✨(backend) implement DoclingServeParser

change parsers and update Docker configuration

.gitignore

@@ -44,6 +44,9 @@ env.d/development/*
 !env.d/development/*.dist
 env.d/terraform
 
+# Configuration
+**/conversations/configuration/llm/dev.json
+
 # npm
 node_modules
 

CHANGELOG.md

@@ -8,6 +8,10 @@ and this project adheres to
 
 ## [Unreleased]
 
+### Added
+
+- ✨(backend) add FindRagBackend
+
 ### Changed
 
 - 📦️(front) update react

Makefile

@@ -53,9 +53,6 @@ MAIL_YARN           = $(COMPOSE_RUN) -w /app/src/mail node yarn
 # -- Frontend
 PATH_FRONT          = ./src/frontend
 PATH_FRONT_CONVERSATIONS  = $(PATH_FRONT)/apps/conversations
-FRONTEND_YARN       = $(COMPOSE_RUN) -w /app/src/frontend node yarn
-FRONTEND_CONVERSATIONS_YARN = $(COMPOSE_RUN) -w /app/src/frontend/apps/conversations node yarn
-FRONTEND_CONVERSATIONS_YARN_3000 = $(COMPOSE_RUN) -p 3000:3000 -w /app/src/frontend/apps/conversations node yarn
 
 # ==============================================================================
 # RULES
@@ -340,19 +337,20 @@ help:
 
 # Front
 frontend-development-install: ## install the frontend locally
-	@$(FRONTEND_CONVERSATIONS_YARN) install
+	cd $(PATH_FRONT_CONVERSATIONS) && yarn
 .PHONY: frontend-development-install
 
 frontend-lint: ## run the frontend linter
-	@$(FRONTEND_YARN) lint
+	cd $(PATH_FRONT) && yarn lint
 .PHONY: frontend-lint
 
 run-frontend-development: ## Run the frontend in development mode
-	@$(FRONTEND_CONVERSATIONS_YARN_3000) dev
+	#@$(COMPOSE) stop frontend frontend-development
+	cd $(PATH_FRONT_CONVERSATIONS) && yarn dev
 .PHONY: run-frontend-development
 
 frontend-i18n-extract: ## Extract the frontend translation inside a json to be used for crowdin
-	@$(FRONTEND_YARN) i18n:extract
+	cd $(PATH_FRONT) && yarn i18n:extract
 .PHONY: frontend-i18n-extract
 
 frontend-i18n-generate: ## Generate the frontend json files used for crowdin
@@ -362,7 +360,7 @@ frontend-i18n-generate: \
 .PHONY: frontend-i18n-generate
 
 frontend-i18n-compile: ## Format the crowin json files used deploy to the apps
-	@$(FRONTEND_YARN) i18n:deploy
+	cd $(PATH_FRONT) && yarn i18n:deploy
 .PHONY: frontend-i18n-compile
 
 # -- K8S
@@ -376,10 +374,10 @@ start-tilt: ## start the kubernetes cluster using kind
 
 bump-packages-version: VERSION_TYPE ?= minor
 bump-packages-version: ## bump the version of the project - VERSION_TYPE can be "major", "minor", "patch"
-	@$(COMPOSE_RUN) -w /app/src/mail node yarn version --no-git-tag-version --$(VERSION_TYPE)
-	@$(COMPOSE_RUN) -w /app/src/frontend node yarn version --no-git-tag-version --$(VERSION_TYPE)
-	@$(COMPOSE_RUN) -w /app/src/frontend/apps/e2e node yarn version --no-git-tag-version --$(VERSION_TYPE)
-	@$(COMPOSE_RUN) -w /app/src/frontend/apps/conversations node yarn version --no-git-tag-version --$(VERSION_TYPE)
-	@$(COMPOSE_RUN) -w /app/src/frontend/packages/eslint-config-conversations node yarn version --no-git-tag-version --$(VERSION_TYPE)
-	@$(COMPOSE_RUN) -w /app/src/frontend/packages/i18n node yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/mail && yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/frontend/ && yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/frontend/apps/e2e/ && yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/frontend/apps/conversations/ && yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/frontend/packages/eslint-config-conversations/ && yarn version --no-git-tag-version --$(VERSION_TYPE)
+	cd ./src/frontend/packages/i18n/ && yarn version --no-git-tag-version --$(VERSION_TYPE)
 .PHONY: bump-packages-version

compose.yml

@@ -16,6 +16,13 @@ services:
   redis:
     image: redis:5
 
+  docling-serve:
+    image: quay.io/docling-project/docling-serve:latest
+    ports:
+      - "5001:5001"
+    environment:
+      - DOCLING_SERVE_ARTIFACTS_PATH=""
+
   maildev:
     image: maildev/maildev:latest
     ports:
@@ -71,6 +78,9 @@ services:
       - "host.docker.internal:host-gateway"
     ports:
       - "8071:8000"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./src/backend:/app
       - ./data/static:/data/static
@@ -84,11 +94,16 @@ services:
           condition: service_started
         createbuckets:
           condition: service_started
+        docling-serve:
+          condition: service_started
 
   nginx:
     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 +192,8 @@ services:
       kc_postgresql:
         condition: service_healthy
         restart: true
+
+networks:
+  lasuite:
+    name: lasuite-network
+    driver: bridge

docs/env.md

@@ -95,7 +95,11 @@ 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                                                      |
+| DOCLING_SERVE_URL                               | URL of Docling Serve                                                                                                              | `http://docling-serve:5001`                             |
+| DOCLING_API_TIMEOUT                             | Docling API timeout                                                                                                               | 60                                                      |
 
 ## 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
 )
 ```
 

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

@@ -0,0 +1,93 @@
+"""Document parsers for RAG backends."""
+
+import logging
+from io import BytesIO
+from urllib.parse import urljoin
+
+from django.conf import settings
+
+import requests
+
+from chat.agent_rag.document_converter.markitdown import DocumentConverter
+
+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 DoclingServeParser(BaseParser):
+    """Document parser using Docling Serve API."""
+
+    def __init__(self):
+        self.endpoint = urljoin(settings.DOCLING_SERVE_URL, "/v1/convert/file")
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse document using Docling Serve API."""
+        timeout = settings.DOCLING_SERVE_TIMEOUT
+        response = requests.post(
+            self.endpoint,
+            files={
+                "files": content,
+            },
+            data={
+                "image_export_mode": "placeholder",
+                "md_page_break_placeholder": "\n\n",
+                "do_picture_description": "true",
+                "document_timeout": timeout,
+            },
+            timeout=timeout,
+        )
+        response.raise_for_status()
+
+        return response.json()["document"]["md_content"]
+
+
+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 DocumentConverter().convert_raw(
+            name=name, content_type=content_type, content=content
+        )

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 DoclingServeParser
 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 = DoclingServeParser()
 
     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 DoclingServeParser
+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 = DoclingServeParser()
+
+    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 DoclingServeParser
 from chat.models import ChatConversation
 
 logger = logging.getLogger(__name__)
@@ -105,32 +105,6 @@ class AlbertRagDocumentSearch:
             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):
         """
@@ -156,16 +130,16 @@ 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.
 
         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.
+            content (bytes): The content of the document as a BytesIO stream.
         """
-        document_content = self.parse_document(name, content_type, content)
+        document_content = DoclingServeParser().parse_document(name, content_type, content)
         self._store_document(name, document_content)
         return document_content
 

src/backend/chat/clients/pydantic_ai.py

@@ -92,6 +92,7 @@ class ContextDeps:
 
     conversation: models.ChatConversation
     user: User
+    session: Optional[Dict] = None
     web_search_enabled: bool = False
 
 
@@ -106,7 +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.
 
@@ -136,6 +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,
         )
 
@@ -278,6 +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
@@ -287,6 +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/"):

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_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."""
@@ -81,10 +103,18 @@ 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"},
@@ -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():
@@ -219,7 +271,7 @@ def fixture_mock_openai_stream():
 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,
@@ -548,7 +600,7 @@ def test_post_conversation_with_document_upload_feature_disabled(
 @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,

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

@@ -37,11 +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
@@ -85,6 +93,10 @@ def test_post_conversation_with_local_pdf_document_url(
         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)
@@ -795,6 +807,10 @@ def test_post_conversation_with_local_not_pdf_document_url(
         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)

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,

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

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 +841,35 @@ 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,
+    )
+
+    # Docling
+    DOCLING_SERVE_URL = values.Value(
+        "http://docling-serve:5001",
+        environ_name="DOCLING_SERVE_URL",
+        environ_prefix = None,
+    )
+    DOCLING_SERVE_TIMEOUT = values.PositiveIntegerValue(
+        default=60,  # seconds
+        environ_name="DOCLING_SERVE_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/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

src/frontend/apps/conversations/src/features/left-panel/components/LeftPanelConversationItem.tsx

@@ -58,7 +58,7 @@ export const LeftPanelConversationItem = ({
     >
       <StyledLink
         href={`/chat/${conversation.id}/`}
-        $css="overflow: auto; flex-grow: 1; color: var(--c--theme--colors--greyscale-900);"
+        $css="overflow: auto; flex-grow: 1;"
         onClick={handleLinkClick}
       >
         <SimpleConversationItem showAccesses conversation={conversation} />