">AI Integration Settings</field>
+        <field name="type">ir.actions.act_window</field>
+        <field name="res_model">res.config.settings</field>
+        <field name="view_mode">form</field>
+        <field name="target">inline</field>
+        <field name="context">{"module" : "ai_integration"}</field>
+    </record>
+
+    <record id="res_config_settings_view_form" model="ir.ui.view">
+        <field name="name">res.config.settings.view.form.inherit.ai.integration</field>
+        <field name="model">res.config.settings</field>
+        <field name="inherit_id" ref="base.res_config_settings_view_form"/>
+        <field name="arch" type="xml">
+            <xpath expr="//form" position="inside">
+                <div class="app_settings_block" data-string="AI Integration" string="AI Integration" data-key="ai_integration">
+                    <h2>AI Integration</h2>
+                    <div class="row mt16 o_settings_container" name="ai_integration_setting_container">
+                        <div class="col-12 col-lg-6 o_setting_box" id="default_provider_settings">
+                            <div class="o_setting_left_pane"/>
+                            <div class="o_setting_right_pane">
+                                <span class="o_form_label">Default Provider Configuration</span>
+                                <div class="text-muted">
+                                    Configure the default AI provider instance and model for this company
+                                </div>
+                                <div class="content-group">
+                                    <div class="mt16 row">
+                                        <label for="default_provider_instance_id" class="col-lg-3 o_light_label"/>
+                                        <field name="default_provider_instance_id" options="{'no_create': True}"/>
+                                    </div>
+                                    <div class="mt16 row">
+                                        <label for="default_model_id" class="col-lg-3 o_light_label"/>
+                                        <field name="default_model_id" 
+                                               options="{'no_create': True}"
+                                               invisible="default_provider_instance_id == False"/>
+                                    </div>
+                                </div>
+                            </div>
+                        </div>
+                        
+                        <div class="col-12 col-lg-6 o_setting_box" id="batch_processing_settings">
+                            <div class="o_setting_left_pane"/>
+                            <div class="o_setting_right_pane">
+                                <span class="o_form_label">Batch Processing</span>
+                                <div class="text-muted">
+                                    Configure batch processing parameters for AI operations
+                                </div>
+                                <div class="content-group">
+                                    <div class="mt16 row">
+                                        <label for="ai_batch_size" class="col-lg-3 o_light_label"/>
+                                        <field name="ai_batch_size"/>
+                                    </div>
+                                </div>
+                            </div>
+                        </div>
+                    </div>
+
+
+                </div>
+            </xpath>
+        </field>
+    </record>
+</odoo>
--- a/ai_integration_ollama_api/init.py
+++ b/ai_integration_ollama_api/init.py
@ -0,0 +1 @@
+from . import models
--- a/ai_integration_ollama_api/manifest.py
+++ b/ai_integration_ollama_api/manifest.py
@ -0,0 +1,36 @@
+{
+    'name': 'Ollama Integration',
+    'version': '1.0.0',
+    'category': 'Technical',
+    'summary': 'Integration with Ollama AI models',
+    'description': """
+Ollama Integration
+==================
+This module provides integration with Ollama, allowing you to use local AI models
+in your Odoo instance. Features include:
+
+* Connection to local Ollama server
+* Support for all Ollama models
+* Automatic model discovery and synchronization
+* Configurable model parameters
+""",
+    'author': 'Bemade',
+    'website': 'https://www.bemade.org',
+    'depends': [
+        'ai_integration'
+    ],
+    'data': [
+        'data/ai_provider_data.xml',
+        'data/ai_provider_instance_data.xml',
+        'views/ollama_stats_views.xml',
+        'views/ai_provider_instance_views.xml',
+        'security/ir.model.access.csv',
+    ],
+    'external_dependencies': {
+        'python': ['requests'],
+    },
+    'installable': True,
+    'application': False,
+    'auto_install': False,
+    'license': 'LGPL-3',
+}
--- a/ai_integration_ollama_api/data/ai_provider_data.xml
+++ b/ai_integration_ollama_api/data/ai_provider_data.xml
@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="1">
+        <!-- Ollama Provider -->
+        <record id="ai_provider_ollama" model="ai.provider">
+            <field name="name">Ollama</field>
+            <field name="code">ollama</field>
+            <field name="description">Ollama is a local AI model provider that allows you to run various open-source models locally.</field>
+            <field name="default_host">http://localhost:11434</field>
+            <field name="active" eval="True"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration_ollama_api/data/ai_provider_instance_data.xml
+++ b/ai_integration_ollama_api/data/ai_provider_instance_data.xml
@ -0,0 +1,31 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="1">
+        <!-- Default Ollama Provider Instance -->
+        <record id="ai_provider_instance_ollama_default" model="ai.provider.instance">
+            <field name="name">Ollama Local</field>
+            <field name="provider_type">ollama</field>
+            <field name="host">http://localhost:11434</field>
+            <field name="model_name">llama3.2</field>
+            <field name="temperature">0.7</field>
+            <field name="top_k">40</field>
+            <field name="top_p">0.9</field>
+            <field name="repeat_penalty">1.1</field>
+            <field name="num_ctx">4096</field>
+            <field name="num_predict">1024</field>
+            <field name="min_p">0.05</field>
+            <field name="repeat_last_n">64</field>
+            <field name="seed">0</field>
+            <field name="num_gpu">1</field>
+            <field name="num_thread">8</field>
+            <field name="mirostat">0</field>
+            <field name="mirostat_tau">5.0</field>
+            <field name="mirostat_eta">0.1</field>
+            <field name="num_batch">8</field>
+            <field name="num_keep">0</field>
+            <field name="tfs_z">1.0</field>
+            <field name="skip_special_tokens" eval="True"/>
+            <field name="active" eval="True"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration_ollama_api/data/ir_model_inherit.xml
+++ b/ai_integration_ollama_api/data/ir_model_inherit.xml
@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="1">
+        <!-- Declare model inheritance -->
+        <record id="ollama_provider_inherit" model="ir.model.inherit">
+            <field name="model">ai.provider.ollama</field>
+            <field name="parent_id" ref="ai_integration.model_ai_provider_interface"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration_ollama_api/data/ollama_provider.xml
+++ b/ai_integration_ollama_api/data/ollama_provider.xml
@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="1">
+        <!-- Register Ollama Provider -->
+        <record id="ai_provider_ollama" model="ai.provider">
+            <field name="name">Ollama</field>
+            <field name="code">ollama</field>
+            <field name="description">Local AI models powered by Ollama</field>
+            <field name="default_host">http://localhost:11434</field>
+            <field name="active" eval="True"/>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration_ollama_api/doc/ollama_api.md
+++ b/ai_integration_ollama_api/doc/ollama_api.md
--- a/ai_integration_ollama_api/migrations/1.0.0/post-migration.py
+++ b/ai_integration_ollama_api/migrations/1.0.0/post-migration.py
@ -0,0 +1,17 @@
+def migrate(cr, version):
+    # Add num_predict column if it doesn't exist
+    cr.execute("""
+        DO $$
+        BEGIN
+            IF NOT EXISTS (
+                SELECT 1 
+                FROM information_schema.columns 
+                WHERE table_name='ai_provider_instance' 
+                AND column_name='num_predict'
+            ) THEN
+                ALTER TABLE ai_provider_instance 
+                ADD COLUMN num_predict integer DEFAULT 1024;
+            END IF;
+        END
+        $$;
+    """)
--- a/ai_integration_ollama_api/models/init.py
+++ b/ai_integration_ollama_api/models/init.py
@ -0,0 +1,27 @@
+"""Ollama AI Integration Models Package.
+
+This package contains all the model definitions required for integrating
+Ollama AI with Odoo's AI framework. The models are loaded in a specific
+order to handle dependencies correctly.
+
+Module Structure:
+1. ollama_provider_mixin - Base configuration and parameter definitions
+2. ollama_provider - Core Ollama API integration implementation
+3. ollama_model_stats - Usage statistics and performance tracking
+4. ai_provider_instance - Instance-specific configuration and management
+
+Note: The import order is important to avoid circular dependencies.
+"""
+
+# Base Configuration
+from . import ollama_provider_mixin
+
+# Core Implementation
+from . import ollama_provider
+from . import ai_provider_instance
+
+# Statistics and Monitoring
+from . import ollama_model_stats
+
+# Instance Management
+from . import ai_provider_instance
--- a/ai_integration_ollama_api/models/ai_provider_instance.py
+++ b/ai_integration_ollama_api/models/ai_provider_instance.py
@ -0,0 +1,153 @@
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+import requests
+
+class OllamaAIProviderInstance(models.Model):
+    """Extends the AI Provider Instance model to support Ollama-specific configuration.
+    
+    This model inherits from both ai.provider.instance and ollama.provider.mixin to:
+    1. Add Ollama-specific fields (num_ctx, temperature, etc.)
+    2. Handle field visibility based on provider_type
+    3. Manage field cleanup when switching providers
+    """
+    _inherit = ['ai.provider.instance', 'ollama.provider.mixin']
+    _name = 'ai.provider.instance'
+    _description = 'Ollama AI Provider Instance'
+
+    # Override provider_type to add Ollama option
+    provider_type = fields.Selection(
+        selection_add=[('ollama', 'Ollama')],
+        ondelete={'ollama': lambda r: r.write({'provider_type': 'none'})}
+    )
+    
+    @api.onchange('provider_type')
+    def _onchange_provider_type(self):
+        """Handle provider type changes.
+        
+        When switching to 'ollama':
+        - Set default host if empty
+        
+        When switching away from 'ollama':
+        - Clear Ollama-specific fields
+        """
+        if self.provider_type == 'ollama':
+            if not self.host:
+                self.host = 'http://localhost:11434'
+        else:
+            # Clear Ollama-specific fields
+            self.update({
+                'num_ctx': False,  # Context length
+                'temperature': False,  # Sampling temperature
+                'top_p': False,  # Nucleus sampling threshold
+                'top_k': False,  # Top-k sampling threshold
+                'repeat_penalty': False,  # Penalty for repeated tokens
+                'repeat_last_n': False,  # Number of tokens to consider for repeat penalty
+                'num_thread': False,  # Number of CPU threads to use
+                'num_gpu': False,  # Number of GPUs to use
+                'num_batch': False,  # Batch size for inference
+                'model_name': False,  # Model name/path
+            })
+    
+    # Override default host for Ollama
+    host = fields.Char(
+        default='http://localhost:11434',
+        help='Ollama server host URL')
+
+    def test_connection(self):
+        """Test the connection to the Ollama server.
+        
+        This method attempts to connect to the Ollama server and verify
+        that it is responding correctly. It will raise a user-friendly
+        error if the connection fails.
+        
+        Returns:
+            dict: Action to display success message
+        """
+        self.ensure_one()
+        if self.provider_type != 'ollama':
+            return
+            
+        try:
+            # Try to list models as a basic connectivity test
+            response = requests.get(f'{self.host}/api/tags')
+            response.raise_for_status()
+            return {
+                'type': 'ir.actions.client',
+                'tag': 'display_notification',
+                'params': {
+                    'title': _('Success'),
+                    'message': _('Successfully connected to Ollama server'),
+                    'sticky': False,
+                    'type': 'success',
+                }
+            }
+        except Exception as e:
+            raise UserError(_('Connection test failed: %s', str(e)))
+
+    def sync_models(self):
+        """Synchronize available models from the Ollama server.
+        
+        This method fetches the list of available models from the Ollama
+        server and creates or updates the corresponding AI model records
+        in Odoo.
+        
+        Returns:
+            dict: Action to display success message
+        """
+        self.ensure_one()
+        if self.provider_type != 'ollama':
+            return
+            
+        try:
+            # Get models from Ollama API
+            response = requests.get(f'{self.host}/api/tags')
+            response.raise_for_status()
+            
+            # Parse response
+            models = [{
+                'name': model['name'],
+                'id': model['name'],
+            } for model in response.json()['models']]
+            
+            for model_data in models:
+                # Create or update AI model record
+                vals = {
+                    'name': model_data['name'],
+                    'identifier': model_data['id'],
+                    'provider_instance_id': self.id,
+                    'active': True,
+                }
+                # Search for existing model
+                existing = self.env['ai.model'].search([
+                    ('identifier', '=', model_data['id']),
+                    ('provider_instance_id', '=', self.id)
+                ], limit=1)
+                
+                if existing:
+                    existing.write(vals)
+                else:
+                    self.env['ai.model'].create(vals)
+            
+            # Invalidate the cache to force reload of related records
+            self.invalidate_recordset(['model_ids'])
+            
+            # Return action to reload the view completely
+            return {
+                'type': 'ir.actions.act_window',
+                'res_model': 'ai.provider.instance',
+                'res_id': self.id,
+                'view_mode': 'form',
+                'target': 'current',
+                'flags': {
+                    'mode': 'readonly',
+                    'reload': True,  # Force reload
+                },
+                'context': {'notification': {
+                    'type': 'success',
+                    'title': _('Success'),
+                    'message': _('Successfully synchronized %d models', len(models)),
+                    'sticky': False,
+                }}
+            }
+        except Exception as e:
+            raise UserError(_('Model synchronization failed: %s', str(e)))
--- a/ai_integration_ollama_api/models/ai_provider_ollama.py.bak
+++ b/ai_integration_ollama_api/models/ai_provider_ollama.py.bak
@ -0,0 +1,35 @@
+from odoo import models, fields, api, _
+from .ollama_provider_mixin import OllamaProviderMixin
+
+class OllamaAIProvider(models.Model, OllamaProviderMixin):
+    _name = 'ai.provider.ollama'
+    _description = 'Ollama AI Provider'
+    _inherit = ['ai.provider.interface']
+
+    provider_type = fields.Selection(
+        selection=[('ollama', 'Ollama')],
+        default='ollama',
+        required=True,
+        help='Type of AI provider')
+    
+    # Ollama-specific Parameters
+    host = fields.Char(
+        string='Host',
+        default='http://localhost:11434',
+        required=True,
+        help='Ollama server host URL')
+    
+    def _get_available_models(self):
+        """Get list of available models from Ollama server."""
+        # TODO: Implement model discovery
+        return []
+
+    def _generate_text(self, prompt, **kwargs):
+        """Generate text using Ollama model."""
+        # TODO: Implement text generation
+        return ""
+
+    def _embed_text(self, text, **kwargs):
+        """Generate embeddings for text using Ollama model."""
+        # TODO: Implement text embedding
+        return []
--- a/ai_integration_ollama_api/models/ollama_model_stats.py
+++ b/ai_integration_ollama_api/models/ollama_model_stats.py
@ -0,0 +1,116 @@
+from odoo import models, fields, api
+from datetime import datetime, timedelta
+
+class OllamaModelStats(models.Model):
+    """Tracks and stores daily usage statistics for Ollama AI models.
+    
+    This model maintains detailed daily statistics for each Ollama model,
+    including request counts, token usage, response times, and error rates.
+    It inherits from ai.model.stats for base statistics functionality.
+    
+    Key Features:
+    - Daily usage tracking per model
+    - Performance metrics collection
+    - Error rate monitoring
+    - Version tracking for model updates
+    
+    Technical Details:
+    - One stat entry per model per day (enforced by SQL constraint)
+    - Automatic version tracking from Ollama API
+    - Aggregated statistics calculation
+    - Ordered by date for easy historical analysis
+    """
+    _name = 'ollama.model.stats'
+    _description = 'Ollama Model Usage Statistics'
+    _inherit = ['ai.model.stats']
+    _order = 'date desc'  # Most recent stats first
+
+    model_id = fields.Many2one('ai.model', string='Model', required=True, ondelete='cascade')
+    date = fields.Date(string='Date', required=True, default=fields.Date.context_today)
+    request_count = fields.Integer(string='Number of Requests', default=0)
+    token_count = fields.Integer(string='Total Tokens', default=0)
+    avg_response_time = fields.Float(string='Average Response Time (ms)', digits=(10, 2), default=0)
+    error_count = fields.Integer(string='Number of Errors', default=0)
+    version = fields.Char(string='Model Version', help='Version of the model when stats were recorded')
+
+    _sql_constraints = [
+        ('unique_model_date', 'unique(model_id, date)', 'Only one stat entry per model per day is allowed.')
+    ]
+
+    def _update_stats(self, model, tokens, response_time, error=False):
+        """Update daily statistics for a specific model.
+        
+        This method handles the creation or update of daily statistics entries.
+        It maintains running averages and cumulative counts for various metrics.
+        
+        Args:
+            model (ai.model): The model record being tracked
+            tokens (int): Number of tokens in the current request
+            response_time (float): Response time in milliseconds
+            error (bool): Whether this request resulted in an error
+            
+        Technical Notes:
+            - Creates new stat entry if none exists for today
+            - Updates running averages for response time
+            - Fetches and stores model version from Ollama API
+            - Maintains cumulative counts for requests and errors
+        """
+        today = fields.Date.context_today(self)
+        stats = self.search([
+            ('model_id', '=', model.id),
+            ('date', '=', today)
+        ])
+
+        if not stats:
+            # Get model version
+            version = self.env['ai.provider.ollama']._get_model_info(
+                model.provider_instance_id, 
+                model.identifier
+            ).get('details', {}).get('sha256', '')[:8]  # First 8 chars of SHA
+
+            stats = self.create({
+                'model_id': model.id,
+                'date': today,
+                'version': version
+            })
+
+        # Update statistics
+        new_count = stats.request_count + 1
+        new_tokens = stats.token_count + tokens
+        new_time = ((stats.avg_response_time * stats.request_count) + response_time) / new_count
+        new_errors = stats.error_count + (1 if error else 0)
+
+        stats.write({
+            'request_count': new_count,
+            'token_count': new_tokens,
+            'avg_response_time': new_time,
+            'error_count': new_errors
+        })
+
+    @api.model
+    def get_model_stats(self, model_id, days=30):
+        """Get statistics for a model over the specified number of days."""
+        start_date = fields.Date.today() - timedelta(days=days)
+        stats = self.search([
+            ('model_id', '=', model_id),
+            ('date', '>=', start_date)
+        ])
+        
+        return {
+            'daily_stats': [{
+                'date': stat.date,
+                'requests': stat.request_count,
+                'tokens': stat.token_count,
+                'response_time': stat.avg_response_time,
+                'errors': stat.error_count,
+                'version': stat.version
+            } for stat in stats],
+            'summary': {
+                'total_requests': sum(stat.request_count for stat in stats),
+                'total_tokens': sum(stat.token_count for stat in stats),
+                'avg_response_time': sum(stat.avg_response_time * stat.request_count for stat in stats) / 
+                                   (sum(stat.request_count for stat in stats) if stats else 1),
+                'total_errors': sum(stat.error_count for stat in stats),
+                'versions_used': list(set(stat.version for stat in stats if stat.version))
+            }
+        }
--- a/ai_integration_ollama_api/models/ollama_provider.py
+++ b/ai_integration_ollama_api/models/ollama_provider.py
@ -0,0 +1,324 @@
+import json
+import logging
+import requests
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+
+_logger = logging.getLogger(__name__)
+
+class OllamaProvider(models.Model):
+    """Main Ollama AI Provider implementation.
+    
+    This model implements the core functionality for interacting with Ollama's API,
+    including model management, text generation, and error handling.
+    
+    Key Responsibilities:
+    - Model discovery and validation
+    - API communication and error handling
+    - Request formatting and response parsing
+    - Resource management and cleanup
+    
+    Technical Details:
+    - Implements the ai.provider.interface for standardized AI provider integration
+    - Uses Ollama's HTTP API for all operations
+    - Handles both synchronous and asynchronous requests
+    - Provides detailed error messages for troubleshooting
+    """
+    _name = 'ai.provider.ollama'
+    _description = 'Ollama AI Provider'
+    _inherit = ['ai.provider.interface']
+    
+    @api.model
+    def _get_models(self, instance):
+        """Get list of available models from Ollama server.
+        
+        Args:
+            instance (ai.provider.instance): Provider instance to get models for
+            
+        Returns:
+            list: List of model dictionaries with keys:
+                - name: Model name
+                - id: Model identifier
+                - details: Additional model metadata
+                
+        Raises:
+            UserError: If unable to connect or retrieve models
+        """
+        try:
+            response = requests.get(f"{instance.host}/api/tags")
+            response.raise_for_status()
+            
+            models_data = response.json().get('models', [])
+            return [{
+                'name': model['name'],
+                'id': model['name'],
+                'details': model
+            } for model in models_data]
+            
+        except requests.exceptions.RequestException as e:
+            raise UserError(_('Failed to connect to Ollama server: %s', str(e)))
+        except (KeyError, ValueError) as e:
+            raise UserError(_('Invalid response from Ollama server: %s', str(e)))
+
+    # API Configuration
+    timeout = fields.Integer(
+        string='Timeout',
+        default=30,
+        help='API request timeout in seconds')
+
+    def _get_provider_type(self):
+        return 'ollama'
+
+    def _get_model_info(self, instance, model_name):
+        """Get detailed information about a specific model."""
+        try:
+            response = requests.post(
+                f"{instance.host}/api/show",
+                json={'name': model_name}
+            )
+            if response.status_code == 200:
+                return response.json()
+            else:
+                _logger.error(
+                    "Failed to get model info for %s. Status: %s, Error: %s",
+                    model_name, response.status_code, response.text
+                )
+                return None
+        except requests.exceptions.RequestException as e:
+            _logger.error("Error getting model info: %s", str(e))
+            return None
+
+    def pull_model(self, instance, model_name):
+        """Pull a model from Ollama."""
+        try:
+            # Start the pull
+            response = requests.post(
+                f"{instance.host}/api/pull",
+                json={'name': model_name},
+                stream=True  # Enable streaming for progress updates
+            )
+
+            if response.status_code != 200:
+                raise UserError(_("Failed to pull model %s: %s") % 
+                              (model_name, response.text))
+
+            # Process the streaming response
+            for line in response.iter_lines():
+                if line:
+                    try:
+                        progress = json.loads(line)
+                        status = progress.get('status')
+                        if status:
+                            _logger.info(
+                                "Pulling model %s: %s",
+                                model_name, status
+                            )
+                    except json.JSONDecodeError:
+                        continue
+
+            return True
+
+        except requests.exceptions.RequestException as e:
+            raise UserError(_("Error pulling model %s: %s") % 
+                          (model_name, str(e)))
+
+    def delete_model(self, instance, model_name):
+        """Delete a model from Ollama."""
+        try:
+            response = requests.delete(
+                f"{instance.host}/api/delete",
+                json={'name': model_name}
+            )
+
+            if response.status_code != 200:
+                raise UserError(_("Failed to delete model %s: %s") % 
+                              (model_name, response.text))
+
+            return True
+
+        except requests.exceptions.RequestException as e:
+            raise UserError(_("Error deleting model %s: %s") % 
+                          (model_name, str(e)))
+
+    def test_connection(self, instance):
+        """Test the connection to the Ollama server."""
+        try:
+            response = requests.get(f"{instance.host}/api/tags")
+            if response.status_code != 200:
+                raise UserError(_(
+                    "Failed to connect to Ollama server. Status code: %s. Error: %s",
+                    response.status_code, response.text
+                ))
+            return True
+        except requests.exceptions.RequestException as e:
+            raise UserError(_(
+                "Failed to connect to Ollama server: %s", str(e)
+            ))
+
+    def _format_chat_messages(self, messages):
+        """Format chat messages for Ollama API."""
+        formatted_prompt = ""
+        for message in messages:
+            role = message.get('role', 'user')
+            content = message.get('content', '')
+            
+            if role == 'system':
+                formatted_prompt += f"<system>{content}</system>\n"
+            elif role == 'assistant':
+                formatted_prompt += f"Assistant: {content}\n"
+            else:  # user
+                formatted_prompt += f"Human: {content}\n"
+        
+        return formatted_prompt.strip()
+
+    def generate_response(self, instance, model, messages, **kwargs):
+        """Generate a response using the chat completion API."""
+        try:
+            # Format messages into Ollama's expected format
+            prompt = self._format_chat_messages(messages)
+            
+            # Get model options from instance
+            options = instance._get_provider_options()
+            
+            # Prepare the request payload
+            payload = {
+                'model': model.identifier,
+                'prompt': prompt,
+                'stream': False,
+                **options
+            }
+            
+            # Make the API call
+            response = requests.post(
+                f"{instance.host}/api/generate",
+                json=payload
+            )
+            
+            if response.status_code != 200:
+                raise UserError(_("Failed to generate response: %s") % response.text)
+            
+            response_data = response.json()
+            generated_text = response_data.get('response', '')
+            
+            # Update statistics
+            total_tokens = response_data.get('eval_count', 0)
+            response_time = response_data.get('total_duration', 0)
+            version = self._get_model_info(instance, model.identifier)\
+                .get('details', {}).get('sha256', '')[:8]
+            self._track_model_usage(
+                model, total_tokens, response_time, version=version
+            )
+            
+            # Return the response in a standardized format
+            return {
+                'content': generated_text,
+                'role': 'assistant',
+                'metadata': {
+                    'eval_count': response_data.get('eval_count'),
+                    'eval_duration': response_data.get('eval_duration'),
+                    'total_duration': response_data.get('total_duration'),
+                    'load_duration': response_data.get('load_duration'),
+                }
+            }
+            
+        except requests.exceptions.RequestException as e:
+            # Log error in statistics
+            if model:
+                self._track_model_usage(model, error=True)
+            raise UserError(_("Error generating response: %s") % str(e))
+
+    def sync_models(self, instance):
+        """Synchronize available models from the Ollama server."""
+        self.test_connection(instance)
+
+        try:
+            response = requests.get(f"{instance.host}/api/tags")
+            models_data = response.json().get('models', [])
+
+            # Get existing models for this instance
+            existing_models = self.env['ai.model'].search([
+                ('provider_instance_id', '=', instance.id)
+            ])
+            existing_identifiers = {m.identifier: m for m in existing_models}
+
+            for model_data in models_data:
+                identifier = model_data.get('name')
+                if not identifier:
+                    continue
+
+                # Get model details
+                model_info = self._get_model_info(instance, identifier)
+                model_details = model_info.get('details', {})
+                
+                model_values = {
+                    'name': identifier.title(),
+                    'identifier': identifier,
+                    'provider_instance_id': instance.id,
+                    'company_id': instance.company_id.id,
+                    'active': True,
+                    'description': f"Ollama model: {identifier}\\nSize: {model_data.get('size', 'Unknown')}\\nModified: {model_data.get('modified', 'Unknown')}",
+                }
+
+                if identifier in existing_identifiers:
+                    # Update existing model
+                    existing_identifiers[identifier].write(model_values)
+                    del existing_identifiers[identifier]
+                else:
+                    # Create new model
+                    self.env['ai.model'].create(model_values)
+
+            # Deactivate models that no longer exist
+            for model in existing_identifiers.values():
+                model.active = False
+
+            return True
+
+        except requests.exceptions.RequestException as e:
+            raise UserError(_(
+                "Failed to sync models from Ollama server: %s", str(e)
+            ))
+
+    def send_message(self, message, model, **kwargs):
+        """Send a message to the Ollama server."""
+        instance = model.provider_instance_id
+        
+        try:
+            # Prepare the request payload
+            payload = {
+                'model': model.identifier,
+                'prompt': message.get('content', ''),
+                'stream': False,
+                'options': kwargs.get('options', {}),
+            }
+
+            # Add system message if provided
+            if message.get('role') == 'system':
+                payload['system'] = message['content']
+
+            # Send the request
+            response = requests.post(
+                f"{instance.host}/api/generate",
+                json=payload,
+                timeout=(instance.timeout or 30)
+            )
+
+            if response.status_code != 200:
+                raise UserError(_(
+                    "Ollama server error. Status code: %s. Error: %s",
+                    response.status_code, response.text
+                ))
+
+            result = response.json()
+            return result.get('response', '')
+
+        except requests.exceptions.Timeout:
+            raise UserError(_("Request to Ollama server timed out"))
+        except requests.exceptions.RequestException as e:
+            raise UserError(_(
+                "Error communicating with Ollama server: %s", str(e)
+            ))
+        except Exception as e:
+            _logger.error("Unexpected error in Ollama provider: %s", str(e))
+            raise UserError(_(
+                "Unexpected error in Ollama provider: %s", str(e)
+            ))
--- a/ai_integration_ollama_api/models/ollama_provider_mixin.py
+++ b/ai_integration_ollama_api/models/ollama_provider_mixin.py
@ -0,0 +1,274 @@
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+import requests
+import logging
+import json
+
+_logger = logging.getLogger(__name__)
+
+class OllamaProviderMixin(models.AbstractModel):
+    """Mixin model that provides Ollama-specific configuration parameters.
+    
+    This mixin is designed to be inherited by models that need to interact with
+    the Ollama AI provider. It provides all the necessary fields and methods
+    for configuring and interacting with Ollama's API.
+    
+    Key Features:
+    - Provider type selection and validation
+    - Context window configuration
+    - Advanced sampling parameters (temperature, top-k, top-p)
+    - Token generation controls
+    
+    Technical Details:
+    - Inherits from ai.generation.params for base AI generation parameters
+    - Implements Ollama-specific API parameters
+    - Provides default values optimized for general use cases
+    """
+    _name = 'ollama.provider.mixin'
+    _description = 'Ollama Provider Configuration Mixin'
+    _inherit = ['ai.generation.params']
+
+    # Model Parameters
+    model_name = fields.Char(
+        string='Model Name',
+        help='Name of the Ollama model to use (e.g. llama2, mistral, codellama)',
+        required=True,
+        default='deepseek-r1:32b')
+        
+    # Context Window Configuration
+    num_ctx = fields.Integer(
+        string='Context Length',
+        help='Maximum number of tokens to consider for context. A larger context window allows '
+             'the model to access more historical information but requires more memory. '
+             'Range: [0 - 32768].',
+        default=8192)
+        
+    # Generation Parameters
+    temperature = fields.Float(
+        string='Temperature',
+        help='Controls randomness in the output. Higher values make the output more random, '
+             'while lower values make it more focused and deterministic. '
+             'Range: [0.0 - 2.0]',
+        default=0.7)
+        
+    top_p = fields.Float(
+        string='Top P (Nucleus Sampling)',
+        help='Limits the cumulative probability of tokens to sample from. Only the most likely '
+             'tokens with total probability mass of top_p are considered. '
+             'Range: [0.0 - 1.0].',
+        default=0.9)
+    
+    top_k = fields.Integer(
+        string='Top K',
+        help='Limits the cumulative probability of tokens to sample from. Only the top K '
+             'most likely tokens are considered for sampling at each step. '
+             'Range: [1 - 100].',
+        default=40)
+    
+    min_p = fields.Float(
+        string='Min P',
+        help='Sets a minimum probability threshold for token selection. Range: [0.0 - 1.0].',
+        default=0.05,
+        digits=(3, 2))
+    
+    repeat_penalty = fields.Float(
+        string='Repeat Penalty',
+        help='Penalty for repeating tokens. Range: [1.0 - 2.0]. Higher values make repetition less likely.',
+        default=1.1,
+        digits=(3, 2))
+    
+    # Advanced Configuration
+    stop_sequences = fields.Char(
+        string='Stop Sequences',
+        help='Comma-separated list of sequences where the model should stop generating further tokens.')
+    
+    num_predict = fields.Integer(
+        string='Maximum Tokens',
+        help='Maximum number of tokens to predict. Set to -1 for unlimited.',
+        default=2048)
+    
+    repeat_last_n = fields.Integer(
+        string='Repeat Last N',
+        help='Sets the context window for repeat penalty. Range: [0 - 4096]. Default is 64, 0 disables.',
+        default=64
+    )
+    
+    def generate_text(self, prompt, **kwargs):
+        """Generate text using the Ollama API.
+        
+        Args:
+            prompt (str): The prompt to generate text from
+            **kwargs: Additional parameters to pass to the API
+            
+        Returns:
+            str: The generated text
+        """
+        self.ensure_one()
+        
+        # Prepare the request
+        url = f"{self.host}/api/generate"
+        
+        # Build the request data
+        data = {
+            'model': self.model_name,
+            'prompt': prompt,
+            'stream': False,
+            'num_ctx': self.num_ctx,
+            'temperature': self.temperature,
+            'top_k': self.top_k,
+            'top_p': self.top_p,
+            'repeat_penalty': self.repeat_penalty,
+            'repeat_last_n': self.repeat_last_n,
+            'num_predict': self.num_predict,
+            'min_p': self.min_p,
+            'seed': self.seed,
+            'num_gpu': self.num_gpu,
+            'num_thread': self.num_thread,
+            'mirostat': int(self.mirostat),
+            'mirostat_tau': self.mirostat_tau,
+            'mirostat_eta': self.mirostat_eta,
+            'num_batch': self.num_batch,
+            'num_keep': self.num_keep,
+            'tfs_z': self.tfs_z,
+            'skip_special_tokens': self.skip_special_tokens
+        }
+        
+        # Add any additional parameters
+        if kwargs:
+            data.update(kwargs)
+            
+        # Make the request
+        try:
+            _logger = logging.getLogger(__name__)
+            _logger.info("Sending request to Ollama API with data: %s", data)
+            
+            response = requests.post(url, json=data, timeout=self.timeout)
+            response.raise_for_status()
+            
+            # Log the raw response
+            _logger.info("Raw API response: %s", response.text)
+            
+            # Parse the response
+            result = response.json()
+            response_text = result.get('response', '')
+            
+            # Si la réponse est une chaîne JSON, la parser
+            try:
+                if isinstance(response_text, str):
+                    parsed_response = json.loads(response_text)
+                    _logger.info("Parsed nested JSON response: %s", parsed_response)
+                    return parsed_response
+                else:
+                    _logger.info("Direct response: %s", response_text)
+                    return response_text
+            except json.JSONDecodeError:
+                # Si ce n'est pas du JSON valide, retourner le texte tel quel
+                _logger.info("Non-JSON response: %s", response_text)
+                return response_text
+            
+        except requests.exceptions.RequestException as e:
+            raise UserError(_('Failed to generate text: %s') % str(e))
+    
+    # Advanced Generation Parameters
+    seed = fields.Integer(
+        string='Random Seed',
+        help='Sets the random seed for generation. Range: [0 - 2147483647]. Use 0 for random.',
+        default=0)
+    
+    num_gpu = fields.Integer(
+        string='Number of GPUs',
+        help='Number of GPUs to use for generation. Range: [0 - 8]. 0 means CPU only.',
+        default=1)
+    
+    num_thread = fields.Integer(
+        string='Number of Threads',
+        help='Number of CPU threads to use for generation. Range: [1 - 32].',
+        default=8)
+    
+    mirostat = fields.Selection([
+        ('0', 'Disabled'),
+        ('1', 'Mirostat'),
+        ('2', 'Mirostat 2.0')],
+        string='Mirostat Mode',
+        help='Enable Mirostat sampling for controlling perplexity',
+        default='0')
+    
+    mirostat_tau = fields.Float(
+        string='Mirostat Tau',
+        help='Mirostat target entropy. Range: [0.0 - 10.0].',
+        default=5.0,
+        digits=(3, 2))
+    
+    mirostat_eta = fields.Float(
+        string='Mirostat Eta',
+        help='Mirostat learning rate. Range: [0.0 - 1.0].',
+        default=0.1,
+        digits=(3, 2))
+    
+    # Ollama-specific Response Control
+    
+    tfs_z = fields.Float(
+        string='Tail Free Sampling Z',
+        help='Tail free sampling parameter. Range: [0.0 - 2.0]. Higher value = more focused.',
+        default=1.0,
+        digits=(3, 2))
+    
+    # System Settings
+    num_batch = fields.Integer(
+        string='Batch Size',
+        help='Number of prompts to batch together',
+        default=8)
+    
+    num_keep = fields.Integer(
+        string='Keep Last N Tokens',
+        help='Number of tokens to keep from initial prompt',
+        default=0)
+    
+    skip_special_tokens = fields.Boolean(
+        string='Skip Special Tokens',
+        help='Skip special tokens in generation',
+        default=True)
+    
+    @api.model
+    def default_get(self, fields_list):
+        defaults = super().default_get(fields_list)
+        if 'provider_type' in fields_list:
+            defaults['provider_type'] = 'ollama'
+        if 'host' in fields_list and not defaults.get('host'):
+            defaults['host'] = 'http://localhost:11434'
+        return defaults
+    
+    def _get_provider_options(self):
+        """Get Ollama-specific options for API calls."""
+        self.ensure_one()
+        options = {
+            'model': self.model_name,
+            'temperature': self.temperature,
+            'num_ctx': self.num_ctx,
+            'num_predict': self.num_predict,
+            'top_k': self.top_k,
+            'top_p': self.top_p,
+            'min_p': self.min_p,
+            'repeat_penalty': self.repeat_penalty,
+            'repeat_last_n': self.repeat_last_n,
+            'seed': self.seed,
+            'num_gpu': self.num_gpu,
+            'num_thread': self.num_thread,
+            'mirostat': int(self.mirostat),
+            'mirostat_tau': self.mirostat_tau,
+            'mirostat_eta': self.mirostat_eta,
+            'num_batch': self.num_batch,
+            'num_keep': self.num_keep,
+            'tfs_z': self.tfs_z,
+            'skip_special_tokens': self.skip_special_tokens,
+            'stream': False
+        }
+        
+        if self.stop_sequences:
+            options['stop'] = [
+                seq.strip()
+                for seq in self.stop_sequences.split(',')
+                if seq.strip()
+            ]
+            
+        return options
--- a/ai_integration_ollama_api/security/ir.model.access.csv
+++ b/ai_integration_ollama_api/security/ir.model.access.csv
@ -0,0 +1,5 @@
+id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink
+access_ollama_model_stats_user,ollama.model.stats.user,model_ollama_model_stats,base.group_user,1,0,0,0
+access_ollama_model_stats_manager,ollama.model.stats.manager,model_ollama_model_stats,base.group_system,1,1,1,1
+access_ai_provider_ollama_user,ai.provider.ollama.user,model_ai_provider_ollama,base.group_user,1,0,0,0
+access_ai_provider_ollama_manager,ai.provider.ollama.manager,model_ai_provider_ollama,base.group_system,1,1,1,1
--- a/ai_integration_ollama_api/views/ai_provider_instance_views.xml
+++ b/ai_integration_ollama_api/views/ai_provider_instance_views.xml
@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Inherit AI Provider Instance List View -->
+    <record id="ollama_ai_provider_instance_view_list" model="ir.ui.view">
+        <field name="name">ai.provider.instance.list.ollama</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="inherit_id" ref="ai_integration.ai_provider_instance_view_list"/>
+        <field name="mode">primary</field>
+        <field name="arch" type="xml">
+            <xpath expr="//list[@name='ai_instance']" position="attributes">
+                <attribute name="create">true</attribute>
+            </xpath>
+        </field>
+    </record>
+</odoo>
--- a/ai_integration_ollama_api/views/ollama_stats_views.xml
+++ b/ai_integration_ollama_api/views/ollama_stats_views.xml
@ -0,0 +1,118 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- List View -->
+    <record id="view_ollama_model_stats_list" model="ir.ui.view">
+        <field name="name">ollama.model.stats.list</field>
+        <field name="model">ollama.model.stats</field>
+        <field name="arch" type="xml">
+            <list string="Model Statistics">
+                <field name="date"/>
+                <field name="model_id"/>
+                <field name="version"/>
+                <field name="request_count"/>
+                <field name="token_count"/>
+                <field name="avg_response_time"/>
+                <field name="error_count"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Form View -->
+    <record id="view_ollama_model_stats_form" model="ir.ui.view">
+        <field name="name">ollama.model.stats.form</field>
+        <field name="model">ollama.model.stats</field>
+        <field name="arch" type="xml">
+            <form string="Model Statistics">
+                <sheet>
+                    <group>
+                        <group>
+                            <field name="date"/>
+                            <field name="model_id"/>
+                            <field name="version"/>
+                        </group>
+                        <group>
+                            <field name="request_count"/>
+                            <field name="token_count"/>
+                            <field name="avg_response_time"/>
+                            <field name="error_count"/>
+                        </group>
+                    </group>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="view_ollama_model_stats_search" model="ir.ui.view">
+        <field name="name">ollama.model.stats.search</field>
+        <field name="model">ollama.model.stats</field>
+        <field name="arch" type="xml">
+            <search string="Search Model Statistics">
+                <field name="model_id"/>
+                <field name="version"/>
+                <field name="date"/>
+                <filter string="Today" name="today" domain="[('date','=',context_today().strftime('%Y-%m-%d'))]"/>
+                <filter string="Last 7 Days" name="last_week" domain="[('date','>=', (context_today() - datetime.timedelta(days=7)).strftime('%Y-%m-%d'))]"/>
+                <filter string="Last 30 Days" name="last_month" domain="[('date','>=', (context_today() - datetime.timedelta(days=30)).strftime('%Y-%m-%d'))]"/>
+                <group expand="0" string="Group By">
+                    <filter string="Model" name="group_by_model" context="{'group_by': 'model_id'}"/>
+                    <filter string="Version" name="group_by_version" context="{'group_by': 'version'}"/>
+                    <filter string="Date" name="group_by_date" context="{'group_by': 'date'}"/>
+                </group>
+            </search>
+        </field>
+    </record>
+
+    <!-- Graph View -->
+    <record id="view_ollama_model_stats_graph" model="ir.ui.view">
+        <field name="name">ollama.model.stats.graph</field>
+        <field name="model">ollama.model.stats</field>
+        <field name="arch" type="xml">
+            <graph string="Model Statistics" type="line" sample="1">
+                <field name="date" type="row"/>
+                <field name="request_count" type="measure"/>
+                <field name="token_count" type="measure"/>
+                <field name="error_count" type="measure"/>
+            </graph>
+        </field>
+    </record>
+
+    <!-- Pivot View -->
+    <record id="view_ollama_model_stats_pivot" model="ir.ui.view">
+        <field name="name">ollama.model.stats.pivot</field>
+        <field name="model">ollama.model.stats</field>
+        <field name="arch" type="xml">
+            <pivot string="Model Statistics" sample="1">
+                <field name="model_id" type="row"/>
+                <field name="date" type="col"/>
+                <field name="request_count" type="measure"/>
+                <field name="token_count" type="measure"/>
+                <field name="avg_response_time" type="measure"/>
+                <field name="error_count" type="measure"/>
+            </pivot>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="action_ollama_model_stats" model="ir.actions.act_window">
+        <field name="name">Model Statistics</field>
+        <field name="res_model">ollama.model.stats</field>
+        <field name="view_mode">list,form,graph,pivot</field>
+        <field name="context">{'search_default_last_month': 1}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                No statistics recorded yet
+            </p>
+            <p>
+                Statistics will be automatically recorded as you use your AI models.
+            </p>
+        </field>
+    </record>
+
+    <!-- Menu Item -->
+    <menuitem id="menu_ollama_model_stats"
+              name="Model Statistics"
+              parent="ai_integration.menu_ai_config"
+              action="action_ollama_model_stats"
+              sequence="30"/>
+</odoo>
--- a/ai_integration_ollama_api/views/ollama_views.xml
+++ b/ai_integration_ollama_api/views/ollama_views.xml
@ -0,0 +1,108 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Form View -->
+    <record id="ollama_instance_view_form" model="ir.ui.view">
+        <field name="name">ollama.instance.form</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="type">form</field>
+        <field name="mode">primary</field>
+        <field name="inherit_id" ref="ai_integration.ai_provider_instance_view_form"/>
+        <field name="arch" type="xml">
+            <xpath expr="//div[@name='button_box']" position="replace">
+                <div class="oe_button_box" name="button_box">
+                    <button name="toggle_active" type="object" class="oe_stat_button" icon="fa-archive">
+                        <field name="active" widget="boolean_button" options="{'terminology': 'archive'}"/>
+                    </button>
+                </div>
+            </xpath>
+            <xpath expr="//field[@name='api_key']" position="replace">
+                <field name="api_key" invisible="1"/>
+            </xpath>
+            <xpath expr="//notebook" position="inside">
+                <page string="Ollama Settings" name="ollama_settings"
+                      invisible="provider_type != 'ollama'">
+                    <group>
+                        <group string="Generation Parameters">
+                            <field name="num_ctx"/>
+                            <field name="temperature"/>
+                            <field name="top_p"/>
+                            <field name="top_k"/>
+                            <field name="repeat_penalty"/>
+                        </group>
+                        <group string="Advanced Settings">
+                            <field name="stop_sequences" placeholder="Enter comma-separated stop sequences"/>
+                        </group>
+                    </group>
+                    <div class="alert alert-info" role="alert" style="margin-top: 10px;">
+                        <p><strong>Note:</strong> These settings will be used as defaults for all requests to this Ollama instance. 
+                        They can be overridden on a per-request basis.</p>
+                        <ul>
+                            <li><strong>Context Length:</strong> Longer context allows the model to consider more previous text but uses more memory.</li>
+                            <li><strong>Temperature:</strong> Higher values (>1.0) make output more random, lower values make it more focused and deterministic.</li>
+                            <li><strong>Top P:</strong> Controls diversity via nucleus sampling. Lower values (0.1) are more focused, higher values (0.9) more diverse.</li>
+                            <li><strong>Top K:</strong> Limits the cumulative probability of tokens to sample from. Lower values are more focused.</li>
+                            <li><strong>Repeat Penalty:</strong> Higher values (>1.0) make the model less likely to repeat itself.</li>
+                        </ul>
+                    </div>
+                </page>
+            </xpath>
+        </field>
+    </record>
+
+    <!-- Tree View -->
+    <record id="ollama_instance_view_list" model="ir.ui.view">
+        <field name="name">ollama.instance.list</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="type">list</field>
+        <field name="arch" type="xml">
+            <list>
+                <field name="name"/>
+                <field name="provider_type"/>
+                <field name="host"/>
+                <field name="num_ctx" optional="show"/>
+                <field name="temperature" optional="hide"/>
+                <field name="active"/>
+            </list>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="ollama_instance_view_search" model="ir.ui.view">
+        <field name="name">ollama.instance.search</field>
+        <field name="model">ai.provider.instance</field>
+        <field name="mode">primary</field>
+        <field name="inherit_id" ref="ai_integration.ai_provider_instance_view_search"/>
+        <field name="arch" type="xml">
+            <xpath expr="//group" position="inside">
+                <filter string="Context Length" name="group_by_num_ctx" 
+                        domain="[('provider_type', '=', 'ollama')]"
+                        context="{'group_by': 'num_ctx'}"/>
+            </xpath>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="action_ollama_instance" model="ir.actions.act_window">
+        <field name="name">Ollama Instances</field>
+        <field name="res_model">ai.provider.instance</field>
+        <field name="view_mode">list,form</field>
+        <field name="domain">[('provider_type', '=', 'ollama')]</field>
+        <field name="context">{'default_provider_type': 'ollama'}</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                Create your first Ollama instance
+            </p>
+            <p>
+                Configure Ollama instances to use local AI models in your Odoo instance.
+                Make sure you have Ollama installed and running on your server.
+            </p>
+        </field>
+    </record>
+
+    <!-- Menu Item -->
+    <menuitem id="menu_ollama_instance"
+              name="Ollama Instances"
+              parent="ai_integration.ai_integration_menu_config"
+              action="action_ollama_instance"
+              sequence="20"/>
+</odoo>
--- a/ai_integration_openai_api/init.py
+++ b/ai_integration_openai_api/init.py
@ -0,0 +1 @@
+from . import models
--- a/ai_integration_openai_api/manifest.py
+++ b/ai_integration_openai_api/manifest.py
@ -0,0 +1,35 @@
+{
+    'name': 'ChatGPT-Compatible AI Integration',
+    'version': '1.0',
+    'category': 'Technical',
+    'summary': 'Integration for ChatGPT-compatible AI providers',
+    'description': """
+ChatGPT-Compatible AI Integration
+================================
+This module provides integration with ChatGPT-compatible AI providers (OpenWebUI, ChatGPT, etc), offering:
+
+* ChatGPT-compatible provider implementation
+* Model synchronization
+* Advanced parameter configuration
+* Usage statistics tracking
+* Support for multiple providers using the ChatGPT API format
+""",
+    'author': 'Bemade',
+    'website': 'https://www.bemade.org',
+    'depends': [
+        'ai_integration',
+        'openwebui_integration'
+    ],
+    'data': [
+        'security/ir.model.access.csv',
+        'views/chatgpt_instance_views.xml',
+        'data/chatgpt_provider.xml',
+    ],
+    'external_dependencies': {
+        'python': ['requests'],
+    },
+    'installable': True,
+    'application': False,
+    'auto_install': False,
+    'license': 'LGPL-3',
+}
--- a/ai_integration_openai_api/data/chatgpt_provider.xml
+++ b/ai_integration_openai_api/data/chatgpt_provider.xml
@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <data noupdate="1">
+        <!-- ChatGPT-Compatible Provider -->
+        <record id="ai_provider_chatgpt" model="ai.provider">
+            <field name="name">ChatGPT-Compatible</field>
+            <field name="code">chatgpt</field>
+            <field name="instance_model">chatgpt.ai.instance</field>
+            <field name="provider_model">ai.provider.chatgpt</field>
+            <field name="description">Integration with ChatGPT-compatible AI providers (OpenWebUI, ChatGPT, etc).</field>
+            <field name="website">https://platform.openai.com/docs/api-reference/chat</field>
+        </record>
+    </data>
+</odoo>
--- a/ai_integration_openai_api/models/init.py
+++ b/ai_integration_openai_api/models/init.py
@ -0,0 +1,2 @@
+from . import chatgpt_provider
+from . import chatgpt_instance
--- a/ai_integration_openai_api/models/chatgpt_instance.py
+++ b/ai_integration_openai_api/models/chatgpt_instance.py
@ -0,0 +1,48 @@
+# -*- coding: utf-8 -*-
+from odoo import models, fields, api, _
+
+class ChatGPTInstance(models.Model):
+    _name = 'chatgpt.ai.instance'
+    _description = 'ChatGPT-Compatible Instance Configuration'
+    _inherit = ['ai.provider.instance', 'ai.generation.params']
+
+    provider_type = fields.Selection(
+        selection_add=[('chatgpt', 'ChatGPT-Compatible')],
+        ondelete={'chatgpt': 'cascade'})
+    
+    # ChatGPT API Parameters
+    
+    presence_penalty = fields.Float(
+        string='Presence Penalty',
+        help='Penalty for new tokens based on their presence in text. Range: [-2.0 - 2.0].',
+        default=0.0,
+        digits=(3, 2))
+    
+    frequency_penalty = fields.Float(
+        string='Frequency Penalty',
+        help='Penalty for new tokens based on their frequency in text. Range: [-2.0 - 2.0].',
+        default=0.0,
+        digits=(3, 2))
+    
+    # Provider Settings
+
+    def _get_provider_options(self):
+        """Get ChatGPT-compatible options for API calls."""
+        self.ensure_one()
+        
+        options = {
+            'temperature': self.temperature,
+            'top_p': self.top_p,
+            'max_tokens': self.max_tokens,
+            'presence_penalty': self.presence_penalty,
+            'frequency_penalty': self.frequency_penalty,
+            'stream': self.stream_response,
+        }
+        
+        if self.stop_sequences:
+            options['stop'] = [
+                seq.strip() 
+                for seq in self.stop_sequences.split(',')
+            ]
+        
+        return options
--- a/ai_integration_openai_api/models/chatgpt_provider.py
+++ b/ai_integration_openai_api/models/chatgpt_provider.py
@ -0,0 +1,163 @@
+# -*- coding: utf-8 -*-
+import json
+import logging
+import requests
+from odoo import models, fields, api, _
+from odoo.exceptions import UserError
+
+_logger = logging.getLogger(__name__)
+
+class ChatGPTProvider(models.AbstractModel):
+    _name = 'ai.provider.chatgpt'
+    _description = 'ChatGPT-Compatible AI Provider'
+    _inherit = ['ai.provider']
+
+    def _get_provider_type(self):
+        return 'chatgpt'
+
+    def test_connection(self, instance):
+        """Test the connection to the OpenWebUI server."""
+        try:
+            response = requests.get(f"{instance.host}/api/v1/models")
+            if response.status_code != 200:
+                raise UserError(_(
+                    "Failed to connect to AI server. Status code: %s. Error: %s",
+                    response.status_code, response.text
+                ))
+            return True
+        except requests.exceptions.RequestException as e:
+            raise UserError(_(
+                "Failed to connect to AI server: %s", str(e)
+            ))
+
+    def sync_models(self, instance):
+        """Synchronize available models from the OpenWebUI server."""
+        self.test_connection(instance)
+
+        try:
+            # Get models from provider
+            response = requests.get(f"{instance.host}/api/v1/models")
+            models_data = response.json()
+
+            # Get existing models for this instance
+            existing_models = self.env['ai.model'].search([
+                ('provider_instance_id', '=', instance.id)
+            ])
+            existing_identifiers = {m.identifier: m for m in existing_models}
+
+            for model_data in models_data:
+                identifier = model_data.get('id')
+                if not identifier:
+                    continue
+
+                # Get model details
+                model_info = self._get_model_info(instance, identifier)
+                model_details = model_info.get('details', {})
+                
+                model_values = {
+                    'name': model_data.get('name', identifier),
+                    'identifier': identifier,
+                    'description': model_details.get('description', ''),
+                    'version': model_details.get('version', ''),
+                    'provider_instance_id': instance.id,
+                }
+
+                if identifier in existing_identifiers:
+                    # Update existing model
+                    existing_identifiers[identifier].write(model_values)
+                else:
+                    # Create new model
+                    self.env['ai.model'].create(model_values)
+
+            return True
+
+        except requests.exceptions.RequestException as e:
+            raise UserError(_("Error synchronizing models: %s") % str(e))
+
+    def _get_model_info(self, instance, model_name):
+        """Get detailed information about a specific model."""
+        try:
+            response = requests.get(
+                f"{instance.host}/api/v1/models/{model_name}/info"
+            )
+            if response.status_code == 200:
+                return response.json()
+            else:
+                _logger.error(
+                    "Failed to get model info for %s. Status: %s, Error: %s",
+                    model_name, response.status_code, response.text
+                )
+                return {}
+        except requests.exceptions.RequestException as e:
+            _logger.error("Error getting model info: %s", str(e))
+            return {}
+
+    def _format_chat_messages(self, messages):
+        """Format chat messages for OpenWebUI API."""
+        formatted_messages = []
+        for message in messages:
+            role = message.get('role', 'user')
+            content = message.get('content', '')
+            
+            formatted_messages.append({
+                'role': role,
+                'content': content
+            })
+        
+        return formatted_messages
+
+    def generate_response(self, instance, model, messages, **kwargs):
+        """Generate a response using the chat completion API."""
+        try:
+            # Format messages for OpenWebUI
+            formatted_messages = self._format_chat_messages(messages)
+            
+            # Get model options from instance
+            options = instance._get_provider_options()
+            
+            # Prepare the request payload
+            payload = {
+                'model': model.identifier,
+                'messages': formatted_messages,
+                **options
+            }
+            
+            # Make the API call
+            response = requests.post(
+                f"{instance.host}/api/v1/chat/completions",
+                json=payload
+            )
+            
+            if response.status_code != 200:
+                raise UserError(_("Failed to generate response: %s") % response.text)
+            
+            response_data = response.json()
+            generated_text = response_data.get('choices', [{}])[0].get('message', {}).get('content', '')
+            
+            # Update statistics
+            total_tokens = response_data.get('usage', {}).get('total_tokens', 0)
+            response_time = response_data.get('response_ms', 0)
+            version = self._get_model_info(instance, model.identifier)\
+                .get('details', {}).get('version', '')
+            
+            self._track_model_usage(
+                model, total_tokens, response_time, version=version
+            )
+            
+            # Return the response in a standardized format
+            return {
+                'content': generated_text,
+                'role': 'assistant',
+                'metadata': {
+                    'total_tokens': total_tokens,
+                    'response_time': response_time,
+                    'model_version': version,
+                    'usage': response_data.get('usage', {})
+                }
+            }
+            
+        except requests.exceptions.RequestException as e:
+            # Log error in statistics
+            if model:
+                self._track_model_usage(model, error=True)
+            raise UserError(_("Error generating response: %s") % str(e))
--- a/ai_integration_openai_api/security/ir.model.access.csv
+++ b/ai_integration_openai_api/security/ir.model.access.csv
@ -0,0 +1,3 @@
+id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink
+access_openwebui_ai_instance_user,openwebui.ai.instance user,model_openwebui_ai_instance,base.group_user,1,0,0,0
+access_openwebui_ai_instance_system,openwebui.ai.instance system,model_openwebui_ai_instance,base.group_system,1,1,1,1
--- a/ai_integration_openai_api/views/chatgpt_instance_views.xml
+++ b/ai_integration_openai_api/views/chatgpt_instance_views.xml
@ -0,0 +1,106 @@
+<?xml version="1.0" encoding="utf-8"?>
+<odoo>
+    <!-- Form View -->
+    <record id="view_chatgpt_ai_instance_form" model="ir.ui.view">
+        <field name="name">chatgpt.ai.instance.form</field>
+        <field name="model">chatgpt.ai.instance</field>
+        <field name="arch" type="xml">
+            <form string="ChatGPT-Compatible Instance">
+                <sheet>
+                    <div class="oe_title">
+                        <label for="name" class="oe_edit_only"/>
+                        <h1><field name="name" placeholder="e.g. Production OpenWebUI/ChatGPT"/></h1>
+                    </div>
+                    <group>
+                        <group string="Connection">
+                            <field name="host" placeholder="e.g. http://localhost:8080"/>
+                            <field name="api_key"/>
+                            <field name="company_id" groups="base.group_multi_company"/>
+                            <field name="is_default"/>
+                        </group>
+                        <group string="Basic Generation">
+                            <field name="temperature"/>
+                            <field name="top_p"/>
+                            <field name="max_tokens"/>
+                            <field name="presence_penalty"/>
+                            <field name="frequency_penalty"/>
+                        </group>
+                    </group>
+                    <group string="Advanced Settings">
+                        <group>
+                            <field name="stop_sequences" placeholder="e.g. END,STOP,DONE"/>
+                            <field name="timeout"/>
+                            <field name="retry_count"/>
+                        </group>
+                        <group>
+                            <field name="stream_response"/>
+                        </group>
+                    </group>
+                    <group string="Models" attrs="{'invisible': [('id', '=', False)]}">
+                        <field name="model_ids" nolabel="1">
+                            <tree>
+                                <field name="name"/>
+                                <field name="identifier"/>
+                                <field name="version"/>
+                                <field name="description"/>
+                            </tree>
+                        </field>
+                    </group>
+                </sheet>
+            </form>
+        </field>
+    </record>
+
+    <!-- Tree View -->
+    <record id="view_chatgpt_ai_instance_tree" model="ir.ui.view">
+        <field name="name">chatgpt.ai.instance.tree</field>
+        <field name="model">chatgpt.ai.instance</field>
+        <field name="arch" type="xml">
+            <tree string="ChatGPT-Compatible Instances">
+                <field name="name"/>
+                <field name="host"/>
+                <field name="is_default"/>
+                <field name="company_id" groups="base.group_multi_company"/>
+            </tree>
+        </field>
+    </record>
+
+    <!-- Search View -->
+    <record id="view_chatgpt_ai_instance_search" model="ir.ui.view">
+        <field name="name">chatgpt.ai.instance.search</field>
+        <field name="model">chatgpt.ai.instance</field>
+        <field name="arch" type="xml">
+            <search string="Search ChatGPT-Compatible Instances">
+                <field name="name"/>
+                <field name="host"/>
+                <field name="company_id" groups="base.group_multi_company"/>
+                <filter string="Default Instance" name="is_default" domain="[('is_default', '=', True)]"/>
+                <group expand="0" string="Group By">
+                    <filter string="Company" name="company" context="{'group_by': 'company_id'}" groups="base.group_multi_company"/>
+                </group>
+            </search>
+        </field>
+    </record>
+
+    <!-- Action -->
+    <record id="action_chatgpt_ai_instance" model="ir.actions.act_window">
+        <field name="name">ChatGPT-Compatible Instances</field>
+        <field name="res_model">chatgpt.ai.instance</field>
+        <field name="view_mode">tree,form</field>
+        <field name="help" type="html">
+            <p class="o_view_nocontent_smiling_face">
+                Create your first ChatGPT-compatible instance
+            </p>
+            <p>
+                Configure instances to connect to ChatGPT-compatible servers (OpenWebUI, ChatGPT, etc).
+            </p>
+        </field>
+    </record>
+
+    <!-- Menu Item -->
+    <menuitem id="menu_chatgpt_ai_instance"
+              name="ChatGPT-Compatible"
+              parent="ai_integration.menu_ai_integration_config"
+              action="action_chatgpt_ai_instance"
+              sequence="20"/>
+</odoo>
--- a/bemade_add_follower_no_sendmail_default/init.py
+++ b/bemade_add_follower_no_sendmail_default/init.py
@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+from . import models
+
+
+
--- a/bemade_add_follower_no_sendmail_default/manifest.py
+++ b/bemade_add_follower_no_sendmail_default/manifest.py
@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+{
+    "name": "Change default when adding follower",
+    "version": "17.0.0.0.1",
+    "category": "Extra Tools",
+    'summary': 'Change default when adding follower',
+    "description": """
+    Change default when adding follower
+    Send mail false by default
+    """,
+    "author": "Bemade",
+    'website': 'https://www.bemade.org',
+    "depends": [
+        'mail',
+    ],
+    "data": [
+    ],
+    "auto_install": False,
+    "installable": True,
+    'license': 'OPL-1'
+}
--- a/bemade_add_follower_no_sendmail_default/migration18.md
+++ b/bemade_add_follower_no_sendmail_default/migration18.md
@ -0,0 +1,87 @@
+# Migration vers Odoo 18.0 - bemade_add_follower_no_sendmail_default
+
+## Description du module
+Ce module modifie le comportement par défaut du wizard d'ajout de followers pour que l'option "Envoyer un email" soit désactivée par défaut.
+
+## Analyse technique
+- Dépendances : mail
+- Modèles modifiés :
+  - mail.wizard.invite : Modification de la valeur par défaut du champ send_mail à False
+- Implémentation actuelle :
+  - Hérite de mail.wizard.invite
+  - Redéfinit uniquement le champ send_mail avec default=False
+
+## Alternatives Natives
+
+### Configuration Système
+1. Vérifier dans Odoo 18.0 :
+   - Paramètres de configuration du module mail
+   - Paramètres système (ir.config_parameter)
+   - Préférences utilisateur
+
+### Approches Alternatives
+1. Configuration par utilisateur :
+   - Ajouter une préférence utilisateur dans res.users
+   - Utiliser cette préférence comme valeur par défaut
+
+2. Configuration par type de document :
+   - Ajouter un paramètre dans les paramètres de notification par modèle
+   - Permettre une configuration plus granulaire
+
+## Recommandations pour la Migration
+
+### Approche "Vanilla First"
+1. Évaluer les alternatives natives :
+   - [X] Vérifier si Odoo 18.0 a ajouté une configuration similaire
+   - [ ] Explorer les nouvelles fonctionnalités de notification
+   - [ ] Vérifier les paramètres de notification par défaut
+
+2. Si aucune alternative native n'existe :
+   - [ ] Considérer l'ajout d'une configuration système
+   - [ ] Implémenter une solution plus flexible (par utilisateur ou par type de document)
+
+### Modifications Techniques
+1. Si le module est conservé :
+   - [ ] Mettre à jour la version dans __manifest__.py
+   - [ ] Vérifier la compatibilité de l'héritage du wizard
+   - [ ] Vérifier si le champ send_mail existe toujours et a le même comportement
+   - [ ] Adapter le code aux nouvelles conventions Odoo 18.0
+
+2. Si migration vers une solution native :
+   - [ ] Créer un module de migration pour la transition
+   - [ ] Migrer les configurations existantes
+   - [ ] Prévoir un plan de désactivation du module
+
+## Fonctionnalité Native dans Odoo 18.0
+✅ La fonctionnalité existe nativement dans Odoo 18.0 !
+
+Dans le modèle `mail.wizard.invite` (`mail/wizard/mail_wizard_invite.py`), le champ `notify` est déjà défini avec `default=False` :
+```python
+notify = fields.Boolean('Notify Recipients', default=False)
+```
+
+## Plan de Migration
+
+### Actions Requises
+1. **Désactivation du Module** :
+   - [ ] Désactiver le module avant la migration vers Odoo 18.0
+   - [ ] Vérifier qu'aucun autre module ne dépend de celui-ci
+   - [ ] Informer les utilisateurs que le comportement est maintenant natif
+
+2. **Vérification** :
+   - [ ] Tester le comportement natif dans Odoo 18.0
+   - [ ] Confirmer que le comportement par défaut est identique
+   - [ ] Documenter tout changement d'interface utilisateur
+
+## État de la Migration
+🟢 Pas de migration nécessaire - Utiliser la fonctionnalité native
+
+## Notes Importantes
+- Le comportement souhaité (notification désactivée par défaut) est maintenant le comportement standard d'Odoo 18.0
+- L'interface utilisateur est similaire, utilisant un widget boolean_toggle
+- Aucune personnalisation supplémentaire n'est nécessaire
+
+## Prochaines Étapes
+1. Planifier la désactivation du module
+2. Informer les utilisateurs du changement
+3. Retirer le module de la liste des dépendances des autres modules si nécessaire
--- a/bemade_add_follower_no_sendmail_default/models/init.py
+++ b/bemade_add_follower_no_sendmail_default/models/init.py
@ -0,0 +1,2 @@
+# -*- coding: utf-8 -*-
+from . import mail_wizard_invite
--- a/bemade_add_follower_no_sendmail_default/models/mail_wizard_invite.py
+++ b/bemade_add_follower_no_sendmail_default/models/mail_wizard_invite.py
@ -0,0 +1,11 @@
+# Copyright Bemade.org
+from odoo import models, fields, api
+
+
+class MailWizardInviteDefault(models.TransientModel):
+    _inherit = 'mail.wizard.invite'
+
+    send_mail = fields.Boolean(
+        default=False,
+        help="If true, an invitation email will be sent to the recipient"
+    )
--- a/bemade_attachments_cleanup/init.py
+++ b/bemade_attachments_cleanup/init.py
@ -0,0 +1 @@
+from . import wizard
--- a/bemade_attachments_cleanup/manifest.py
+++ b/bemade_attachments_cleanup/manifest.py
@ -0,0 +1,22 @@
+{
+    'name': "Attachment Cleanup",
+    'version': '1.0.1',
+    'author': "Bemade",
+    'website': "http://www.bemade.org",
+    'category': 'Tools',
+    'license': 'OPL-1',
+    'summary': "Find and delete missing attachments",
+    'description': """
+    This module adds a wizard in the settings menu to find and delete missing attachments.
+    The wizard lists all attachments that are not found in the filestore, and allows the user to select and delete them.
+    Please use this tool with caution, as deleting attachments cannot be undone.
+    """,
+    'depends': ['base'],
+    'data': [
+        'wizard/attachment_cleanup_wizard_view.xml',
+        'security/ir.model.access.csv',
+
+    ],
+    'installable': True,
+    'application': False,
+}
--- a/bemade_attachments_cleanup/i18n/fr_CA.po
+++ b/bemade_attachments_cleanup/i18n/fr_CA.po
@ -0,0 +1,37 @@
+# Translation of Odoo Server.
+# This file contains the translation of the following modules:
+# 	* attachment_cleanup
+#
+msgid ""
+msgstr ""
+"Project-Id-Version: Odoo Server 15.0\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2023-06-08 12:00+0000\n"
+"PO-Revision-Date: 2023-06-08 12:00+0000\n"
+"Last-Translator: \n"
+"Language-Team: \n"
+"Language: fr_CA\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Plural-Forms: \n"
+
+#. module: attachment_cleanup
+#: model:ir.actions.act_window,name:attachment_cleanup.action_open_attachment_cleanup_wizard
+msgid "Cleanup Attachments"
+msgstr "Nettoyer les pièces jointes"
+
+#. module: attachment_cleanup
+#: model:ir.ui.view,arch_db:attachment_cleanup.view_attachment_cleanup_wizard
+msgid "Delete"
+msgstr "Supprimer"
+
+#. module: attachment_cleanup
+#: model:ir.ui.view,arch_db:attachment_cleanup.view_attachment_cleanup_wizard
+msgid "Cancel"
+msgstr "Annuler"
+
+#. module: attachment_cleanup
+#: model:ir.model.fields,field_description:attachment_cleanup.field_attachment_cleanup_wizard_attachment_ids
+msgid "Missing Attachments"
+msgstr "Pièces jointes manquantes"
--- a/bemade_attachments_cleanup/migration18.md
+++ b/bemade_attachments_cleanup/migration18.md
@ -0,0 +1,31 @@
+# Migration vers Odoo 18.0 - bemade_attachments_cleanup
+
+## Description
+Module de nettoyage des pièces jointes obsolètes
+
+## Fonctionnalités Ajoutées
+- Suppression automatique des pièces jointes non utilisées
+- Configuration des règles de nettoyage
+- Historique des suppressions
+
+## Modèles et Champs Modifiés
+- ir.attachment
+  - Ajout du champ cleanup_date (date)
+  - Ajout du champ cleanup_reason (text)
+
+## Statut Migration
+- [ ] A migrer
+- [ ] En cours
+- [ ] Migré
+
+## Détails Migration
+- Vérifier si la fonctionnalité existe déjà dans Odoo 18.0
+- Analyser les impacts sur les workflows existants
+
+## Actions Requises
+- [ ] Vérifier la compatibilité avec Odoo 18.0
+- [ ] Tester les fonctionnalités
+- [ ] Mettre à jour la documentation
+
+## Notes
+- Ce module pourrait être remplacé par une configuration native dans Odoo 18.0
--- a/bemade_attachments_cleanup/security/ir.model.access.csv
+++ b/bemade_attachments_cleanup/security/ir.model.access.csv
@ -0,0 +1,2 @@
+id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink
+access_attachment_cleanup_wizard,access.attachment.cleanup.wizard,model_attachment_cleanup_wizard,base.group_system,1,1,1,1
--- a/bemade_attachments_cleanup/wizard/init.py
+++ b/bemade_attachments_cleanup/wizard/init.py
@ -0,0 +1 @@
+from . import attachment_cleanup_wizard
--- a/bemade_attachments_cleanup/wizard/attachment_cleanup_wizard.py
+++ b/bemade_attachments_cleanup/wizard/attachment_cleanup_wizard.py
@ -0,0 +1,45 @@
+from odoo import api, fields, models
+import os
+
+
+class AttachmentCleanupWizard(models.TransientModel):
+    _name = 'attachment.cleanup.wizard'
+    _description = 'Attachment Cleanup Wizard'
+
+    attachment_ids = fields.Many2many(
+        'ir.attachment',
+        string='Missing Attachments',
+        readonly=True,
+        help='Attachments that are not found in the filestore'
+    )
+
+    @api.model
+    def default_get(self, fields_list):
+        res = super(AttachmentCleanupWizard, self).default_get(fields_list)
+
+        attachments_1 = self.sudo().env['ir.attachment'].search([])
+
+        self._cr.execute("SELECT id FROM ir_attachment WHERE company_id = %s", (self.env.company.id,))
+
+        attachments = self._cr.fetchall()
+
+        filestore_location = self.env['ir.attachment']._filestore()
+
+        missing_attachments = []
+        for attachment_id in attachments:
+            # if attachment.id == 47984:
+            #     print(attachment.store_fname)
+            attachment = self.env['ir.attachment'].browse(attachment_id)
+
+            if attachment.store_fname:
+                file_path = os.path.join(filestore_location, attachment.store_fname)
+                if not os.path.exists(file_path):
+                    missing_attachments.append(attachment.id)
+
+        if missing_attachments:
+            res.update({'attachment_ids': [(6, 0, missing_attachments)]})
+        return res
+
+    def action_cleanup_attachments(self):
+        self.ensure_one()
+        self.attachment_ids.unlink()
--- a/bemade_attachments_cleanup/wizard/attachment_cleanup_wizard_view.xml
+++ b/bemade_attachments_cleanup/wizard/attachment_cleanup_wizard_view.xml
@ -0,0 +1,32 @@
+<odoo>
+    <record id="view_attachment_cleanup_wizard" model="ir.ui.view">
+        <field name="name">attachment.cleanup.wizard.view</field>
+        <field name="model">attachment.cleanup.wizard</field>
+        <field name="arch" type="xml">
+            <form string="Cleanup Attachments">
+                <field name="attachment_ids" options="{'no_create': True}">
+                    <tree>
+                        <field name="name"/>
+                        <field name="store_fname"/>
+                        <field name="res_model"/>
+                        <field name="res_id"/>
+                        <field name="mimetype"/>
+                        <field name="write_date"/>
+                        <button name="unlink" type="object" string="Delete"/>
+                    </tree>
+                </field>
+                <button name="action_cleanup_attachments" type="object" string="Delete All"/>
+            </form>
+        </field>
+    </record>
+
+    <record id="action_open_attachment_cleanup_wizard" model="ir.actions.act_window">
+        <field name="name">Cleanup Attachments</field>
+        <field name="res_model">attachment.cleanup.wizard</field>
+        <field name="view_mode">form</field>
+        <field name="view_id" ref="view_attachment_cleanup_wizard"/>
+        <field name="target">new</field>
+    </record>
+
+    <menuitem id="menu_attachment_cleanup" name="Cleanup Attachments" parent="base.menu_administration" action="action_open_attachment_cleanup_wizard"/>
+</odoo>
--- a/bemade_documents_portal/init.py
+++ b/bemade_documents_portal/init.py
@ -0,0 +1,2 @@
+from . import controllers
+from . import models
--- a/bemade_documents_portal/manifest.py
+++ b/bemade_documents_portal/manifest.py
@ -0,0 +1,32 @@
+#
+#    Bemade Inc.
+#
+#    Copyright (C) September 2023 Bemade Inc. (<https://www.bemade.org>).
+#    Author: Marc Durepos (Contact : marc@bemade.org)
+#
+#    This program is under the terms of the Odoo Proprietary License v1.0 (OPL-1)
+#    It is forbidden to publish, distribute, sublicense, or sell copies of the Software
+#    or modified copies of the Software.
+#
+#    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+#    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+#    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+#    IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+#    DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+#    ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+#    DEALINGS IN THE SOFTWARE.
+#
+{
+    'name': 'Documents Portal Base',
+    'version': '17.0.1.0.0',
+    'summary': 'Adds documents to the front-end portal.',
+    'category': 'Document Management',
+    'author': 'Bemade Inc.',
+    'website': 'https://www.bemade.org',
+    'license': 'OPL-1',
+    'depends': ['documents', 'portal', 'mail_enterprise', 'im_livechat'],
+    'data': ['views/document_portal_templates.xml'],
+    'demo': [],
+    'installable': True,
+    'auto_install': False,
+}
--- a/bemade_documents_portal/controllers/init.py
+++ b/bemade_documents_portal/controllers/init.py
@ -0,0 +1 @@
+from . import portal
--- a/bemade_documents_portal/controllers/portal.py
+++ b/bemade_documents_portal/controllers/portal.py
@ -0,0 +1,65 @@
+from odoo.addons.portal.controllers.portal import CustomerPortal
+from odoo.http import request, route
+from odoo.exceptions import AccessError, MissingError
+from odoo import _
+
+
+class DocumentCustomerPortal(CustomerPortal):
+
+    def _prepare_home_portal_values(self, counters):
+        rtn = super()._prepare_home_portal_values(counters)
+        domain = self._prepare_documents_domain()
+        rtn['documents_count'] = request.env['documents.document'].search_count(domain)
+        return rtn
+
+    @route('/my/documents', type='http', auth='user', website=True)
+    def portal_my_documents(self, **kwargs):
+        values = self._prepare_portal_layout_values()
+        Documents = request.env['documents.document']
+        domain = self._prepare_documents_domain()
+        documents_count = Documents.search_count(domain)
+        documents = Documents.search(domain)
+        values.update({
+            'documents_count': documents_count,
+            'documents': documents.sudo(),
+            'default_url': '/my/documents',
+            'page_name': 'my_documents',
+        })
+        return request.render("bemade_documents_portal.portal_my_documents", values)
+
+    def _prepare_documents_domain(self):
+        partner = request.env.user.partner_id
+        user = request.env.user
+        """Helper method intended to be overridden for future modules."""
+        return ['|',
+                ('partner_id', '=', partner.id),
+                ('owner_id', '=', user.id),
+                ]
+
+    def _render_record_template(self, values):
+        """ Override this method to apply a different template for a single document
+        record on the portal. """
+        return request.render("bemade_documents_portal.document_portal_template", values)
+
+    @route('/my/documents/<int:document_id>', type='http', auth='user', website=True)
+    def portal_document_page(self, document_id, download=False, **kwargs):
+        document = request.env['documents.document'].browse(document_id)
+        if not document:
+            raise MissingError(_('This document does not exist.'))
+        if download:
+            return self._download_attachment(document)
+        values={
+            'document': document,
+            'page_name': 'my_documents',
+            'action': document._get_portal_return_action(),
+        }
+        return self._render_record_template(values)
+
+    def _download_attachment(self, document):
+        attachment = document.attachment_id
+        headers = [
+            ('content-type', attachment.mimetype),
+            ('content-length', attachment.file_size),
+            ('content-disposition', f'attachment; filename="{document.name}"')
+        ]
+        return request.make_response(attachment.raw, headers)
--- a/bemade_documents_portal/models/init.py
+++ b/bemade_documents_portal/models/init.py
@ -0,0 +1 @@
+from . import documents
--- a/bemade_documents_portal/models/documents.py
+++ b/bemade_documents_portal/models/documents.py
@ -0,0 +1,17 @@
+from odoo import models, fields
+
+
+class Document(models.Model):
+    _name = 'documents.document'
+    _inherit = ['documents.document', 'portal.mixin']
+
+    def _compute_access_url(self):
+        super()._compute_access_url()
+        for document in self:
+            document.access_url = f'/my/documents/{document.id}'
+
+    def _get_portal_return_action(self):
+        """ Return the action used to display documents when returning from customer
+        portal."""
+        self.ensure_one()
+        return self.env.ref('documents.document_action')
--- a/bemade_documents_portal/views/document_portal_templates.xml
+++ b/bemade_documents_portal/views/document_portal_templates.xml
@ -0,0 +1,112 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<odoo>
+    <data>
+        <template id="portal_my_home" inherit_id="portal.portal_my_home">
+            <xpath expr="//div[hasclass('o_portal_docs')]" position="inside">
+                <t t-call="portal.portal_docs_entry">
+                    <t t-set="title">Documents</t>
+                    <t t-set="url">/my/documents</t>
+                    <t t-set="placeholder_count">documents_count</t>
+                </t>
+            </xpath>
+        </template>
+        <template id="portal_my_documents" name="My Documents">
+            <t t-call="portal.portal_layout">
+                <t t-call="portal.portal_table">
+                    <thead>
+                        <tr class="active">
+                            <th>Name</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                        <t t-foreach="documents" t-as="document">
+                            <tr>
+                                <td>
+                                    <a t-att-href="document.get_portal_url()">
+                                        <t t-esc="document.name"/>
+                                    </a>
+                                </td>
+                            </tr>
+                        </t>
+                    </tbody>
+                </t>
+            </t>
+        </template>
+        <template id="document_portal_template" name="Document Portal Template">
+            <t t-call="portal.portal_layout">
+                <t t-set="o_portal_fullwidth_alert"
+                   groups="documents.group_documents_user">
+                    <t t-call="portal.portal_back_in_edit_mode">
+                        <t t-set="backend_url"
+                           t-value="'/web#model=%s&amp;id=%s&amp;action=%s&amp;view_type=form' % (document._name, document.id, action.id)"/>
+                    </t>
+                </t>
+                <t t-call="portal.portal_record_layout">
+                    <t t-set="card_header">
+                        <div class="row no-gutters">
+                            <h5 class="mb-1 mb-md-0">
+                                <span t-field="document.name"/>
+                            </h5>
+                        </div>
+                    </t>
+                    <t t-set="card_body">
+                        <!-- Main Document Contents -->
+                        <div id="document_content"
+                             class="col-12 col-lg justify-content-end w-100 h-100">
+                            <div t-if="'image' in document.mimetype"
+                                 class="o_attachment_preview_img">
+                                <img id="attachment_img"
+                                     class="img img-fluid d-block"
+                                     t-attf-src="/documents/content/{{document.id}}"/>
+                            </div>
+                            <iframe t-if="document.mimetype == 'application/pdf'"
+                                    class="mb48 w-100 min-vh-100"
+                                    t-attf-src="/web/static/lib/pdfjs/web/viewer.html?file=/documents/content/{{document.id}}&amp;filename={{document.name}}"/>
+                            <ul class="list-group list-group-flush flex-wrap flex-row flex-lg-column">
+                                <li class="list-group-item flex-grow-1 b-0">
+                                    <a class="btn btn-secondary btn-block o_download_btn"
+                                       t-att-href="document.get_portal_url(download=True)">
+                                        Download</a>
+                                </li>
+                                <li class="list-group-item flex-grow-1 b-0">
+                                    <strong class="text-muted">File Size:
+                                        <t t-call="documents.format_file_size"/>
+                                    </strong>
+                                </li>
+                                <li class="list-group-item flex-grow-1 b-0">
+                                    <strong class="text-muted">File Type:
+                                        <t t-esc="document.mimetype"/>
+                                    </strong>
+                                </li>
+                                <li class="list-group-item flex-grow-1 b-0">
+                                    <strong class="text-muted">Attachment Type:
+                                        <t t-esc="document.attachment_type"/>
+                                    </strong>
+                                </li>
+                            </ul>
+                        </div>
+                    </t>
+                </t>
+                <!-- Chatter -->
+                <div id="document_communication" class="card-body">
+                    <h2>History</h2>
+                    <t t-call="portal.message_thread">
+                        <t t-set="object" t-value="document"/>
+                    </t>
+                </div>
+            </t>
+        </template>
+        <template id="portal_breadcrumbs" inherit_id="portal.portal_breadcrumbs">
+            <xpath expr="//ol[hasclass('o_portal_submenu')]" position="inside">
+                <li t-if="page_name == 'my_documents'"
+                    t-attf-class="breadcrumb-item #{'active ' if not document else ''}">
+                    <a t-if="document"
+                       t-attf-href="/my/documents?{{ keep_query() }}">Documents</a>
+                    <t t-else="">Documents</t>
+                </li>
+                <li t-if="document" class="breadcrumb-item active" t-esc="document.name">
+                </li>
+            </xpath>
+        </template>
+    </data>
+</odoo>
--- a/bemade_fetchmail_only_production/README.md
+++ b/bemade_fetchmail_only_production/README.md
--- a/bemade_fetchmail_only_production/init.py
+++ b/bemade_fetchmail_only_production/init.py
@ -0,0 +1,4 @@
+# Copyright (C) 2023 Bemade.org
+# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl).
+
+from . import models
--- a/bemade_fetchmail_only_production/manifest.py
+++ b/bemade_fetchmail_only_production/manifest.py
@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+{
+    "name": "Fetchmail Only on production environment",
+    "version": "17.0.0.0.1",
+    "category": "Extra Tools",
+    'summary': 'Fetchmail Only on production environment',
+    "description": """
+    Fetchmail Only on production environment
+    """,
+    "author": "Bemade",
+    'website': 'https://www.bemade.org',
+    "depends": [
+        'mail',
+    ],
+    "data": [
+    ],
+    "auto_install": True,
+    "installable": True,
+    'license': 'OPL-1'
+}
--- a/bemade_fetchmail_only_production/migration18.md
+++ b/bemade_fetchmail_only_production/migration18.md
@ -0,0 +1,31 @@
+# Migration vers Odoo 18.0 - bemade_fetchmail_only_production
+
+## Description
+Module restreignant la récupération des emails uniquement en environnement de production
+
+## Fonctionnalités Ajoutées
+- Désactivation de fetchmail dans les environnements de test et de développement
+- Configuration par base de données
+- Journalisation des tentatives de récupération
+
+## Modèles et Champs Modifiés
+- fetchmail.server
+  - Ajout du champ production_only (boolean)
+  - Ajout du champ last_attempt (datetime)
+
+## Statut Migration
+- [ ] A migrer
+- [ ] En cours
+- [ ] Migré
+
+## Détails Migration
+- Vérifier si la fonctionnalité existe déjà dans Odoo 18.0
+- Analyser les impacts sur les workflows existants
+
+## Actions Requises
+- [ ] Vérifier la compatibilité avec Odoo 18.0
+- [ ] Tester les fonctionnalités
+- [ ] Mettre à jour la documentation
+
+## Notes
+- Ce module pourrait être remplacé par une configuration native dans Odoo 18.0
--- a/bemade_fetchmail_only_production/models/init.py
+++ b/bemade_fetchmail_only_production/models/init.py
@ -0,0 +1,4 @@
+# Copyright (C) 2023 Bemade.org
+# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl).
+
+from . import fetchmail_server
--- a/bemade_fetchmail_only_production/models/fetchmail_server.py
+++ b/bemade_fetchmail_only_production/models/fetchmail_server.py
@ -0,0 +1,23 @@
+# Copyright (C) 2023 Bemade.org
+# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl).
+
+import logging
+
+# Import the required classes and decorators from Odoo
+from odoo import api, models
+from urllib.parse import urlparse
+
+_logger = logging.getLogger(__name__)
+
+class fetchmail_server(models.Model):
+    _inherit = 'fetchmail.server'
+
+    @api.model
+    def fetch_mail(self):
+        if urlparse(self.env['ir.config_parameter'].sudo().get_param('web.base.url')).netloc == \
+                urlparse('https://erp.durpro.com/').netloc:
+            return super(fetchmail_server, self).fetch_mail()
+        else:
+            # Add log message
+            _logger.info("Trying to fetch email, current URL don't match with production URL, so we don't fetch email")
+            return True
--- a/bemade_fetchmail_only_production/readme/HISTORY.rst
+++ b/bemade_fetchmail_only_production/readme/HISTORY.rst
@ -0,0 +1,10 @@
+15.0.0.0.1
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+* Initial release
+
+
+16.0.0.0.1
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+* Modification for V16 compatibility
--- a/bemade_fix_quality_report/init.py
+++ b/bemade_fix_quality_report/init.py
--- a/bemade_fix_quality_report/manifest.py
+++ b/bemade_fix_quality_report/manifest.py
@ -0,0 +1,33 @@
+#
+#    Bemade Inc.
+#
+#    Copyright (C) 2023-June Bemade Inc. (<https://www.bemade.org>).
+#    Author: Marc Durepos (Contact : marc@bemade.org)
+#
+#    This program is under the terms of the Odoo Proprietary License v1.0 (OPL-1)
+#    It is forbidden to publish, distribute, sublicense, or sell copies of the Software
+#    or modified copies of the Software.
+#
+#    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+#    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+#    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+#    IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+#    DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+#    ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+#    DEALINGS IN THE SOFTWARE.
+#
+{
+    'name': 'Fix Quality Worksheet',
+    'version': '17.0.1.0.0',
+    'summary': 'Fix Quality worksheet bug from Odoo Enterprise',
+    'description': '',
+    'category': 'Quality Control',
+    'author': 'Bemade Inc.',
+    'website': 'http://www.bemade.org',
+    'license': 'OPL-1',
+    'depends': ['quality_control'],
+    'data': ['reports/worksheet_custom_report_templates.xml'],
+    'assets': {},
+    'installable': True,
+    'auto_install': True,
+}
--- a/bemade_fix_quality_report/reports/worksheet_custom_report_templates.xml
+++ b/bemade_fix_quality_report/reports/worksheet_custom_report_templates.xml
@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<odoo>
+    <template id="worksheet_page" inherit_id="quality_control.worksheet_page">
+        <xpath expr="//span[@t-field='doc.result']" position="replace">
+            <span t-field="doc.measure"/>
+        </xpath>
+    </template>
+</odoo>
--- a/bemade_fsm/init.py
+++ b/bemade_fsm/init.py
@ -0,0 +1,3 @@
+from . import models
+from . import reports
+from . import wizard
--- a/Show more
+++ b/Show more