✨(backend) use docling

I save my changes  but this is deprecated
as we want must use docling-serve.

.gitignore

@@ -44,6 +44,9 @@ env.d/development/*
 !env.d/development/*.dist
 env.d/terraform
 
+# Configuration
+**/conversations/configuration/llm/dev.json
+
 # npm
 node_modules
 
@@ -79,3 +82,6 @@ db.sqlite3
 
 # Docker compose override
 compose.override.yml
+
+# Docling
+docling-models

CHANGELOG.md

@@ -8,13 +8,19 @@ and this project adheres to
 
 ## [Unreleased]
 
+### Added
+
+- ✨(backend) add FindRagBackend
+
 ### Changed
 
 - 📦️(front) update react
 
 ### Fixed
 
-- 🐛(e2e) fix test-e2e-chronium
+- 🐛(e2e) fix test-e2e-chromium
+- 🐛(back) fix system prompt compatibility with self-hosted models #200
+- ⚰️(back) remove dead code and unused files
 
 ## [0.0.10] - 2025-12-15
 
@@ -34,6 +40,7 @@ and this project adheres to
 ## [0.0.9] - 2025-11-17
 
 ### Added
+
 - ✨(front) add code copy button
 - ✨(RAG) add generic collection RAG tools #159
 
@@ -41,7 +48,6 @@ and this project adheres to
 
 - 🔊(langfuse) enable tracing with redacted content #162
 
-
 ## [0.0.8] - 2025-11-10
 
 ### Fixed
@@ -56,28 +62,24 @@ and this project adheres to
 
 - 🔥(posthog) remove posthog middleware for async mode fix #146
 
-
 ## [0.0.7] - 2025-10-28
 
 ### Fixed
 
 - 🚑️(posthog) fix the posthog middleware for async mode #133
 
-
 ## [0.0.6] - 2025-10-28
 
 ### Fixed
 
 - 🚑️(stats) fix tracking id in upload event #130
 
-
 ## [0.0.5] - 2025-10-27
 
 ### Fixed
 
 - 🚑️(drag-drop) fix the rejection display on Safari #127
 
-
 ## [0.0.4] - 2025-10-27
 
 ### Added
@@ -94,14 +96,12 @@ and this project adheres to
 - 🐛(front) fix mobile source
 - 🐛(attachments) reject the whole drag&drop if unsupported formats #123
 
-
 ## [0.0.3] - 2025-10-21
 
 ### Fixed
 
 - 🚑️(web-search) fix missing argument in RAG backend #116
 
-
 ## [0.0.2] - 2025-10-21
 
 ### Added
@@ -111,6 +111,7 @@ and this project adheres to
 - 📈(posthog) add `sub` field to tracking #95
 
 ### Changed
+
 - 🔧(front) change links feedback tchap + settings popup
 - 🐛(front) code activation fix session end #93
 - 💬(wording) error page wording #102
@@ -118,7 +119,6 @@ and this project adheres to
 - 🐛(activation-codes) create contact in brevo before add to list #108
 - ⚗️(summarization) add system prompt to handle tool #112
 
-
 ## [0.0.1] - 2025-10-19
 
 ### Changed
@@ -141,7 +141,7 @@ and this project adheres to
 - 🎨(front) change list attachment in chat
 - 🎨(front) move emplacement for attachment
 - 🎨(ui) retour ui sources files
-- ✨(ui) fix retour global ui 
+- ✨(ui) fix retour global ui
 - 🐛(fix) broken staging css
 - 🎨(alpha) adjustment for alpha version
 - ✨(ui) delete flex message

compose.yml

@@ -71,6 +71,9 @@ services:
       - "host.docker.internal:host-gateway"
     ports:
       - "8071:8000"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./src/backend:/app
       - ./data/static:/data/static
@@ -89,6 +92,9 @@ services:
     image: nginx:1.25
     ports:
       - "8083:8083"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./docker/files/etc/nginx/conf.d:/etc/nginx/conf.d:ro
     depends_on:
@@ -177,3 +183,8 @@ services:
       kc_postgresql:
         condition: service_healthy
         restart: true
+
+networks:
+  lasuite:
+    name: lasuite-network
+    driver: bridge

docs/env.md

@@ -95,6 +95,9 @@ These are the environment variables you can set for the `conversations-backend`
 | CACHES_KEY_PREFIX                               | The prefix used to every cache keys.                                                                                              | conversations                                           |
 | THEME_CUSTOMIZATION_FILE_PATH                   | full path to the file customizing the theme. An example is provided in src/backend/conversations/configuration/theme/default.json | BASE_DIR/conversations/configuration/theme/default.json |
 | THEME_CUSTOMIZATION_CACHE_TIMEOUT               | Cache duration for the customization settings                                                                                     | 86400                                                   |
+| FIND_API_KEY                                    | API key of Find                                                                                                                   |                                                         |
+| FIND_API_URL                                    | URL of Find                                                                                                                       | `https://app-find/api`                                  |
+| FIND_API_TIMEOUT                                | Find API timeout                                                                                                                  | 30                                                      |
 
 
 ## conversations-frontend image

docs/llm-configuration.md

@@ -244,9 +244,9 @@ For Mistral AI models using the Etalab platform:
 {
   "models": [
     {
-      "hrid": "mistral-large",
-      "model_name": "mistral-large-latest",
-      "human_readable_name": "Mistral Large (Etalab)",
+      "hrid": "mistral-medium",
+      "model_name": "mistral-medium-2508",
+      "human_readable_name": "Mistral Medium (Etalab)",
       "provider_name": "mistral-etalab",
       "profile": null,
       "settings": {

docs/tools/web_search_brave.md

@@ -357,6 +357,7 @@ The RAG backend performs semantic search to find the most relevant content:
 rag_results = document_store.search(
     query,
     results_count=settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER,
+    **kwargs, # Additional search parameters like session with access_token
 )
 ```
 

package.json

@@ -1,6 +0,0 @@
-{
-  "dependencies": {
-    "@ai-sdk/react": "^1.2.12",
-    "@ai-sdk/ui-utils": "^1.2.11"
-  }
-}

src/backend/chat/agent_rag/document_converter/parser.py

@@ -0,0 +1,100 @@
+"""Document parsers for RAG backends."""
+
+import logging
+from io import BytesIO
+from urllib.parse import urljoin
+
+from django.conf import settings
+
+import requests
+from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.pipeline_options import PdfPipelineOptions, TableStructureOptions
+from docling.document_converter import DocumentConverter as DoclingDocumentConverter
+from docling.document_converter import PdfFormatOption
+from docling_core.types.io import DocumentStream
+
+from chat.agent_rag.document_converter.markitdown import (
+    DocumentConverter as MarkitdownDocumentConverter,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class BaseParser:
+    """Base class for document parsers."""
+
+    def parse_document(self, name: str, content_type: str, content: BytesIO) -> str:
+        """
+        Parse the document and prepare it for the search operation.
+        This method should handle the logic to convert the document
+        into a format suitable for storage.
+
+        Args:
+            name (str): The name of the document.
+            content_type (str): The MIME type of the document (e.g., "application/pdf").
+            content (BytesIO): The content of the document as a BytesIO stream.
+
+        Returns:
+            str: The document content in Markdown format.
+        """
+        raise NotImplementedError("Must be implemented in subclass.")
+
+
+class AlbertParser(BaseParser):
+    """Document parser using Albert API for PDFs and DocumentConverter for other formats."""
+
+    endpoint = urljoin(settings.ALBERT_API_URL, "/v1/parse-beta")
+
+    def parse_pdf_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse PDF document using Albert API."""
+        response = requests.post(
+            self.endpoint,
+            headers={
+                "Authorization": f"Bearer {settings.ALBERT_API_KEY}",
+            },
+            files={
+                "file": (name, content, content_type),
+                "output_format": (None, "markdown"),
+            },
+            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return "\n\n".join(
+            document_page["content"] for document_page in response.json().get("data", [])
+        )
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse document based on content type."""
+        if content_type == "application/pdf":
+            return self.parse_pdf_document(name=name, content_type=content_type, content=content)
+        return MarkitdownDocumentConverter().convert_raw(
+            name=name, content_type=content_type, content=content
+        )
+
+
+class DoclingParser(BaseParser):
+    """Document parser using Docling's DocumentConverter."""
+
+    artifacts_path = "src/backend/docling-models"
+
+    def __init__(self):
+        pipeline_options = PdfPipelineOptions(artifacts_path=self.artifacts_path)
+        pipeline_options.do_ocr = True
+        pipeline_options.do_table_structure = True
+        pipeline_options.table_structure_options = TableStructureOptions(do_cell_matching=False)
+
+        self.converter = DoclingDocumentConverter(
+            format_options={
+                InputFormat.PDF: PdfFormatOption(
+                    pipeline_options=pipeline_options,
+                    backend=PyPdfiumDocumentBackend
+                )}
+        )
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse document using Docling's DocumentConverter."""
+        return self.converter.convert(
+            DocumentStream(name=name, stream=BytesIO(content))
+        ).document.export_to_markdown()

src/backend/chat/agent_rag/document_rag_backends/albert_rag_backend.py

@@ -13,7 +13,7 @@ import requests
 
 from chat.agent_rag.albert_api_constants import Searches
 from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
-from chat.agent_rag.document_converter.markitdown import DocumentConverter
+from chat.agent_rag.document_converter.parser import DoclingParser
 from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
 
 logger = logging.getLogger(__name__)
@@ -26,9 +26,6 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
 
     It provides methods to:
     - Create a collection for the search operation.
-    - Parse documents and convert them to Markdown format:
-       + Handle PDF parsing using the Albert API.
-       + Use the DocumentConverter (markitdown) for other formats.
     - Store parsed documents in the Albert collection.
     - Perform a search operation using the Albert API.
     """
@@ -46,10 +43,9 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         }
         self._collections_endpoint = urljoin(self._base_url, "/v1/collections")
         self._documents_endpoint = urljoin(self._base_url, "/v1/documents")
-        self._pdf_parser_endpoint = urljoin(self._base_url, "/v1/parse-beta")
         self._search_endpoint = urljoin(self._base_url, "/v1/search")
-
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser = DoclingParser()
 
     def create_collection(self, name: str, description: Optional[str] = None) -> str:
         """
@@ -114,59 +110,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             )
             response.raise_for_status()
 
-    def parse_pdf_document(self, name: str, content_type: str, content: BytesIO) -> str:
-        """
-        Parse the PDF document content and return the text content.
-        This method should handle the logic to convert the PDF into
-        a format suitable for the Albert API.
-        """
-        response = requests.post(
-            self._pdf_parser_endpoint,
-            headers=self._headers,
-            files={
-                "file": (
-                    name,
-                    content,
-                    content_type,
-                ),  # Use the name as the filename in the request
-                "output_format": (None, "markdown"),  # Specify the output format as Markdown,
-            },
-            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
-        )
-        response.raise_for_status()
-
-        return "\n\n".join(
-            document_page["content"] for document_page in response.json().get("data", [])
-        )
-
-    def parse_document(self, name: str, content_type: str, content: BytesIO):
-        """
-        Parse the document and prepare it for the search operation.
-        This method should handle the logic to convert the document
-        into a format suitable for the Albert API.
-
-        Args:
-            name (str): The name of the document.
-            content_type (str): The MIME type of the document (e.g., "application/pdf").
-            content (BytesIO): The content of the document as a BytesIO stream.
-
-        Returns:
-            str: The document content in Markdown format.
-        """
-        # Implement the parsing logic here
-        if content_type == "application/pdf":
-            # Handle PDF parsing
-            markdown_content = self.parse_pdf_document(
-                name=name, content_type=content_type, content=content
-            )
-        else:
-            markdown_content = DocumentConverter().convert_raw(
-                name=name, content_type=content_type, content=content
-            )
-
-        return markdown_content
-
-    def store_document(self, name: str, content: str) -> None:
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
@@ -174,6 +118,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         response = requests.post(
             urljoin(self._base_url, self._documents_endpoint),
@@ -188,7 +133,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         logger.debug(response.json())
         response.raise_for_status()
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
@@ -196,6 +141,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         async with httpx.AsyncClient(timeout=settings.ALBERT_API_TIMEOUT) as client:
             response = await client.post(
@@ -213,13 +159,14 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             logger.debug(response.json())
             response.raise_for_status()
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform a search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.
@@ -256,13 +203,14 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             ),
         )
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform an asynchronous search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.

src/backend/chat/agent_rag/document_rag_backends/base_rag_backend.py

@@ -8,6 +8,7 @@ from typing import List, Optional
 from asgiref.sync import sync_to_async
 
 from chat.agent_rag.constants import RAGWebResults
+from chat.agent_rag.document_converter.parser import BaseParser
 
 logger = logging.getLogger(__name__)
 
@@ -38,6 +39,7 @@ class BaseRagBackend:
         self.collection_id = collection_id
         self.read_only_collection_id = read_only_collection_id or []
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser: BaseParser = BaseParser()
 
     def get_all_collection_ids(self) -> List[str]:
         """
@@ -53,7 +55,7 @@ class BaseRagBackend:
 
         collection_ids = []
         if self.collection_id:
-            collection_ids.append(int(self.collection_id))
+            collection_ids.append(self.collection_id)
         if self.read_only_collection_id:
             collection_ids.extend(
                 [int(collection_id) for collection_id in self.read_only_collection_id]
@@ -88,9 +90,9 @@ class BaseRagBackend:
         Returns:
             str: The document content in Markdown format.
         """
-        raise NotImplementedError("Must be implemented in subclass.")
+        return self.parser.parse_document(name, content_type, content)
 
-    def store_document(self, name: str, content: str) -> None:
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -98,10 +100,11 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -109,10 +112,13 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
-        return await sync_to_async(self.store_document)(name=name, content=content)
+        return await sync_to_async(self.store_document)(name=name, content=content, **kwargs)
 
-    def parse_and_store_document(self, name: str, content_type: str, content: BytesIO) -> str:
+    def parse_and_store_document(
+        self, name: str, content_type: str, content: BytesIO, **kwargs
+    ) -> str:
         """
         Parse the document and store it in the Albert collection.
 
@@ -120,12 +126,13 @@ class BaseRagBackend:
             name (str): The name of the document.
             content_type (str): The MIME type of the document (e.g., "application/pdf").
             content (BytesIO): The content of the document as a BytesIO stream.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         if not self.collection_id:
             raise RuntimeError("The RAG backend requires collection_id")
 
         document_content = self.parse_document(name, content_type, content)
-        self.store_document(name, document_content)
+        self.store_document(name, document_content, **kwargs)
         return document_content
 
     def delete_collection(self) -> None:
@@ -142,17 +149,27 @@ class BaseRagBackend:
         """
         return await sync_to_async(self.delete_collection)()
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Search the collection for the given query.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
-        Search the collection for the given query.
+        Search the collection for the given query asynchronously.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
-        return await sync_to_async(self.search)(query=query, results_count=results_count)
+        return await sync_to_async(self.search)(query=query, results_count=results_count, **kwargs)
 
     @classmethod
     @contextmanager

src/backend/chat/agent_rag/document_rag_backends/find_rag_backend.py

@@ -0,0 +1,153 @@
+"""Implementation of the Find API for RAG document search."""
+
+import logging
+import uuid
+from typing import List, Optional
+from urllib.parse import urljoin
+from uuid import uuid4
+
+from django.conf import settings
+from django.utils import timezone
+
+import requests
+
+from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
+from chat.agent_rag.document_converter.parser import DoclingParser
+from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
+from utils.oidc import with_fresh_access_token
+
+logger = logging.getLogger(__name__)
+
+
+SUPPORTED_LANGUAGE_CODES = ["en", "fr", "de", "nl"]
+
+
+class FindRagBackend(BaseRagBackend):
+    """
+    This class is a placeholder for the Find API implementation.
+    It is designed to be used with the RAG (Retrieval-Augmented Generation) document search system.
+
+    It provides methods to:
+    - Store parsed documents in the Find index.
+    - Perform a search operation using the Find API.
+    """
+
+    def __init__(
+        self,
+        collection_id: Optional[str] = None,
+        read_only_collection_id: Optional[List[str]] = None,
+    ):
+        # Initialize any necessary parameters or configurations here
+        super().__init__(collection_id, read_only_collection_id)
+        self.api_key = settings.FIND_API_KEY
+        self.search_endpoint = "api/v1.0/documents/search/"
+        self.indexing_endpoint = "api/v1.0/documents/index/"
+        self.parser = DoclingParser()
+
+    def create_collection(self, name: str, description: Optional[str] = None) -> str:
+        """
+        init collection_id
+        """
+        self.collection_id = self.collection_id or str(uuid.uuid4())
+        return self.collection_id
+
+    def delete_collection(self) -> None:
+        """
+        Deletion not available
+        """
+        logger.warning("deletion of collections is not yet supported in FindRagBackend")
+
+    def store_document(self, name: str, content: str, **kwargs) -> None:
+        """
+        index document in Find
+
+        Args:
+            name (str): The name of the document.
+            content (str): The content of the document in Markdown format.
+            user_sub (str): The user subject identifier for access control.
+        """
+        logger.debug("index document '%s' in Find", name)
+
+        user_sub = kwargs.get("user_sub")
+        if not user_sub:
+            raise ValueError("user_sub is required to store document in FindRagBackend")
+
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.indexing_endpoint),
+            headers={"Authorization": f"Bearer {self.api_key}"},
+            json={
+                "id": str(uuid4()),
+                "title": str(name) or "",
+                "depth": 0,
+                "path": str(name) or "",
+                "numchild": 0,
+                "content": content or "",
+                "created_at": timezone.now().isoformat(),
+                "updated_at": timezone.now().isoformat(),
+                "tags": [f"collection-{self.collection_id}"],
+                "size": len(content.encode("utf-8")),
+                "users": [user_sub],
+                "groups": [],
+                "reach": "authenticated",
+                "is_active": True,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+    @with_fresh_access_token
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
+        """
+        Perform a search using the Find API.
+        Uses the user's OIDC token from the request session.
+
+        Args:
+            query: The search query.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. Expected: 'session' containing OIDC tokens,
+
+        Returns:
+            RAGWebResults: The search results.
+        """
+        logger.debug("search documents in Find with query '%s'", query)
+
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.search_endpoint),
+            headers={"Authorization": f"Bearer {kwargs['session'].get('oidc_access_token')}"},
+            json={
+                "q": query,
+                "tags": [
+                    f"collection-{collection_id}" for collection_id in self.get_all_collection_ids()
+                ],
+                "k": results_count,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return RAGWebResults(
+            data=[
+                RAGWebResult(
+                    url=get_language_value(result["_source"], "title"),
+                    content=get_language_value(result["_source"], "content"),
+                    score=result["_score"],
+                )
+                for result in response.json()
+            ],
+            usage=RAGWebUsage(
+                prompt_tokens=0,
+                completion_tokens=0,
+            ),
+        )
+
+
+def get_language_value(source, language_field):
+    """
+    extract the value of the language field with the correct language_code extension.
+    "title" and "content" have extensions like "title.en" or "title.fr".
+    get_language_value will return the value regardless of the extension.
+    """
+    for language_code in SUPPORTED_LANGUAGE_CODES:
+        if f"{language_field}.{language_code}" in source:
+            return source[f"{language_field}.{language_code}"]
+    raise ValueError(f"No '{language_field}' field with any supported language code in object")

src/backend/chat/agent_rag/document_search/albert_api.py

@@ -11,7 +11,7 @@ import requests
 
 from chat.agent_rag.albert_api_constants import Searches
 from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
-from chat.agent_rag.document_converter.markitdown import DocumentConverter
+from chat.agent_rag.document_converter.parser import DoclingParser
 from chat.models import ChatConversation
 
 logger = logging.getLogger(__name__)
@@ -80,58 +80,6 @@ class AlbertRagDocumentSearch:
         self.conversation.collection_id = str(response.json()["id"])
         return True
 
-    def _parse_pdf_document(self, name: str, content_type: str, content: BytesIO) -> str:
-        """
-        Parse the PDF document content and return the text content.
-        This method should handle the logic to convert the PDF into
-        a format suitable for the Albert API.
-        """
-        response = requests.post(
-            self._pdf_parser_endpoint,
-            headers=self._headers,
-            files={
-                "file": (
-                    name,
-                    content,
-                    content_type,
-                ),  # Use the name as the filename in the request
-                "output_format": (None, "markdown"),  # Specify the output format as Markdown,
-            },
-            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
-        )
-        response.raise_for_status()
-
-        return "\n\n".join(
-            document_page["content"] for document_page in response.json().get("data", [])
-        )
-
-    def parse_document(self, name: str, content_type: str, content: BytesIO):
-        """
-        Parse the document and prepare it for the search operation.
-        This method should handle the logic to convert the document
-        into a format suitable for the Albert API.
-
-        Args:
-            name (str): The name of the document.
-            content_type (str): The MIME type of the document (e.g., "application/pdf").
-            content (BytesIO): The content of the document as a BytesIO stream.
-
-        Returns:
-            str: The document content in Markdown format.
-        """
-        # Implement the parsing logic here
-        if content_type == "application/pdf":
-            # Handle PDF parsing
-            markdown_content = self._parse_pdf_document(
-                name=name, content_type=content_type, content=content
-            )
-        else:
-            markdown_content = DocumentConverter().convert_raw(
-                name=name, content_type=content_type, content=content
-            )
-
-        return markdown_content
-
     def _store_document(self, name: str, content: str):
         """
         Store the document content in the Albert collection.
@@ -156,7 +104,7 @@ class AlbertRagDocumentSearch:
         logger.debug(response.json())
         response.raise_for_status()
 
-    def parse_and_store_document(self, name: str, content_type: str, content: BytesIO):
+    def parse_and_store_document(self, name: str, content_type: str, content: bytes):
         """
         Parse the document and store it in the Albert collection.
 
@@ -165,7 +113,9 @@ class AlbertRagDocumentSearch:
             content_type (str): The MIME type of the document (e.g., "application/pdf").
             content (BytesIO): The content of the document as a BytesIO stream.
         """
-        document_content = self.parse_document(name, content_type, content)
+        document_content = DoclingParser().parse_document(
+            name=name, content_type=content_type, content=content
+        )
         self._store_document(name, document_content)
         return document_content
 

src/backend/chat/agents/base.py

@@ -190,6 +190,4 @@ class BaseAgent(Agent):
 
         _tools = [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]
 
-        super().__init__(
-            model=_model_instance, system_prompt=_system_prompt, tools=_tools, **kwargs
-        )
+        super().__init__(model=_model_instance, instructions=_system_prompt, tools=_tools, **kwargs)

src/backend/chat/agents/conversation.py

@@ -16,7 +16,6 @@ from .base import BaseAgent
 
 logger = logging.getLogger(__name__)
 
-
 MOCKED_RESPONSE = """
 # **Ode to the AI Assistant** 🤖✨
 
@@ -102,10 +101,10 @@ class ConversationAgent(BaseAgent):
         if settings.WARNING_MOCK_CONVERSATION_AGENT:
             self._model = FunctionModel(stream_function=mocked_agent_model)
 
-        @self.system_prompt
+        @self.instructions
         def add_the_date() -> str:
             """
-            Dynamic system prompt function to add the current date.
+            Dynamic instruction function to add the current date.
 
             Warning: this will always use the date in the server timezone,
             not the user's timezone...
@@ -113,9 +112,9 @@ class ConversationAgent(BaseAgent):
             _formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
             return f"Today is {_formatted_date}."
 
-        @self.system_prompt
+        @self.instructions
         def enforce_response_language() -> str:
-            """Dynamic system prompt function to set the expected language to use."""
+            """Dynamic instruction function to set the expected language to use."""
             return f"Answer in {get_language_name(language).lower()}." if language else ""
 
     def get_web_search_tool_name(self) -> str | None:

src/backend/chat/clients/pydantic_ai.py

@@ -78,6 +78,9 @@ from chat.tools.document_summarize import document_summarize
 from chat.vercel_ai_sdk.core import events_v4, events_v5
 from chat.vercel_ai_sdk.encoder import EventEncoder
 
+# Keep at the top of the file to avoid mocking issues
+document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
+
 logger = logging.getLogger(__name__)
 
 User = get_user_model()
@@ -89,6 +92,7 @@ class ContextDeps:
 
     conversation: models.ChatConversation
     user: User
+    session: Optional[Dict] = None
     web_search_enabled: bool = False
 
 
@@ -103,7 +107,14 @@ def get_model_configuration(model_hrid: str):
 class AIAgentService:  # pylint: disable=too-many-instance-attributes
     """Service class for AI-related operations (Pydantic-AI edition)."""
 
-    def __init__(self, conversation: models.ChatConversation, user, model_hrid=None, language=None):
+    def __init__(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+        self,
+        conversation: models.ChatConversation,
+        user,
+        session=None,
+        model_hrid=None,
+        language=None,
+    ):
         """
         Initialize the AI agent service.
 
@@ -133,6 +144,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         self._context_deps = ContextDeps(
             conversation=conversation,
             user=user,
+            session=session,
             web_search_enabled=self._is_web_search_enabled,
         )
 
@@ -236,6 +248,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         Parse and store input documents in the conversation's document store.
         """
         # Early external document URL rejection
+
         if any(
             not document.url.startswith("/media-key/")
             for document in documents
@@ -249,8 +262,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         ):
             raise ValueError("Document URL does not belong to the conversation.")
 
-        document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
-
         document_store = document_store_backend(self.conversation.collection_id)
         if not document_store.collection_id:
             # Create a new collection for the conversation
@@ -276,6 +287,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                         name=document.identifier,
                         content_type=document.media_type,
                         content=document_data,
+                        user_sub=self.user.sub,
                     )
                 else:
                     # Remote URL
@@ -285,6 +297,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     name=document.identifier,
                     content_type=document.media_type,
                     content=document.data,
+                    user_sub=self.user.sub,
                 )
 
             if not document.media_type.startswith("text/"):
@@ -420,6 +433,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     ],
                 },
             )
+
             try:
                 await self.parse_input_documents(input_documents)
             except Exception as exc:  # pylint: disable=broad-except
@@ -457,7 +471,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         if force_web_search:
 
-            @self.conversation_agent.system_prompt
+            @self.conversation_agent.instructions
             def force_web_search_prompt() -> str:
                 """Dynamic system prompt function to force web search."""
                 return (
@@ -505,7 +519,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                 )
 
             # Inform the model (system-level) that documents are attached and available
-            @self.conversation_agent.system_prompt
+            @self.conversation_agent.instructions
             def attached_documents_note() -> str:
                 return (
                     "[Internal context] User documents are attached to this conversation. "
@@ -731,7 +745,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             langfuse.update_current_trace(
                 output=run.result.output if self._store_analytics else "REDACTED"
             )
-
         # Vercel finish message
         yield events_v4.FinishMessagePart(
             finish_reason=events_v4.FinishReason.STOP,

src/backend/chat/tests/agent_rag/document_converter/run_docling.py

@@ -0,0 +1,29 @@
+"""
+Unit tests for the DocumentConverter.
+
+Only for coverage as the DocumentConverter is a simple wrapper around MarkItDown.
+"""
+
+from io import BytesIO
+
+from docling.document_converter import DocumentConverter
+from docling_core.types.io import DocumentStream
+
+
+def main():
+    """Test that the DocumentConverter calls the underlying MarkItDown converter."""
+    file_path = "test.pdf"
+    converter = DocumentConverter()
+
+    # Convert from file content instead of file path
+    with open(file_path, "rb") as file:
+        content = file.read()
+        stream = DocumentStream(name="test.pdf", stream=BytesIO(content))
+        result = converter.convert(stream)
+        markdown = result.document.export_to_markdown()
+
+    assert markdown == "Document PDF test"
+
+
+if __name__ == "__main__":
+    main()

src/backend/chat/tests/agent_rag/document_converter/test.pdf

@@ -0,0 +1,90 @@
+%PDF-1.4
+%Çì�¢
+5 0 obj
+<</Length 6 0 R/Filter /FlateDecode>>
+stream
+xœMŽ±NÄ0†÷<…Çd¨ÏNœ¸^OÀÀ§l'¦Šc*¨âx’RªÚƒ­ÿóo{
BŽ@=ÿ›ivnq#¦«xì§ÎÕ�.
+ÍQoŽÐÌ„WÆ „#h!¨³»ú‡À˜5Sò_a Œ&¦â§�°•Ÿƒ4‡!¢ÊÅ¿ÿÑϽwÊ%çÑC—Y4[ò/a�ö³n‡D¢
+‹æhû¨Z<nØö‡�1F3Ýaj–·úì«{mùµi:uendstream
+endobj
+6 0 obj
+180
+endobj
+4 0 obj
+<</Type/Page/MediaBox [0 0 595 842]
+/Rotate 0/Parent 3 0 R
+/Resources<</ProcSet[/PDF /Text]
+/Font 8 0 R
+>>
+/Contents 5 0 R
+>>
+endobj
+3 0 obj
+<< /Type /Pages /Kids [
+4 0 R
+] /Count 1
+>>
+endobj
+1 0 obj
+<</Type /Catalog /Pages 3 0 R
+/Metadata 9 0 R
+>>
+endobj
+8 0 obj
+<</R7
+7 0 R>>
+endobj
+7 0 obj
+<</BaseFont/Times-Roman/Type/Font
+/Subtype/Type1>>
+endobj
+9 0 obj
+<</Type/Metadata
+/Subtype/XML/Length 1549>>stream
+<?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>
+<?adobe-xap-filters esc="CRLF"?>
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='XMP toolkit 2.9.1-13, framework 1.6'>
+<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#' xmlns:iX='http://ns.adobe.com/iX/1.0/'>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:pdf='http://ns.adobe.com/pdf/1.3/'><pdf:Producer>GPL Ghostscript 9.06</pdf:Producer>
+<pdf:Keywords>()</pdf:Keywords>
+</rdf:Description>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:xmp='http://ns.adobe.com/xap/1.0/'><xmp:ModifyDate>2014-12-22T00:49:20+01:00</xmp:ModifyDate>
+<xmp:CreateDate>2014-12-22T00:49:20+01:00</xmp:CreateDate>
+<xmp:CreatorTool>PDFCreator Version 1.6.0</xmp:CreatorTool></rdf:Description>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:xapMM='http://ns.adobe.com/xap/1.0/mm/' xapMM:DocumentID='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c'/>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:dc='http://purl.org/dc/elements/1.1/' dc:format='application/pdf'><dc:title><rdf:Alt><rdf:li xml:lang='x-default'>test_word</rdf:li></rdf:Alt></dc:title><dc:creator><rdf:Seq><rdf:li>Seb</rdf:li></rdf:Seq></dc:creator><dc:description><rdf:Seq><rdf:li>()</rdf:li></rdf:Seq></dc:description></rdf:Description>
+</rdf:RDF>
+</x:xmpmeta>
+                                                                        
+                                                                        
+<?xpacket end='w'?>
+endstream
+endobj
+2 0 obj
+<</Producer(GPL Ghostscript 9.06)
+/CreationDate(D:20141222004920+01'00')
+/ModDate(D:20141222004920+01'00')
+/Title(\376\377\000t\000e\000s\000t\000_\000w\000o\000r\000d)
+/Creator(\376\377\000P\000D\000F\000C\000r\000e\000a\000t\000o\000r\000 \000V\000e\000r\000s\000i\000o\000n\000 \0001\000.\0006\000.\0000)
+/Author(\376\377\000S\000e\000b)
+/Keywords()
+/Subject()>>endobj
+xref
+0 10
+0000000000 65535 f 
+0000000484 00000 n 
+0000002268 00000 n 
+0000000425 00000 n 
+0000000284 00000 n 
+0000000015 00000 n 
+0000000265 00000 n 
+0000000577 00000 n 
+0000000548 00000 n 
+0000000643 00000 n 
+trailer
+<< /Size 10 /Root 1 0 R /Info 2 0 R
+/ID [<0CB231047435B33BCE0B1C6881DCF011><0CB231047435B33BCE0B1C6881DCF011>]
+>>
+startxref
+2648
+%%EOF

src/backend/chat/tests/agent_rag/document_converter/test_docling.py

@@ -0,0 +1,18 @@
+"""
+Unit tests for the DoclingParser.
+"""
+from chat.agent_rag.document_converter.parser import DoclingParser
+
+
+def test_document_converter():
+    """Test that the DocumentConverter calls the underlying MarkItDown converter."""
+    file_name = "test"
+    content_type = "application/pdf"
+    file_path = "src/backend/chat/tests/data/test.pdf"
+    parser = DoclingParser()
+
+    with open(file_path, "rb") as file:
+        content = file.read()
+        result = parser.parse_document(name= file_name, content_type= content_type, content= content)
+
+    assert "Document PDF test" in result

src/backend/chat/tests/agent_rag/document_converter/test_markitdown.py

@@ -5,28 +5,21 @@ Only for coverage as the DocumentConverter is a simple wrapper around MarkItDown
 """
 
 from io import BytesIO
-from unittest.mock import MagicMock, patch
 
 from chat.agent_rag.document_converter.markitdown import DocumentConverter
 
 
-@patch("chat.agent_rag.document_converter.markitdown.MarkItDown")
-def test_document_converter(mock_markitdown: MagicMock):
+def test_document_converter():
     """Test that the DocumentConverter calls the underlying MarkItDown converter."""
-    mock_conversion = MagicMock()
-    mock_conversion.text_content = "converted text"
-    mock_markitdown.return_value.convert_stream.return_value = mock_conversion
-
+    file_path = "src/backend/chat/tests/data/test.pdf"
     converter = DocumentConverter()
 
-    result = converter.convert_raw(
-        name="test.pdf",
-        content_type="application/pdf",
-        content=b"test content",
-    )
+    with open(file_path, "rb") as file:
+        content = file.read()
+        result = converter.convert_raw(
+            name="test.pdf",
+            content_type="application/pdf",
+            content=content,
+        )
 
-    assert result == "converted text"
-    converter.converter.convert_stream.assert_called_once()  # pylint: disable=no-member
-    args, kwargs = converter.converter.convert_stream.call_args  # pylint: disable=no-member
-    assert isinstance(args[0], BytesIO)
-    assert kwargs["file_extension"] == ".pdf"
+    assert result == "Document PDF test\n\n"

src/backend/chat/tests/agents/test_build_conversation_agent.py

@@ -27,9 +27,14 @@ def test_build_pydantic_agent_success_no_tools():
     """Test successful agent creation without tools."""
     agent = ConversationAgent(model_hrid="default-model")
     assert isinstance(agent, Agent)
+    assert agent._system_prompts == ()
+
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[2].__name__ == "enforce_response_language"
 
-    assert agent._system_prompts == ("You are a helpful assistant",)
-    assert agent._instructions == []
     assert isinstance(agent.model, OpenAIChatModel)
     assert agent.model.model_name == "model-123"
     assert str(agent.model.client.base_url) == "https://api.llm.com/v1/"
@@ -37,6 +42,7 @@ def test_build_pydantic_agent_success_no_tools():
     assert agent._function_toolset.tools == {}
 
 
+@freeze_time("2025-07-25T10:36:35.297675Z")
 def test_build_pydantic_agent_with_tools(settings):
     """Test successful agent creation with tools."""
     settings.AI_AGENT_TOOLS = ["get_current_weather"]
@@ -44,8 +50,14 @@ def test_build_pydantic_agent_with_tools(settings):
     agent = ConversationAgent(model_hrid="default-model")
     assert isinstance(agent, Agent)
 
-    assert agent._system_prompts == ("You are a helpful assistant",)
-    assert agent._instructions == []
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[1]() == "Today is Friday 25/07/2025."
+    assert instructions[2].__name__ == "enforce_response_language"
+    assert instructions[2]() == ""
+
     assert isinstance(agent.model, OpenAIChatModel)
     assert agent.model.model_name == "model-123"
     assert str(agent.model.client.base_url) == "https://api.llm.com/v1/"
@@ -56,21 +68,23 @@ def test_build_pydantic_agent_with_tools(settings):
 @freeze_time("2025-07-25T10:36:35.297675Z")
 def test_add_dynamic_system_prompt():
     """
-    Ensure add_the_date and enforce_response_language system prompt are registered
+    Ensure add_the_date and enforce_response_language instructions are registered
     and returns proper values.
     """
     agent = ConversationAgent(model_hrid="default-model")
 
-    assert len(agent._system_prompt_functions) == 2
+    assert len(agent._system_prompt_functions) == 0
 
-    assert agent._system_prompt_functions[0].function.__name__ == "add_the_date"
-    assert agent._system_prompt_functions[0].function() == "Today is Friday 25/07/2025."
-
-    assert agent._system_prompt_functions[1].function.__name__ == "enforce_response_language"
-    assert agent._system_prompt_functions[1].function() == ""
+    instructions = agent._instructions
+    assert len(instructions) == 3
+    assert instructions[0] == "You are a helpful assistant"
+    assert instructions[1].__name__ == "add_the_date"
+    assert instructions[1]() == "Today is Friday 25/07/2025."
+    assert instructions[2].__name__ == "enforce_response_language"
+    assert instructions[2]() == ""
 
     agent = ConversationAgent(model_hrid="default-model", language="fr-fr")
-    assert agent._system_prompt_functions[1].function() == "Answer in french."
+    assert agent._instructions[2]() == "Answer in french."
 
 
 def test_agent_get_web_search_tool_name(settings):

src/backend/chat/tests/data/test.pdf

@@ -0,0 +1,90 @@
+%PDF-1.4
+%Çì�¢
+5 0 obj
+<</Length 6 0 R/Filter /FlateDecode>>
+stream
+xœMŽ±NÄ0†÷<…Çd¨ÏNœ¸^OÀÀ§l'¦Šc*¨âx’RªÚƒ­ÿóo{
BŽ@=ÿ›ivnq#¦«xì§ÎÕ�.
+ÍQoŽÐÌ„WÆ „#h!¨³»ú‡À˜5Sò_a Œ&¦â§�°•Ÿƒ4‡!¢ÊÅ¿ÿÑϽwÊ%çÑC—Y4[ò/a�ö³n‡D¢
+‹æhû¨Z<nØö‡�1F3Ýaj–·úì«{mùµi:uendstream
+endobj
+6 0 obj
+180
+endobj
+4 0 obj
+<</Type/Page/MediaBox [0 0 595 842]
+/Rotate 0/Parent 3 0 R
+/Resources<</ProcSet[/PDF /Text]
+/Font 8 0 R
+>>
+/Contents 5 0 R
+>>
+endobj
+3 0 obj
+<< /Type /Pages /Kids [
+4 0 R
+] /Count 1
+>>
+endobj
+1 0 obj
+<</Type /Catalog /Pages 3 0 R
+/Metadata 9 0 R
+>>
+endobj
+8 0 obj
+<</R7
+7 0 R>>
+endobj
+7 0 obj
+<</BaseFont/Times-Roman/Type/Font
+/Subtype/Type1>>
+endobj
+9 0 obj
+<</Type/Metadata
+/Subtype/XML/Length 1549>>stream
+<?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>
+<?adobe-xap-filters esc="CRLF"?>
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='XMP toolkit 2.9.1-13, framework 1.6'>
+<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#' xmlns:iX='http://ns.adobe.com/iX/1.0/'>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:pdf='http://ns.adobe.com/pdf/1.3/'><pdf:Producer>GPL Ghostscript 9.06</pdf:Producer>
+<pdf:Keywords>()</pdf:Keywords>
+</rdf:Description>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:xmp='http://ns.adobe.com/xap/1.0/'><xmp:ModifyDate>2014-12-22T00:49:20+01:00</xmp:ModifyDate>
+<xmp:CreateDate>2014-12-22T00:49:20+01:00</xmp:CreateDate>
+<xmp:CreatorTool>PDFCreator Version 1.6.0</xmp:CreatorTool></rdf:Description>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:xapMM='http://ns.adobe.com/xap/1.0/mm/' xapMM:DocumentID='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c'/>
+<rdf:Description rdf:about='uuid:81d69fb9-8bc7-11e4-0000-66b1dd18110c' xmlns:dc='http://purl.org/dc/elements/1.1/' dc:format='application/pdf'><dc:title><rdf:Alt><rdf:li xml:lang='x-default'>test_word</rdf:li></rdf:Alt></dc:title><dc:creator><rdf:Seq><rdf:li>Seb</rdf:li></rdf:Seq></dc:creator><dc:description><rdf:Seq><rdf:li>()</rdf:li></rdf:Seq></dc:description></rdf:Description>
+</rdf:RDF>
+</x:xmpmeta>
+                                                                        
+                                                                        
+<?xpacket end='w'?>
+endstream
+endobj
+2 0 obj
+<</Producer(GPL Ghostscript 9.06)
+/CreationDate(D:20141222004920+01'00')
+/ModDate(D:20141222004920+01'00')
+/Title(\376\377\000t\000e\000s\000t\000_\000w\000o\000r\000d)
+/Creator(\376\377\000P\000D\000F\000C\000r\000e\000a\000t\000o\000r\000 \000V\000e\000r\000s\000i\000o\000n\000 \0001\000.\0006\000.\0000)
+/Author(\376\377\000S\000e\000b)
+/Keywords()
+/Subject()>>endobj
+xref
+0 10
+0000000000 65535 f 
+0000000484 00000 n 
+0000002268 00000 n 
+0000000425 00000 n 
+0000000284 00000 n 
+0000000015 00000 n 
+0000000265 00000 n 
+0000000577 00000 n 
+0000000548 00000 n 
+0000000643 00000 n 
+trailer
+<< /Size 10 /Root 1 0 R /Info 2 0 R
+/ID [<0CB231047435B33BCE0B1C6881DCF011><0CB231047435B33BCE0B1C6881DCF011>]
+>>
+startxref
+2648
+%%EOF

src/backend/chat/tests/tools/test_web_search_brave.py

@@ -38,9 +38,6 @@ def brave_settings(settings):
     settings.BRAVE_SEARCH_EXTRA_SNIPPETS = True
     settings.BRAVE_SUMMARIZATION_ENABLED = False
     settings.BRAVE_CACHE_TTL = 3600
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
     settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER = 5
 
 

src/backend/chat/tests/views/chat/conftest.py

@@ -0,0 +1,17 @@
+"""Common test fixtures for chat views tests."""
+
+from unittest import mock
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def mock_process_request():
+    """
+    Mock process_request to bypass OIDC authentication in tests.
+    """
+    with mock.patch(
+        "lasuite.oidc_login.decorators.RefreshOIDCAccessToken.process_request"
+    ) as mocked_process_request:
+        mocked_process_request.return_value = None
+        yield mocked_process_request

src/backend/chat/tests/views/chat/conversations/test_conversation.py

@@ -130,6 +130,16 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
 
     assert mock_openai_stream.called
 
+    # ensure instructions are merged as a system prompt
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    assert last_request_payload["messages"][0] == {
+        "content": (
+            "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
+            "Answer in english."
+        ),
+        "role": "system",
+    }
+
     chat_conversation.refresh_from_db()
     assert chat_conversation.ui_messages == [
         {
@@ -170,29 +180,15 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
     )
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",
@@ -255,6 +251,15 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
     assert response_content == "Hello there"
 
     assert mock_openai_stream.called
+    # ensure instructions are merged as a system prompt
+    last_request_payload = json.loads(respx.calls.last.request.content)
+    assert last_request_payload["messages"][0] == {
+        "content": (
+            "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025.\n\n"
+            "Answer in english."
+        ),
+        "role": "system",
+    }
 
     chat_conversation.refresh_from_db()
     assert chat_conversation.ui_messages == [
@@ -296,29 +301,15 @@ def test_post_conversation_text_protocol(api_client, mock_openai_stream):
     )
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",
@@ -409,11 +400,12 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
     # Check the exact structure expected by the AI service
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\nToday is Friday 25/07/2025."
+                "\n\nAnswer in english."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in english.", "role": "system"},
         {
             "content": [
                 {"text": "Hello, what do you see on this picture?", "type": "text"},
@@ -498,27 +490,12 @@ def test_post_conversation_with_image(api_client, mock_openai_stream_image):
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": [
                         "Hello, what do you see on this picture?",
@@ -616,11 +593,12 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
 
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in english.", "role": "system"},
         {"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
     ]
 
@@ -678,27 +656,12 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Weather in Paris?"],
                     "part_kind": "user-prompt",
@@ -737,7 +700,10 @@ def test_post_conversation_tool_call(api_client, mock_openai_stream_tool, settin
             "run_id": _run_id,
         },
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
                 {
@@ -829,11 +795,12 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
 
     assert body["messages"] == [
         {
-            "content": "You are a helpful test assistant :)",
+            "content": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "role": "system",
         },
-        {"content": "Today is Friday 25/07/2025.", "role": "system"},
-        {"content": "Answer in french.", "role": "system"},
         {"content": [{"text": "Weather in Paris?", "type": "text"}], "role": "user"},
     ]
 
@@ -891,27 +858,12 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in french.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Weather in Paris?"],
                     "part_kind": "user-prompt",
@@ -950,7 +902,10 @@ def test_post_conversation_tool_call_fails(api_client, mock_openai_stream_tool,
             "run_id": _run_id,
         },
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in french."
+            ),
             "kind": "request",
             "parts": [
                 {
@@ -1214,27 +1169,11 @@ def test_post_conversation_data_protocol_no_stream(
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are an amazing assistant.\n\nToday is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are an amazing assistant.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Why the sky is blue?"],
                     "part_kind": "user-prompt",
@@ -1369,27 +1308,12 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Today is Friday 25/07/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-07-25T10:36:35.297675Z",
-                },
                 {
                     "content": ["Hello"],
                     "part_kind": "user-prompt",

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_upload.py

@@ -8,6 +8,7 @@ import logging
 from io import BytesIO
 from unittest import mock
 
+from django.contrib.sessions.backends.cache import SessionStore
 from django.utils import formats, timezone
 
 import httpx
@@ -41,28 +42,49 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
-    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
-    settings.AI_API_KEY = "test-api-key"
-    settings.AI_MODEL = "test-model"
-    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
 
-    # Enable Albert API for document search
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
-    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
-    settings.ALBERT_API_KEY = "albert-api-key"
+    # enable on rag document search tool
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.RAG_WEB_SEARCH_PROMPT_UPDATE = (
         "Based on the following document contents:\n\n{search_results}\n\n"
         "Please answer the user's question: {user_prompt}"
     )
 
+    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
+    settings.AI_API_KEY = "test-api-key"
+    settings.AI_MODEL = "test-model"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
+
+    # Albert API settings
+    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
+    settings.ALBERT_API_KEY = "albert-api-key"
+
+    # Find API settings
+    settings.FIND_API_URL = "https://find.api.example.com"
+    settings.FIND_API_KEY = "find-api-key"
+
     return settings
 
 
+@pytest.fixture(autouse=True)
+def mock_refresh_access_token():
+    """Mock refresh_access_token to bypass token refresh in tests."""
+    with mock.patch("utils.oidc.refresh_access_token") as mocked_refresh_access_token:
+        session = SessionStore()
+        session["oidc_access_token"] = "mocked-access-token"
+        mocked_refresh_access_token.return_value = session
+        yield mocked_refresh_access_token
+
+
 @pytest.fixture(name="sample_pdf_content")
 def fixture_sample_pdf_content():
     """Create a dummy PDF content as BytesIO."""
@@ -81,17 +103,25 @@ def fixture_sample_pdf_content():
     return BytesIO(pdf_data)
 
 
-@pytest.fixture(name="mock_albert_api")
-def fixture_mock_albert_api():
+@pytest.fixture(name="mock_document_api")
+def fixture_mock_document_api():
     """Fixture to mock the Albert API endpoints."""
     # Mock collection creation
+
+    document_name = "sample.pdf"
+    document_content = "This is the content of the PDF."
+    prompt_tokens = 10
+    completion_tokens = 20
+    search_method = "semantic"
+    search_score = 0.9
+
     responses.post(
         "https://albert.api.etalab.gouv.fr/v1/collections",
         json={"id": "123", "name": "test-collection"},
         status=status.HTTP_200_OK,
     )
 
-    # Mock PDF parsing
+    # Mock Albert PDF parsing -> deprecated
     responses.post(
         "https://albert.api.etalab.gouv.fr/v1/parse-beta",
         json={
@@ -101,7 +131,7 @@ def fixture_mock_albert_api():
                     "metadata": {"document_name": "sample.pdf"},
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
@@ -119,20 +149,42 @@ def fixture_mock_albert_api():
         json={
             "data": [
                 {
-                    "method": "semantic",
+                    "method": search_method,
                     "chunk": {
                         "id": 123,
-                        "content": "This is the content of the PDF.",
-                        "metadata": {"document_name": "sample.pdf"},
+                        "content": document_content,
+                        "metadata": {"document_name": document_name},
                     },
-                    "score": 0.9,
+                    "score": search_score,
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
 
+    # Mock document indexing (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/index/",
+        json={"id": "456", "status": "indexed"},
+        status=status.HTTP_200_OK,
+    )
+
+    # Mock document search (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/search/",
+        json=[
+            {
+                "_source": {
+                    "title.fr": document_name,
+                    "content.fr": document_content,
+                },
+                "_score": search_score,
+            }
+        ],
+        status=status.HTTP_200_OK,
+    )
+
 
 @pytest.fixture(name="mock_summarization_agent")
 def fixture_mock_summarization_agent():
@@ -216,9 +268,10 @@ def fixture_mock_openai_stream():
 @responses.activate
 @respx.mock
 @freeze_time()
-def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_document_upload(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,
@@ -353,53 +406,25 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
     assert len(chat_conversation.pydantic_messages) == 4
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
     assert chat_conversation.pydantic_messages[0] == {
-        "instructions": "When you receive a result from the summarization tool, you "
-        "MUST return it directly to the user without any "
-        "modification, paraphrasing, or additional summarization.The "
-        "tool already produces optimized summaries that should be "
-        "presented verbatim.You may translate the summary if "
-        "required, but you MUST preserve all the information from the "
-        "original summary.You may add a follow-up question after the "
-        "summary if needed.",
+        "instructions": "You are a helpful test assistant :)\n\n"
+        f"{today_promt_date}\n\n"
+        "Answer in english.\n\n"
+        "Use document_search_rag ONLY to retrieve specific passages from "
+        "attached documents. Do NOT use it to summarize; for summaries, "
+        "call the summarize tool instead.\n\nWhen you receive a result from the "
+        "summarization tool, you MUST return it directly to the user without "
+        "any modification, paraphrasing, or additional summarization."
+        "The tool already produces optimized summaries that should be "
+        "presented verbatim.You may translate the summary if required, "
+        "but you MUST preserve all the information from the original summary."
+        "You may add a follow-up question after the summary if needed.\n\n"
+        "[Internal context] User documents are attached to this conversation. "
+        "Do not request re-upload of documents; consider them already "
+        "available via the internal store.",
         "kind": "request",
         "parts": [
-            {
-                "content": "You are a helpful test assistant :)",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": today_promt_date,
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Answer in english.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Use document_search_rag ONLY to retrieve specific "
-                "passages from attached documents. Do NOT use it to "
-                "summarize; for summaries, call the summarize tool "
-                "instead.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "[Internal context] User documents are attached to this "
-                "conversation. Do not request re-upload of documents; "
-                "consider them already available via the internal "
-                "store.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
             {
                 "content": ["What does the document say?"],
                 "part_kind": "user-prompt",
@@ -439,14 +464,21 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
     }
     assert chat_conversation.pydantic_messages[2] == {
         "instructions": (
-            "When you receive a result from the summarization tool, you MUST "
-            "return it directly to the user without any modification, "
-            "paraphrasing, or additional summarization."
-            "The tool already produces optimized summaries that should "
-            "be presented verbatim."
-            "You may translate the summary if required, but you MUST preserve "
-            "all the information from the original summary."
-            "You may add a follow-up question after the summary if needed."
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
         ),
         "kind": "request",
         "parts": [
@@ -499,7 +531,8 @@ def test_post_conversation_with_document_upload(  # pylint: disable=too-many-arg
 @responses.activate
 @respx.mock
 @freeze_time("2025-07-25T10:36:35.297675Z")
-def test_post_conversation_with_document_upload_feature_disabled(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_document_upload_feature_disabled(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     caplog,
     mock_openai_stream,  # pylint: disable=unused-argument
@@ -552,14 +585,12 @@ def test_post_conversation_with_document_upload_feature_disabled(  # pylint: dis
 
     # Replace UUIDs with placeholders for assertion
     response_content = replace_uuids_with_placeholder(response_content)
-
     assert response_content == (
         '0:"From the document, I can see that "\n'
         "0:\"it says 'Hello PDF'.\"\n"
         'f:{"messageId":"<mocked_uuid>"}\n'
         'd:{"finishReason":"stop","usage":{"promptTokens":150,"completionTokens":25}}\n'
     )
-
     # This behavior must be improved in the future to inform the user properly
     assert "Document upload feature is disabled, ignoring input documents." in caplog.text
 
@@ -569,7 +600,7 @@ def test_post_conversation_with_document_upload_feature_disabled(  # pylint: dis
 @freeze_time()
 def test_post_conversation_with_document_upload_summarize(  # pylint: disable=too-many-arguments,too-many-positional-arguments  # noqa: PLR0913
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,
@@ -582,6 +613,7 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
     api_client.force_authenticate(user=chat_conversation.owner)
 
     pdf_base64 = base64.b64encode(sample_pdf_content.read()).decode("utf-8")
+
     message = UIMessage(
         id="1",
         role="user",
@@ -643,7 +675,7 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
         'document discusses various topics."}\n'
         '0:"The document discusses various topics."\n'
         'f:{"messageId":"<mocked_uuid>"}\n'
-        'd:{"finishReason":"stop","usage":{"promptTokens":317,"completionTokens":19}}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":283,"completionTokens":19}}\n'
     )
 
     # Check that the conversation was updated
@@ -705,52 +737,25 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
 
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages[0] == {
-        "instructions": "When you receive a result from the summarization tool, you "
-        "MUST return it directly to the user without any "
-        "modification, paraphrasing, or additional summarization.The "
-        "tool already produces optimized summaries that should be "
-        "presented verbatim.You may translate the summary if "
-        "required, but you MUST preserve all the information from the "
-        "original summary.You may add a follow-up question after the "
-        "summary if needed.",
+        "instructions": (
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
+        ),
         "kind": "request",
         "parts": [
-            {
-                "content": "You are a helpful test assistant :)",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": today_promt_date,
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Answer in english.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "Use document_search_rag ONLY to retrieve specific "
-                "passages from attached documents. Do NOT use it to "
-                "summarize; for summaries, call the summarize tool "
-                "instead.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
-            {
-                "content": "[Internal context] User documents are attached to this "
-                "conversation. Do not request re-upload of documents; "
-                "consider them already available via the internal "
-                "store.",
-                "dynamic_ref": None,
-                "part_kind": "system-prompt",
-                "timestamp": timezone_now,
-            },
             {
                 "content": ["Make a summary of this document."],
                 "part_kind": "user-prompt",
@@ -790,14 +795,21 @@ def test_post_conversation_with_document_upload_summarize(  # pylint: disable=to
     }
     assert chat_conversation.pydantic_messages[2] == {
         "instructions": (
-            "When you receive a result from the summarization tool, you MUST "
-            "return it directly to the user without any modification, "
-            "paraphrasing, or additional summarization."
-            "The tool already produces optimized summaries that should "
-            "be presented verbatim."
-            "You may translate the summary if required, but you MUST preserve "
-            "all the information from the original summary."
-            "You may add a follow-up question after the summary if needed."
+            "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.\n\n"
+            "Use document_search_rag ONLY to retrieve specific passages from "
+            "attached documents. Do NOT use it to summarize; for summaries, "
+            "call the summarize tool instead.\n\nWhen you receive a result from the "
+            "summarization tool, you MUST return it directly to the user without "
+            "any modification, paraphrasing, or additional summarization."
+            "The tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if required, "
+            "but you MUST preserve all the information from the original summary."
+            "You may add a follow-up question after the summary if needed.\n\n"
+            "[Internal context] User documents are attached to this conversation. "
+            "Do not request re-upload of documents; consider them already "
+            "available via the internal store."
         ),
         "kind": "request",
         "parts": [

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_url.py

@@ -17,7 +17,6 @@ from pydantic_ai.messages import (
     DocumentUrl,
     ModelMessage,
     ModelResponse,
-    SystemPromptPart,
     TextPart,
     UserPromptPart,
 )
@@ -38,11 +37,19 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.AI_BASE_URL = "https://www.external-ai-service.com/"
     settings.AI_API_KEY = "test-api-key"
+    settings.FIND_API_KEY = "find-api-key"
     settings.AI_MODEL = "test-model"
     settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
     return settings
@@ -61,7 +68,8 @@ def fixture_sample_document_content():
 
 @responses.activate
 @freeze_time()
-def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_local_pdf_document_url(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     sample_document_content,
     today_promt_date,
@@ -85,6 +93,10 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)
@@ -120,7 +132,7 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
+        presigned_url = messages[0].parts[0].content[1].url
         assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
@@ -129,11 +141,6 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this document?",
@@ -146,6 +153,8 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
+                "\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -221,27 +230,11 @@ def test_post_conversation_with_local_pdf_document_url(  # pylint: disable=too-m
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            f"{today_promt_date}\n\n"
+            "Answer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
                 {
                     "content": [
                         "What is in this document?",
@@ -429,7 +422,6 @@ def test_post_conversation_with_remote_document_url(
 @freeze_time("2025-10-18T20:48:20.286204Z")
 def test_post_conversation_with_local_document_url_in_history(  # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
-    today_promt_date,
     mock_ai_agent_service,
 ):
     """
@@ -437,6 +429,8 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     """
     chat_conversation_pk = "0be55da5-8eb7-4dad-aa0f-fea454bd5809"
     document_url = f"/media-key/{chat_conversation_pk}/sample.pdf"
+    formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
+
     chat_conversation = ChatConversationFactory(
         pk=chat_conversation_pk,
         owner__language="en-us",
@@ -472,27 +466,11 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         ],
         pydantic_messages=[
             {
-                "instructions": None,
+                "instructions": "You are a helpful test assistant :)\n\n"
+                f"Today is {formatted_date}.\n\n"
+                "Answer in english.",
                 "kind": "request",
                 "parts": [
-                    {
-                        "content": "You are a helpful test assistant :)",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": today_promt_date,
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": "Answer in english.",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
                     {
                         "content": [
                             "What is in this document?",
@@ -555,7 +533,7 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
+        presigned_url = messages[0].parts[0].content[1].url
         assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
@@ -564,18 +542,6 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)",
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=today_promt_date,
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content="Answer in english.",
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this document?",
@@ -588,6 +554,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\n"
+                "Answer in english.",
                 run_id=messages[0].run_id,
             ),
             ModelResponse(
@@ -606,6 +575,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
                         timestamp=timezone.now(),
                     )
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\n"
+                "Answer in english.",
                 run_id=messages[2].run_id,
             ),
         ]
@@ -705,27 +677,11 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
     _run_id = chat_conversation.pydantic_messages[2]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\n"
+            "Answer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this document?",
@@ -772,7 +728,9 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
             # no run_id here
         },
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\n"
+            "Answer in english.",
             "kind": "request",
             "parts": [
                 {
@@ -823,7 +781,8 @@ def test_post_conversation_with_local_document_url_in_history(  # pylint: disabl
         ("data.csv", "text/csv"),
     ],
 )
-def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+def test_post_conversation_with_local_not_pdf_document_url(
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
     today_promt_date,
     mock_ai_agent_service,
@@ -848,6 +807,10 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)
@@ -886,27 +849,6 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
-                    SystemPromptPart(
-                        content=(
-                            "Use document_search_rag ONLY to retrieve specific passages from "
-                            "attached documents. Do NOT use it to summarize; for summaries, "
-                            "call the summarize tool instead."
-                        ),
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=(
-                            "[Internal context] User documents are attached to this conversation. "
-                            "Do not request re-upload of documents; consider them already "
-                            "available via the internal store."
-                        ),
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this document?",
@@ -916,14 +858,22 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
                     ),
                 ],
                 instructions=(
-                    "When you receive a result from the summarization tool, you MUST "
-                    "return it directly to the user without any modification, "
-                    "paraphrasing, or additional summarization."
-                    "The tool already produces optimized summaries that should "
-                    "be presented verbatim."
-                    "You may translate the summary if required, but you MUST preserve "
-                    "all the information from the original summary."
-                    "You may add a follow-up question after the summary if needed."
+                    "You are a helpful test assistant :)\n\n"
+                    f"{today_promt_date}\n\n"
+                    "Answer in english.\n\n"
+                    "Use document_search_rag ONLY to retrieve specific passages from "
+                    "attached documents. Do NOT use it to summarize; for summaries, "
+                    "call the summarize tool instead.\n\nWhen you receive a result "
+                    "from the summarization tool, you MUST return it directly to "
+                    "the user without any modification, paraphrasing, or additional "
+                    "summarization.The tool already produces optimized summaries "
+                    "that should be presented verbatim.You may translate the summary "
+                    "if required, but you MUST preserve all the information from the "
+                    "original summary.You may add a follow-up question after the "
+                    "summary if needed.\n\n"
+                    "[Internal context] User documents are attached to this conversation. "
+                    "Do not request re-upload of documents; "
+                    "consider them already available via the internal store."
                 ),
                 run_id=messages[0].run_id,
             )
@@ -999,53 +949,25 @@ def test_post_conversation_with_local_not_pdf_document_url(  # pylint: disable=t
     assert chat_conversation.pydantic_messages == [
         {
             "instructions": (
-                "When you receive a result from the summarization tool, you MUST "
-                "return it directly to the user without any modification, "
-                "paraphrasing, or additional summarization."
-                "The tool already produces optimized summaries that should "
-                "be presented verbatim."
-                "You may translate the summary if required, but you MUST preserve "
-                "all the information from the original summary."
-                "You may add a follow-up question after the summary if needed."
+                "You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\n"
+                "Answer in english.\n\n"
+                "Use document_search_rag ONLY to retrieve specific passages from "
+                "attached documents. Do NOT use it to summarize; for summaries, "
+                "call the summarize tool instead.\n\nWhen you receive a result "
+                "from the summarization tool, you MUST return it directly to "
+                "the user without any modification, paraphrasing, or additional "
+                "summarization.The tool already produces optimized summaries "
+                "that should be presented verbatim.You may translate the summary "
+                "if required, but you MUST preserve all the information from the "
+                "original summary.You may add a follow-up question after the "
+                "summary if needed.\n\n"
+                "[Internal context] User documents are attached to this conversation. "
+                "Do not request re-upload of documents; "
+                "consider them already available via the internal store."
             ),
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "Use document_search_rag ONLY to retrieve specific "
-                    "passages from attached documents. Do NOT use it to "
-                    "summarize; for summaries, call the summarize tool "
-                    "instead.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
-                {
-                    "content": "[Internal context] User documents are attached to "
-                    "this conversation. Do not request re-upload of "
-                    "documents; consider them already available via the "
-                    "internal store.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": timestamp,
-                },
                 {
                     "content": [
                         "What is in this document?",

src/backend/chat/tests/views/chat/conversations/test_conversation_with_history.py

@@ -919,7 +919,7 @@ def history_conversation_with_tool_fixture():
     history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
 
     # Create a conversation with pre-existing messages including a tool invocation
-    conversation = ChatConversationFactory()
+    conversation = ChatConversationFactory(owner__language="nl-nl")
 
     # Add previous user and assistant messages with tool invocation
     conversation.messages = [
@@ -1377,7 +1377,9 @@ def test_post_conversation_with_existing_tool_history(
 
     # Verify the new tool call request is included
     assert history_conversation_with_tool.pydantic_messages[8] == {
-        "instructions": None,
+        "instructions": "You are a helpful test assistant :)\n\n"
+        "Today is Friday 25/07/2025.\n\n"
+        "Answer in dutch.",
         "kind": "request",
         "parts": [
             {
@@ -1420,7 +1422,9 @@ def test_post_conversation_with_existing_tool_history(
     }
 
     assert history_conversation_with_tool.pydantic_messages[10] == {
-        "instructions": None,
+        "instructions": "You are a helpful test assistant :)\n\n"
+        "Today is Friday 25/07/2025.\n\n"
+        "Answer in dutch.",
         "kind": "request",
         "parts": [
             {

src/backend/chat/tests/views/chat/conversations/test_conversation_with_image_url.py

@@ -2,7 +2,7 @@
 
 import uuid
 
-from django.utils import timezone
+from django.utils import formats, timezone
 
 import pytest
 from dirty_equals import IsUUID
@@ -12,7 +12,6 @@ from pydantic_ai.messages import (
     ImageUrl,
     ModelMessage,
     ModelResponse,
-    SystemPromptPart,
     TextPart,
     UserPromptPart,
 )
@@ -87,22 +86,15 @@ def test_post_conversation_with_local_image_url(
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
-        assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
+        presigned_url = messages[0].parts[0].content[1].url
+        # assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
         assert presigned_url.find("X-Amz-Expires=") != -1
-
+        formatted_date = formats.date_format(timezone.now(), "l d/m/Y", use_l10n=False)
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(
-                        content="Today is Saturday 18/10/2025.", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -115,6 +107,8 @@ def test_post_conversation_with_local_image_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\nToday is "
+                f"{formatted_date}.\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -184,27 +178,10 @@ def test_post_conversation_with_local_image_url(
     _run_id = chat_conversation.pydantic_messages[0]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\n"
+            "Today is Saturday 18/10/2025.\n\nAnswer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Today is Saturday 18/10/2025.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this image?",
@@ -286,11 +263,6 @@ def test_post_conversation_with_local_image_wrong_url(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -303,6 +275,8 @@ def test_post_conversation_with_local_image_wrong_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
+                "\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -374,11 +348,6 @@ def test_post_conversation_with_remote_image_url(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)", timestamp=timezone.now()
-                    ),
-                    SystemPromptPart(content=today_promt_date, timestamp=timezone.now()),
-                    SystemPromptPart(content="Answer in english.", timestamp=timezone.now()),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -391,6 +360,8 @@ def test_post_conversation_with_remote_image_url(
                         timestamp=timezone.now(),
                     ),
                 ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\nAnswer in english.",
                 run_id=messages[0].run_id,
             )
         ]
@@ -504,27 +475,10 @@ def test_post_conversation_with_local_image_url_in_history(
         ],
         pydantic_messages=[
             {
-                "instructions": None,
+                "instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
+                "\n\nAnswer in english.",
                 "kind": "request",
                 "parts": [
-                    {
-                        "content": "You are a helpful test assistant :)",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": today_promt_date,
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
-                    {
-                        "content": "Answer in english.",
-                        "dynamic_ref": None,
-                        "part_kind": "system-prompt",
-                        "timestamp": "2025-10-18T20:48:20.286204Z",
-                    },
                     {
                         "content": [
                             "What is in this image?",
@@ -587,7 +541,7 @@ def test_post_conversation_with_local_image_url_in_history(
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[3].content[1].url
+        presigned_url = messages[0].parts[0].content[1].url
         assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
         assert presigned_url.find("X-Amz-Signature=") != -1
         assert presigned_url.find("X-Amz-Date=") != -1
@@ -596,18 +550,6 @@ def test_post_conversation_with_local_image_url_in_history(
         assert messages == [
             ModelRequest(
                 parts=[
-                    SystemPromptPart(
-                        content="You are a helpful test assistant :)",
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content=today_promt_date,
-                        timestamp=timezone.now(),
-                    ),
-                    SystemPromptPart(
-                        content="Answer in english.",
-                        timestamp=timezone.now(),
-                    ),
                     UserPromptPart(
                         content=[
                             "What is in this image?",
@@ -619,7 +561,9 @@ def test_post_conversation_with_local_image_url_in_history(
                         ],
                         timestamp=timezone.now(),
                     ),
-                ]
+                ],
+                instructions="You are a helpful test assistant :)\n\n"
+                f"{today_promt_date}\n\nAnswer in english.",
             ),
             ModelResponse(
                 parts=[TextPart(content="This is an image of a single pixel.")],
@@ -637,6 +581,8 @@ def test_post_conversation_with_local_image_url_in_history(
                     )
                 ],
                 run_id=messages[2].run_id,
+                instructions="You are a helpful test assistant :)\n\n"
+                "Today is Saturday 18/10/2025.\n\nAnswer in english.",
             ),
         ]
         yield "This is an image of square, very small and nice."
@@ -735,27 +681,10 @@ def test_post_conversation_with_local_image_url_in_history(
     _run_id = chat_conversation.pydantic_messages[2]["run_id"]
     assert chat_conversation.pydantic_messages == [
         {
-            "instructions": None,
+            "instructions": f"You are a helpful test assistant :)\n\n{today_promt_date}"
+            "\n\nAnswer in english.",
             "kind": "request",
             "parts": [
-                {
-                    "content": "You are a helpful test assistant :)",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": today_promt_date,
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
-                {
-                    "content": "Answer in english.",
-                    "dynamic_ref": None,
-                    "part_kind": "system-prompt",
-                    "timestamp": "2025-10-18T20:48:20.286204Z",
-                },
                 {
                     "content": [
                         "What is in this image?",
@@ -796,7 +725,8 @@ def test_post_conversation_with_local_image_url_in_history(
             },
         },
         {
-            "instructions": None,
+            "instructions": "You are a helpful test assistant :)\n\nToday is Saturday 18/10/2025."
+            "\n\nAnswer in english.",
             "kind": "request",
             "parts": [
                 {

src/backend/chat/tests/views/chat/conversations/test_stop_streaming.py

@@ -1,4 +1,4 @@
-"""Test the post_stop_steaming view."""
+"""Test the post_stop_streaming view."""
 
 from unittest.mock import patch
 

src/backend/chat/tools/document_search_rag.py

@@ -26,7 +26,7 @@ def add_document_rag_search_tool(agent: Agent) -> None:
 
         document_store = document_store_backend(ctx.deps.conversation.collection_id)
 
-        rag_results = document_store.search(query)
+        rag_results = document_store.search(query, session=ctx.deps.session)
 
         ctx.usage += RunUsage(
             input_tokens=rag_results.usage.prompt_tokens,
@@ -39,7 +39,7 @@ def add_document_rag_search_tool(agent: Agent) -> None:
             metadata={"sources": {result.url for result in rag_results.data}},
         )
 
-    @agent.system_prompt
+    @agent.instructions
     def document_rag_instructions() -> str:
         """Dynamic system prompt function to add RAG instructions if any."""
         return (

src/backend/chat/tools/document_summarize.py

@@ -101,7 +101,7 @@ async def document_summarize(  # pylint: disable=too-many-locals
         )
         documents_chunks = chunker(
             [doc[1] for doc in documents],
-            overlap=settings.SUMMARIZATION_OVERLAP_SIZE,
+            # overlap=settings.SUMMARIZATION_OVERLAP_SIZE,
         )
 
         logger.info(

src/backend/chat/tools/exceptions.py

@@ -3,17 +3,6 @@
 from pydantic_ai import ModelRetry
 
 
-class ModelRetryLast(ModelRetry):
-    """
-    Same as ModelRetry but also holds the last retry message to return when all attempts failed.
-    """
-
-    def __init__(self, message: str, last_retry_message: str):
-        """Initialize ModelRetryLast with message and last retry message."""
-        self.last_retry_message = last_retry_message
-        super().__init__(message)
-
-
 class ModelCannotRetry(ModelRetry):
     """
     Exception to raise when a tool function cannot be retried.

src/backend/chat/tools/web_search_brave.py

@@ -127,7 +127,7 @@ async def _extract_and_summarize_snippets_async(query: str, url: str) -> List[st
         return []
 
 
-async def _fetch_and_store_async(url: str, document_store) -> None:
+async def _fetch_and_store_async(url: str, document_store, **kwargs) -> None:
     """Fetch, extract and store text content from the URL in the document store."""
 
     try:
@@ -136,7 +136,7 @@ async def _fetch_and_store_async(url: str, document_store) -> None:
         logger.debug("Fetched document: %s", document)
 
         if document:
-            await document_store.astore_document(url, document)
+            await document_store.astore_document(url, document, **kwargs)
     except DocumentFetchError as e:
         logger.warning("Failed to fetch and store %s: %s", url, e)
         # Continue with other documents

src/backend/chat/views.py

@@ -7,11 +7,13 @@ from uuid import uuid4
 from django.conf import settings
 from django.core.files.storage import default_storage
 from django.http import Http404, StreamingHttpResponse
+from django.utils.decorators import method_decorator
 
 import langfuse
 import magic
 import posthog
 from lasuite.malware_detection import malware_detection
+from lasuite.oidc_login.decorators import refresh_oidc_access_token
 from rest_framework import decorators, filters, mixins, permissions, status, viewsets
 from rest_framework.exceptions import MethodNotAllowed, PermissionDenied, ValidationError
 from rest_framework.response import Response
@@ -122,6 +124,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
             self.permission_classes = []
         return super().get_permissions()
 
+    @method_decorator(refresh_oidc_access_token)
     @decorators.action(
         methods=["post"],
         detail=True,
@@ -173,6 +176,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         ai_service = AIAgentService(
             conversation=conversation,
             user=self.request.user,
+            session=request.session,
             model_hrid=model_hrid,
             language=(
                 self.request.user.language
@@ -221,7 +225,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         url_path="stop-streaming",
         url_name="stop-streaming",
     )
-    def post_stop_steaming(self, request, pk):  # pylint: disable=unused-argument
+    def post_stop_streaming(self, request, pk):  # pylint: disable=unused-argument
         """Handle POST requests to stop streaming the chat conversation.
 
         This action will put a poison pill in the redis cache to stop any ongoing streaming.

src/backend/conftest.py

@@ -22,7 +22,7 @@ def no_http_requests(monkeypatch):
     Credits: https://blog.jerrycodes.com/no-http-requests/
     """
 
-    allowed_hosts = {"localhost", "minio", "minio:9000"}
+    allowed_hosts = {"localhost", "127.0.0.1", "minio", "minio:9000"}
     original_urlopen = HTTPConnectionPool.urlopen
 
     def urlopen_mock(self, method, url, *args, **kwargs):

src/backend/conversations/settings.py

@@ -841,6 +841,23 @@ USER QUESTION:
         environ_prefix=None,
     )
 
+    # Find
+    FIND_API_KEY = values.Value(
+        None,
+        environ_name="FIND_API_KEY",
+        environ_prefix=None,
+    )
+    FIND_API_URL = values.Value(
+        "https://app-find/api",
+        environ_name="FIND_API_URL",
+        environ_prefix=None,
+    )
+    FIND_API_TIMEOUT = values.PositiveIntegerValue(
+        default=30,  # seconds
+        environ_name="FIND_API_TIMEOUT",
+        environ_prefix=None,
+    )
+
     # Logging
     # We want to make it easy to log to console but by default we log production
     # to Sentry and don't want to log to console.

src/backend/core/api/__init__.py

@@ -1,12 +1,9 @@
 """Conversations core API endpoints"""
 
-from django.conf import settings
 from django.core.exceptions import ValidationError
 
 from rest_framework import exceptions as drf_exceptions
 from rest_framework import views as drf_views
-from rest_framework.decorators import api_view
-from rest_framework.response import Response
 
 
 def exception_handler(exc, context):
@@ -28,14 +25,3 @@ def exception_handler(exc, context):
         exc = drf_exceptions.ValidationError(detail=detail)
 
     return drf_views.exception_handler(exc, context)
-
-
-# pylint: disable=unused-argument
-@api_view(["GET"])
-def get_frontend_configuration(request):
-    """Returns the frontend configuration dict as configured in settings."""
-    frontend_configuration = {
-        "LANGUAGE_CODE": settings.LANGUAGE_CODE,
-    }
-    frontend_configuration.update(settings.FRONTEND_CONFIGURATION)
-    return Response(frontend_configuration)

src/backend/core/api/serializers.py

@@ -20,23 +20,3 @@ class UserSerializer(serializers.ModelSerializer):
             "sub",
         ]
         read_only_fields = ["id", "email", "full_name", "short_name", "sub"]
-
-
-class UserLightSerializer(UserSerializer):
-    """Serialize users with limited fields."""
-
-    id = serializers.SerializerMethodField(read_only=True)
-    email = serializers.SerializerMethodField(read_only=True)
-
-    def get_id(self, _user):
-        """Return always None. Here to have the same fields than in UserSerializer."""
-        return None
-
-    def get_email(self, _user):
-        """Return always None. Here to have the same fields than in UserSerializer."""
-        return None
-
-    class Meta:
-        model = models.User
-        fields = ["id", "email", "full_name", "short_name"]
-        read_only_fields = ["id", "email", "full_name", "short_name"]

src/backend/core/authentication/__init__.py

@@ -1,52 +0,0 @@
-"""Custom authentication classes for the Conversations core app"""
-
-from django.conf import settings
-
-from rest_framework.authentication import BaseAuthentication
-from rest_framework.exceptions import AuthenticationFailed
-
-
-class ServerToServerAuthentication(BaseAuthentication):
-    """
-    Custom authentication class for server-to-server requests.
-    Validates the presence and correctness of the Authorization header.
-    """
-
-    AUTH_HEADER = "Authorization"
-    TOKEN_TYPE = "Bearer"  # noqa S105
-
-    def authenticate(self, request):
-        """
-        Authenticate the server-to-server request by validating the Authorization header.
-
-        This method checks if the Authorization header is present in the request, ensures it
-        contains a valid token with the correct format, and verifies the token against the
-        list of allowed server-to-server tokens. If the header is missing, improperly formatted,
-        or contains an invalid token, an AuthenticationFailed exception is raised.
-
-        Returns:
-            None: If authentication is successful
-                  (no user is authenticated for server-to-server requests).
-
-        Raises:
-            AuthenticationFailed: If the Authorization header is missing, malformed,
-            or contains an invalid token.
-        """
-        auth_header = request.headers.get(self.AUTH_HEADER)
-        if not auth_header:
-            raise AuthenticationFailed("Authorization header is missing.")
-
-        # Validate token format and existence
-        auth_parts = auth_header.split(" ")
-        if len(auth_parts) != 2 or auth_parts[0] != self.TOKEN_TYPE:
-            raise AuthenticationFailed("Invalid authorization header.")
-
-        token = auth_parts[1]
-        if token not in settings.SERVER_TO_SERVER_API_TOKENS:
-            raise AuthenticationFailed("Invalid server-to-server token.")
-
-        # Authentication is successful, but no user is authenticated
-
-    def authenticate_header(self, request):
-        """Return the WWW-Authenticate header value."""
-        return f"{self.TOKEN_TYPE} realm='Create document server to server'"

src/backend/core/fields.py

@@ -1,25 +0,0 @@
-"""A JSONField for DRF to handle serialization/deserialization."""
-
-import json
-
-from rest_framework import serializers
-
-
-class JSONField(serializers.Field):
-    """
-    A custom field for handling JSON data.
-    """
-
-    def to_representation(self, value):
-        """
-        Convert the JSON string to a Python dictionary for serialization.
-        """
-        return value
-
-    def to_internal_value(self, data):
-        """
-        Convert the Python dictionary to a JSON string for deserialization.
-        """
-        if data is None:
-            return None
-        return json.dumps(data)

src/backend/core/filters.py

@@ -2,31 +2,9 @@
 
 import unicodedata
 
-import django_filters
-
 
 def remove_accents(value):
     """Remove accents from a string (vélo -> velo)."""
     return "".join(
         c for c in unicodedata.normalize("NFD", value) if unicodedata.category(c) != "Mn"
     )
-
-
-class AccentInsensitiveCharFilter(django_filters.CharFilter):
-    """
-    A custom CharFilter that filters on the accent-insensitive value searched.
-    """
-
-    def filter(self, qs, value):
-        """
-        Apply the filter to the queryset using the unaccented version of the field.
-
-        Args:
-            qs: The queryset to filter.
-            value: The value to search for in the unaccented field.
-        Returns:
-            A filtered queryset.
-        """
-        if value:
-            value = remove_accents(value)
-        return super().filter(qs, value)

src/backend/core/templates/core/generate_document.html

@@ -1,14 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Generate Document</title>
-</head>
-<body>
-    <h2>Generate Document</h2>
-    <form method="post" enctype="multipart/form-data">
-        {% csrf_token %}
-        {{ form.as_p }}
-        <button type="submit">Generate PDF</button>
-    </form>
-</body>
-</html>

src/backend/core/templatetags/extra_tags.py

@@ -1,58 +0,0 @@
-"""Custom template tags for the core application of People."""
-
-import base64
-
-from django import template
-from django.contrib.staticfiles import finders
-
-from PIL import ImageFile as PillowImageFile
-
-register = template.Library()
-
-
-def image_to_base64(file_or_path, close=False):
-    """
-    Return the src string of the base64 encoding of an image represented by its path
-    or file opened or not.
-
-    Inspired by Django's "get_image_dimensions"
-    """
-    pil_parser = PillowImageFile.Parser()
-    if hasattr(file_or_path, "read"):
-        file = file_or_path
-        if file.closed and hasattr(file, "open"):
-            file_or_path.open()
-        file_pos = file.tell()
-        file.seek(0)
-    else:
-        try:
-            # pylint: disable=consider-using-with
-            file = open(file_or_path, "rb")
-        except OSError:
-            return ""
-        close = True
-
-    try:
-        image_data = file.read()
-        if not image_data:
-            return ""
-        pil_parser.feed(image_data)
-        if pil_parser.image:
-            mime_type = pil_parser.image.get_format_mimetype()
-            encoded_string = base64.b64encode(image_data)
-            return f"data:{mime_type:s};base64, {encoded_string.decode('utf-8'):s}"
-        return ""
-    finally:
-        if close:
-            file.close()
-        else:
-            file.seek(file_pos)
-
-
-@register.simple_tag
-def base64_static(path):
-    """Return a static file into a base64."""
-    full_path = finders.find(path)
-    if full_path:
-        return image_to_base64(full_path, True)
-    return ""

src/backend/pyproject.toml

@@ -43,7 +43,9 @@ dependencies = [
     "djangorestframework==3.16.1",
     "drf_spectacular==0.29.0",
     "dockerflow==2024.4.2",
+    "docling",
     "easy_thumbnails==2.10.1",
+    "easyocr",
     "factory_boy==3.3.3",
     "gunicorn==23.0.0",
     "jsonschema==4.25.1",

src/backend/utils/oidc.py

@@ -0,0 +1,54 @@
+"""Utility functions for OIDC token management."""
+
+from functools import wraps
+
+from django.conf import settings
+
+import requests
+from lasuite.oidc_login.backends import get_oidc_refresh_token, store_tokens
+from rest_framework.exceptions import AuthenticationFailed
+
+
+def refresh_access_token(session):
+    """Refresh the OIDC access token using the refresh token."""
+    refresh_token = get_oidc_refresh_token(session)
+    if not refresh_token:
+        raise AuthenticationFailed({"error": "Refresh token is missing from session"})
+
+    response = requests.post(
+        settings.OIDC_OP_TOKEN_ENDPOINT,
+        data={
+            "grant_type": "refresh_token",
+            "client_id": settings.OIDC_RP_CLIENT_ID,
+            "client_secret": settings.OIDC_RP_CLIENT_SECRET,
+            "refresh_token": refresh_token,
+        },
+        timeout=5,
+    )
+    response.raise_for_status()
+    token_info = response.json()
+
+    store_tokens(
+        session,
+        access_token=token_info.get("access_token"),
+        id_token=None,
+        refresh_token=token_info.get("refresh_token"),
+    )
+    return session
+
+
+def with_fresh_access_token(func):
+    """
+    Decorator to handle OIDC token refresh and extraction.
+    Expects 'session' in kwargs and update it with the fresh token.
+    """
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        session = kwargs.pop("session", None)
+        if session is None:
+            raise AuthenticationFailed({"error": "Session is required but not provided"})
+        refreshed_session = refresh_access_token(session)
+        return func(*args, session=refreshed_session, **kwargs)
+
+    return wrapper