openrag 0.4.1.dev21__tar.gz → 0.5.0.dev1__tar.gz

{openrag-0.4.1.dev21/src/openrag.egg-info → openrag-0.5.0.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.4.1.dev21
+Version: 0.5.0.dev1
 Summary: OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
@@ -17,14 +17,15 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: agentd>=0.8.1
 Requires-Dist: aiofiles>=24.1.0
-Requires-Dist: cryptography>=45.0.6
+Requires-Dist: aiohttp>=3.13.4
+Requires-Dist: cryptography>=46.0.6
 Requires-Dist: google-api-python-client>=2.143.0
 Requires-Dist: google-auth-httplib2>=0.2.0
 Requires-Dist: google-auth-oauthlib>=1.2.0
 Requires-Dist: msal>=1.29.0
 Requires-Dist: httpx>=0.27.0
 Requires-Dist: opensearch-py[async]>=3.0.0
-Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: pyjwt>=2.12.0
 Requires-Dist: python-multipart>=0.0.20
 Requires-Dist: fastapi>=0.115.0
 Requires-Dist: uvicorn>=0.35.0
@@ -37,10 +38,17 @@ Requires-Dist: python-dotenv>=1.0.0
 Requires-Dist: textual-fspicker>=0.6.0
 Requires-Dist: structlog>=25.4.0
 Requires-Dist: zxcvbn>=4.5.0
+Requires-Dist: prometheus-fastapi-instrumentator>=7.1.0
 Requires-Dist: litellm==1.83.3
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: tiktoken>=0.7.0
+Requires-Dist: prometheus-fastapi-instrumentator>=7.1.0
+Requires-Dist: fastmcp>=3.2.3
 Requires-Dist: openai>=2.30.0
+Requires-Dist: tenacity>=9.1.4
+Requires-Dist: pygments>=2.20.0
+Requires-Dist: pyasn1>=0.6.3
+Requires-Dist: requests>=2.33.0
 Dynamic: license-file
 
 <div align="center">

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openrag"
-version = "0.4.1.dev21"
+version = "0.5.0.dev1"
 description = "OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations."
 readme = "README.md"
 requires-python = ">=3.13"
@@ -23,14 +23,15 @@ classifiers = [
 dependencies = [
     "agentd>=0.8.1",
     "aiofiles>=24.1.0",
-    "cryptography>=45.0.6",
+    "aiohttp>=3.13.4",
+    "cryptography>=46.0.6",
     "google-api-python-client>=2.143.0",
     "google-auth-httplib2>=0.2.0",
     "google-auth-oauthlib>=1.2.0",
     "msal>=1.29.0",
     "httpx>=0.27.0",
     "opensearch-py[async]>=3.0.0",
-    "pyjwt>=2.8.0",
+    "pyjwt>=2.12.0",
     "python-multipart>=0.0.20",
     "fastapi>=0.115.0",
     "uvicorn>=0.35.0",
@@ -43,19 +44,27 @@ dependencies = [
     "textual-fspicker>=0.6.0",
     "structlog>=25.4.0",
     "zxcvbn>=4.5.0",
+    "prometheus-fastapi-instrumentator>=7.1.0",
     "litellm==1.83.3",
     "pyyaml>=6.0",
     "tiktoken>=0.7.0",
+    "prometheus-fastapi-instrumentator>=7.1.0",
+    "fastmcp>=3.2.3",
     "openai>=2.30.0",
+    "tenacity>=9.1.4",
+    "pygments>=2.20.0",
+    "pyasn1>=0.6.3",
+    "requests>=2.33.0",
 ]
 
 [dependency-groups]
-dev = ["pytest>=8", "pytest-asyncio>=0.21.0", "pytest-mock>=3.12.0", "pytest-cov>=4.0.0"]
+dev = ["pytest>=9.0.3", "pytest-asyncio>=0.21.0", "pytest-mock>=3.12.0", "pytest-cov>=4.0.0"]
 
 [project.scripts]
 openrag = "tui.main:run_tui"
 
 [tool.uv]
 package = true
+override-dependencies = ["python-dotenv>=1.1.0"]
 
 

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/agent.py

@@ -138,9 +138,6 @@ async def async_response_stream(
         detected_tool_call = False
         async for chunk in response:
             chunk_count += 1
-            logger.debug(
-                "Stream chunk received", chunk_count=chunk_count, chunk=str(chunk)
-            )
 
             import json
 
@@ -258,10 +255,7 @@ async def async_response_stream(
         logger.info("Response generated", log_prefix=log_prefix, response=full_response)
 
     except Exception as e:
-        logger.error("Exception in streaming", error=str(e))
-        import traceback
-
-        traceback.print_exc()
+        logger.exception("[AGENT] Streaming failed")
         raise
 
 
@@ -316,10 +310,7 @@ async def async_response(
                     msg = error_msg
             raise ValueError(msg)
     except Exception as e:
-        logger.error("Exception in non-streaming response", error=str(e))
-        import traceback
-
-        traceback.print_exc()
+        logger.exception("[AGENT] Non-streaming response failed")
         raise
 
 
@@ -387,10 +378,7 @@ async def async_langflow_stream(
             yield chunk
         logger.debug("Langflow stream completed")
     except Exception as e:
-        logger.error("Exception in langflow stream", error=str(e))
-        import traceback
-
-        traceback.print_exc()
+        logger.exception("[AGENT] Langflow stream failed")
         raise
 
 

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/auth.py

@@ -1,8 +1,12 @@
 from typing import Optional
 
-from fastapi import Depends, Request
+from fastapi import Depends, HTTPException, Request
 from fastapi.responses import JSONResponse
 from utils.telemetry import TelemetryClient, Category, MessageId
+from utils.version_utils import OPENRAG_VERSION
+from utils.logging_config import get_logger
+
+logger = get_logger(__name__)
 
 from dependencies import (
     get_auth_service,
@@ -20,6 +24,8 @@ class AuthInitBody(BaseModel):
     redirect_uri: Optional[str] = None
 
 
+
+
 class AuthCallbackBody(BaseModel):
     connection_id: str
     authorization_code: str
@@ -47,9 +53,7 @@ async def auth_init(
         return JSONResponse(result)
 
     except Exception as e:
-        import traceback
-
-        traceback.print_exc()
+        logger.exception("[AUTH] OAuth init failed")
         return JSONResponse(
             {"error": f"Failed to initialize OAuth: {str(e)}"}, status_code=500
         )
@@ -74,9 +78,14 @@ async def auth_callback(
             response = JSONResponse(
                 {k: v for k, v in result.items() if k != "jwt_token"}
             )
+            # Store only the raw JWT (without "Bearer " prefix) in the cookie.
+            # The prefix is added by the OpenSearch client when building the Authorization header.
+            jwt_value = result["jwt_token"]
+            if jwt_value.startswith("Bearer "):
+                jwt_value = jwt_value[len("Bearer "):]
             response.set_cookie(
                 key="auth_token",
-                value=result["jwt_token"],
+                value=jwt_value,
                 httponly=True,
                 secure=False,
                 samesite="lax",
@@ -87,9 +96,7 @@ async def auth_callback(
             return JSONResponse(result)
 
     except Exception as e:
-        import traceback
-
-        traceback.print_exc()
+        logger.exception("[AUTH] OAuth callback failed")
         await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_OAUTH_FAILED)
         return JSONResponse({"error": f"Callback failed: {str(e)}"}, status_code=500)
 
@@ -101,6 +108,7 @@ async def auth_me(
 ):
     """Get current user information"""
     result = await auth_service.get_user_info(request)
+    result["version"] = OPENRAG_VERSION
     return JSONResponse(result)
 
 
@@ -108,8 +116,28 @@ async def auth_logout(
     auth_service=Depends(get_auth_service),
     user: User = Depends(get_current_user),
 ):
-    """Logout user by clearing auth cookie"""
+    """Logout user by clearing auth cookie(s)"""
+    from config.settings import IBM_AUTH_ENABLED, IBM_SESSION_COOKIE_NAME
+
     await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_LOGOUT)
+
+    if IBM_AUTH_ENABLED:
+        # Best-effort: clear cookies from the browser, but warn that the
+        # server-side AMS session is NOT terminated. The IBM session cookie
+        # is owned by Traefik/AMS — it may be re-injected on the next
+        # proxied request if AMS still considers the session active.
+        response = JSONResponse(
+            {
+                "status": "partial_logout",
+                "message": "Browser cookies cleared, but the IBM session is "
+                "managed by the identity provider and may still be active. "
+                "Please log out through IBM Watsonx Data for full session termination.",
+            }
+        )
+        response.delete_cookie(key=IBM_SESSION_COOKIE_NAME, httponly=True, samesite="lax")
+        response.delete_cookie(key="ibm-auth-basic", httponly=True, samesite="lax")
+        return response
+
     response = JSONResponse(
         {"status": "logged_out", "message": "Successfully logged out"}
     )
@@ -120,3 +148,35 @@ async def auth_logout(
     )
 
     return response
+
+
+async def ibm_login(request: Request):
+    """IBM login endpoint.
+
+    Production: Traefik intercepts the request, validates Basic credentials
+    with AMS, and sets the ibm-openrag-session cookie before forwarding here.
+    This handler just returns 200 — no cookie work needed.
+
+    Local dev (no Traefik): stores the Basic Auth header in ibm-auth-basic
+    cookie so subsequent requests can be authenticated by _get_ibm_user.
+    """
+    from config.settings import IBM_AUTH_ENABLED, IBM_SESSION_COOKIE_NAME
+
+    if not IBM_AUTH_ENABLED:
+        raise HTTPException(status_code=404, detail="IBM auth is not enabled")
+
+    response = JSONResponse({"status": "ok"})
+
+    # Local dev fallback only — in production Traefik sets the session cookie.
+    if not request.cookies.get(IBM_SESSION_COOKIE_NAME):
+        auth_header = request.headers.get("Authorization", "")
+        if auth_header.startswith("Basic "):
+            # secure =True not needed for local development
+            response.set_cookie(
+                "ibm-auth-basic",
+                auth_header,
+                httponly=True,
+                samesite="lax",
+            )
+
+    return response

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/chat.py

@@ -101,6 +101,9 @@ async def langflow_endpoint(
                     previous_response_id=body.previous_response_id,
                     stream=True,
                     filter_id=body.filter_id,
+                    owner=user.user_id,
+                    owner_name=user.name,
+                    owner_email=user.email,
                 ),
                 media_type="text/event-stream",
                 headers={
@@ -118,13 +121,14 @@ async def langflow_endpoint(
                 previous_response_id=body.previous_response_id,
                 stream=False,
                 filter_id=body.filter_id,
+                owner=user.user_id,
+                owner_name=user.name,
+                owner_email=user.email,
             )
             return JSONResponse(result)
 
     except Exception as e:
-        import traceback
-        traceback.print_exc()
-        logger.error("Langflow request failed", error=str(e))
+        logger.exception("[CHAT] Langflow request failed")
         return JSONResponse(
             {"error": f"Langflow request failed: {str(e)}"}, status_code=500
         )
@@ -139,6 +143,7 @@ async def chat_history_endpoint(
         history = await chat_service.get_chat_history(user.user_id)
         return JSONResponse(history)
     except Exception as e:
+        logger.exception("[CHAT] Failed to get chat history")
         return JSONResponse(
             {"error": f"Failed to get chat history: {str(e)}"}, status_code=500
         )
@@ -153,6 +158,7 @@ async def langflow_history_endpoint(
         history = await chat_service.get_langflow_history(user.user_id)
         return JSONResponse(history)
     except Exception as e:
+        logger.exception("[CHAT] Failed to get langflow history")
         return JSONResponse(
             {"error": f"Failed to get langflow history: {str(e)}"}, status_code=500
         )

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/connector_router.py

@@ -50,11 +50,22 @@ class ConnectorRouter:
         return await self.get_active_service().get_connector(connection_id)
 
     async def sync_specific_files(
-        self, connection_id: str, user_id: str, file_list: list, jwt_token: str = None, file_infos: list = None
+        self,
+        connection_id: str,
+        user_id: str,
+        file_list: list,
+        jwt_token: str = None,
+        file_infos: list = None,
+        ingest_settings: dict = None,
     ):
         """Sync specific files using the active service."""
         return await self.get_active_service().sync_specific_files(
-            connection_id, user_id, file_list, jwt_token, file_infos=file_infos
+            connection_id,
+            user_id,
+            file_list,
+            jwt_token,
+            file_infos=file_infos,
+            ingest_settings=ingest_settings,
         )
 
     def __getattr__(self, name):

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/connectors.py

@@ -1,4 +1,4 @@
-from typing import Any, List, Optional
+from typing import Any, Dict, List, Optional
 
 from fastapi import Depends, Request
 from pydantic import BaseModel
@@ -93,6 +93,8 @@ class ConnectorSyncBody(BaseModel):
     sync_all: bool = False
     # When set, only ingest files from these buckets (IBM COS specific).
     bucket_filter: Optional[List[str]] = None
+    # Per-request ingest options from the connector upload UI (overrides saved Knowledge for this sync).
+    settings: Optional[Dict[str, Any]] = None
 
 
 async def list_connectors(
@@ -106,7 +108,7 @@ async def list_connectors(
         )
         return JSONResponse({"connectors": connector_types})
     except Exception as e:
-        logger.info("Error listing connectors", error=str(e))
+        logger.error("[CONNECTOR] Error listing connectors", error=str(e))
         return JSONResponse({"connectors": []})
 
 
@@ -197,13 +199,14 @@ async def connector_sync(
         if selected_files:
             # Explicit files selected (e.g., from file picker) - sync those specific files
             from .documents import _ensure_index_exists
-            await _ensure_index_exists()
+            await _ensure_index_exists(jwt_token)
             task_id = await connector_service.sync_specific_files(
                 working_connection.connection_id,
                 user.user_id,
                 selected_files,
                 jwt_token=jwt_token,
                 file_infos=file_infos,
+                ingest_settings=body.settings,
             )
         elif body.sync_all or body.bucket_filter:
             # Full ingest: discover and ingest all files (or files from specific buckets).
@@ -241,6 +244,7 @@ async def connector_sync(
                     user.user_id,
                     all_file_ids,
                     jwt_token=jwt_token,
+                    ingest_settings=body.settings,
                 )
             else:
                 # sync_all: ingest everything the connector can see
@@ -549,15 +553,10 @@ async def connector_webhook(
             )
 
         except Exception as e:
-            logger.error(
-                "Failed to process webhook for connection",
+            logger.exception(
+                "[CONNECTOR] Failed to process webhook",
                 connection_id=connection.connection_id,
-                error=str(e),
             )
-            import traceback
-
-            traceback.print_exc()
-
             return JSONResponse(
                 {
                     "status": "error",

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/documents.py

@@ -99,10 +99,16 @@ async def delete_documents_by_filename_core(
         )
 
 
-async def _ensure_index_exists():
+async def _ensure_index_exists(jwt_token: str = None):
     """Create the OpenSearch index if it doesn't exist yet."""
     from main import init_index
-    await init_index()
+    from config.settings import IBM_AUTH_ENABLED, clients as app_clients
+
+    opensearch_client = None
+    if IBM_AUTH_ENABLED and jwt_token:
+        opensearch_client = app_clients.create_user_opensearch_client(jwt_token)
+
+    await init_index(opensearch_client)
 
 
 async def check_filename_exists(
@@ -144,7 +150,7 @@ async def check_filename_exists(
         except Exception as search_err:
             if "index_not_found_exception" in str(search_err):
                 logger.info("Index does not exist, creating it now before upload")
-                await _ensure_index_exists()
+                await _ensure_index_exists(jwt_token)
                 return JSONResponse({"exists": False, "filename": filename}, status_code=200)
             raise
 

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/keys.py

@@ -28,7 +28,7 @@ async def list_keys_endpoint(
 
     GET /keys
     """
-    result = await api_key_service.list_keys(user.user_id, None)
+    result = await api_key_service.list_keys(user.user_id, user.jwt_token)
     return JSONResponse(result)
 
 

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/knowledge_filter.py

@@ -418,12 +418,9 @@ async def knowledge_filter_webhook(
         )
 
     except Exception as e:
-        logger.error(
-            "Failed to process knowledge filter webhook",
+        logger.exception(
+            "[API] Knowledge filter webhook failed",
             filter_id=filter_id,
             subscription_id=subscription_id,
-            error=str(e),
         )
-        import traceback
-        traceback.print_exc()
         return JSONResponse({"error": f"Webhook processing failed: {str(e)}"}, status_code=500)

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/provider_validation.py

@@ -316,7 +316,7 @@ async def _test_openai_completion_with_tools(api_key: str, llm_model: str) -> No
 
             # If max_tokens doesn't work, try with max_completion_tokens
             if response.status_code != 200:
-                logger.info("max_tokens parameter failed, trying max_completion_tokens instead")
+                logger.warning("[API] max_tokens parameter failed, trying max_completion_tokens instead")
                 payload = {**base_payload, "max_completion_tokens": 50}
                 response = await client.post(
                     "https://api.openai.com/v1/chat/completions",
@@ -454,7 +454,7 @@ async def _test_watsonx_completion_with_tools(
 
         # Test completion with tools
         url = f"{endpoint}/ml/v1/text/chat"
-        params = {"version": "2024-09-16"}
+        params = {"version": "2026-04-15"}
         payload = {
             "model_id": llm_model,
             "project_id": project_id,
@@ -549,7 +549,7 @@ async def _test_watsonx_embedding(
 
         # Test embedding
         url = f"{endpoint}/ml/v1/text/embeddings"
-        params = {"version": "2024-09-16"}
+        params = {"version": "2026-04-15"}
         payload = {
             "model_id": embedding_model,
             "project_id": project_id,

{openrag-0.4.1.dev21 → openrag-0.5.0.dev1}/src/api/search.py

@@ -33,7 +33,6 @@ async def search(
 
         logger.debug(
             "Search API request",
-            user=str(user),
             user_id=user.user_id,
             has_jwt_token=jwt_token is not None,
             query=body.query,