OpenRAG 0.1.31__tar.gz → 0.2.0__tar.gz

{openrag-0.1.31/src/openrag.egg-info → openrag-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.1.31
+Version: 0.2.0
 Summary: Add your description here
 Requires-Python: >=3.13
 Description-Content-Type: text/markdown
@@ -30,7 +30,8 @@ Requires-Dist: textual-fspicker>=0.6.0
 Requires-Dist: structlog>=25.4.0
 Requires-Dist: docling-serve==1.5.0
 Requires-Dist: docling-core==2.48.1
-Requires-Dist: easyocr>=1.7.1
+Requires-Dist: easyocr>=1.7.1; sys_platform != "darwin"
+Requires-Dist: zxcvbn>=4.5.0
 Dynamic: license-file
 
 <div align="center">
@@ -53,27 +54,29 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
 </div>
 <div align="center">
   <a href="#quickstart" style="color: #0366d6;">Quickstart</a> &nbsp;&nbsp;|&nbsp;&nbsp;
-  <a href="#tui-interface" style="color: #0366d6;">TUI Interface</a> &nbsp;&nbsp;|&nbsp;&nbsp;
-  <a href="#docker-deployment" style="color: #0366d6;">Docker Deployment</a> &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="#install-python-package" style="color: #0366d6;">Python package</a> &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="#docker-or-podman-installation" style="color: #0366d6;">Docker or Podman</a> &nbsp;&nbsp;|&nbsp;&nbsp;
   <a href="#development" style="color: #0366d6;">Development</a> &nbsp;&nbsp;|&nbsp;&nbsp;
   <a href="#troubleshooting" style="color: #0366d6;">Troubleshooting</a>
 </div>
 
 ## Quickstart
 
-To quickly run OpenRAG without creating or modifying any project files, use `uvx`:
+To run OpenRAG without creating or modifying any project files, use `uvx`:
 
 ```bash
 uvx openrag
 ```
-This runs OpenRAG without installing it to your project or globally.
-To run a specific version of OpenRAG, add the version to the command, such as: `uvx --from openrag==0.1.25 openrag`.
+
+This command runs OpenRAG without installing it to your project or globally.
+
+To run a specific version of OpenRAG, run `uvx --from openrag==VERSION openrag`.
 
 ## Install Python package
 
-To first set up a project and then install the OpenRAG Python package, do the following:
+To add the OpenRAG Python package to a Python project, use `uv`:
 
-1. Create a new project with a virtual environment using `uv init`.
+1. Create a new project with a virtual environment using `uv init`:
 
    ```bash
    uv init YOUR_PROJECT_NAME
@@ -83,33 +86,33 @@ To first set up a project and then install the OpenRAG Python package, do the fo
    The `(venv)` prompt doesn't change, but `uv` commands will automatically use the project's virtual environment.
    For more information on virtual environments, see the [uv documentation](https://docs.astral.sh/uv/pip/environments).
 
-2. Add OpenRAG to your project.
+2. Add OpenRAG to your project:
+
    ```bash
    uv add openrag
    ```
 
-   To add a specific version of OpenRAG:
-   ```bash
-   uv add openrag==0.1.25
-   ```
+   To add a specific version of OpenRAG, run `uv add openrag==VERSION`.
+
+3. Start the OpenRAG terminal user interface (TUI):
 
-3. Start the OpenRAG TUI.
    ```bash
    uv run openrag
    ```
 
 4. Continue with the [Quickstart](https://docs.openr.ag/quickstart).
 
-For the full TUI installation guide, see [TUI](https://docs.openr.ag/install).
+For all installation options, see the [OpenRAG installation guide](https://docs.openr.ag/install).
 
 ## Docker or Podman installation
 
-For more information, see [Install OpenRAG containers](https://docs.openr.ag/get-started/docker).
-
-## Troubleshooting
-
-For common issues and fixes, see [Troubleshoot](https://docs.openr.ag/support/troubleshoot).
+By default, OpenRAG automatically starts the required containers and helps you manage them.
+To install OpenRAG with self-managed containers, see the [OpenRAG installation guide](https://docs.openr.ag/docker).
 
 ## Development
 
 For developers wanting to contribute to OpenRAG or set up a development environment, see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+## Troubleshooting
+
+For common issues and fixes, see [Troubleshoot OpenRAG](https://docs.openr.ag/support/troubleshoot).

{openrag-0.1.31 → openrag-0.2.0}/README.md

@@ -18,27 +18,29 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
 </div>
 <div align="center">
   <a href="#quickstart" style="color: #0366d6;">Quickstart</a> &nbsp;&nbsp;|&nbsp;&nbsp;
-  <a href="#tui-interface" style="color: #0366d6;">TUI Interface</a> &nbsp;&nbsp;|&nbsp;&nbsp;
-  <a href="#docker-deployment" style="color: #0366d6;">Docker Deployment</a> &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="#install-python-package" style="color: #0366d6;">Python package</a> &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="#docker-or-podman-installation" style="color: #0366d6;">Docker or Podman</a> &nbsp;&nbsp;|&nbsp;&nbsp;
   <a href="#development" style="color: #0366d6;">Development</a> &nbsp;&nbsp;|&nbsp;&nbsp;
   <a href="#troubleshooting" style="color: #0366d6;">Troubleshooting</a>
 </div>
 
 ## Quickstart
 
-To quickly run OpenRAG without creating or modifying any project files, use `uvx`:
+To run OpenRAG without creating or modifying any project files, use `uvx`:
 
 ```bash
 uvx openrag
 ```
-This runs OpenRAG without installing it to your project or globally.
-To run a specific version of OpenRAG, add the version to the command, such as: `uvx --from openrag==0.1.25 openrag`.
+
+This command runs OpenRAG without installing it to your project or globally.
+
+To run a specific version of OpenRAG, run `uvx --from openrag==VERSION openrag`.
 
 ## Install Python package
 
-To first set up a project and then install the OpenRAG Python package, do the following:
+To add the OpenRAG Python package to a Python project, use `uv`:
 
-1. Create a new project with a virtual environment using `uv init`.
+1. Create a new project with a virtual environment using `uv init`:
 
    ```bash
    uv init YOUR_PROJECT_NAME
@@ -48,33 +50,33 @@ To first set up a project and then install the OpenRAG Python package, do the fo
    The `(venv)` prompt doesn't change, but `uv` commands will automatically use the project's virtual environment.
    For more information on virtual environments, see the [uv documentation](https://docs.astral.sh/uv/pip/environments).
 
-2. Add OpenRAG to your project.
+2. Add OpenRAG to your project:
+
    ```bash
    uv add openrag
    ```
 
-   To add a specific version of OpenRAG:
-   ```bash
-   uv add openrag==0.1.25
-   ```
+   To add a specific version of OpenRAG, run `uv add openrag==VERSION`.
+
+3. Start the OpenRAG terminal user interface (TUI):
 
-3. Start the OpenRAG TUI.
    ```bash
    uv run openrag
    ```
 
 4. Continue with the [Quickstart](https://docs.openr.ag/quickstart).
 
-For the full TUI installation guide, see [TUI](https://docs.openr.ag/install).
+For all installation options, see the [OpenRAG installation guide](https://docs.openr.ag/install).
 
 ## Docker or Podman installation
 
-For more information, see [Install OpenRAG containers](https://docs.openr.ag/get-started/docker).
+By default, OpenRAG automatically starts the required containers and helps you manage them.
+To install OpenRAG with self-managed containers, see the [OpenRAG installation guide](https://docs.openr.ag/docker).
 
-## Troubleshooting
+## Development
 
-For common issues and fixes, see [Troubleshoot](https://docs.openr.ag/support/troubleshoot).
+For developers wanting to contribute to OpenRAG or set up a development environment, see [CONTRIBUTING.md](CONTRIBUTING.md).
 
-## Development
+## Troubleshooting
 
-For developers wanting to contribute to OpenRAG or set up a development environment, see [CONTRIBUTING.md](CONTRIBUTING.md).
+For common issues and fixes, see [Troubleshoot OpenRAG](https://docs.openr.ag/support/troubleshoot).

{openrag-0.1.31 → openrag-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openrag"
-version = "0.1.31"
+version = "0.2.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
@@ -34,7 +34,8 @@ dependencies = [
     "structlog>=25.4.0",
     "docling-serve==1.5.0",
     "docling-core==2.48.1",
-    "easyocr>=1.7.1"
+    "easyocr>=1.7.1; sys_platform != 'darwin'",
+    "zxcvbn>=4.5.0"
 ]
 
 [dependency-groups]

{openrag-0.1.31 → openrag-0.2.0}/src/agent.py

@@ -1,3 +1,5 @@
+from http.client import HTTPException
+
 from utils.logging_config import get_logger
 
 logger = get_logger(__name__)
@@ -34,7 +36,7 @@ def get_conversation_thread(user_id: str, previous_response_id: str = None):
         "messages": [
             {
                 "role": "system",
-                "content": "You are a helpful assistant that can use tools to answer questions and perform tasks. You are part of OpenRAG, an assistant that analyzes documents and provides informations about them. When asked about what is OpenRAG, answer the following:\n\n\"OpenRAG is an open-source package for building agentic RAG systems. It supports integration with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:\n\n**Langflow** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.langflow.org/)\n\n**OpenSearch** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://opensearch.org/)\n\n**Docling** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.docling.ai/)\"",
+                "content": "You are the OpenRAG Agent. You answer questions using retrieval, reasoning, and tool use.\nYou have access to several tools. Your job is to determine **which tool to use and when**.\n### Available Tools\n- OpenSearch Retrieval Tool:\n  Use this to search the indexed knowledge base. Use when the user asks about product details, internal concepts, processes, architecture, documentation, roadmaps, or anything that may be stored in the index.\n- Conversation History:\n  Use this to maintain continuity when the user is referring to previous turns. \n  Do not treat history as a factual source.\n- Conversation File Context:\n  Use this when the user asks about a document they uploaded or refers directly to its contents.\n  **IMPORTANT**: If you receive confirmation that a file was uploaded (e.g., \"Confirm that you received this file\"), the file content is already available in the conversation context. Do NOT attempt to ingest it as a URL.\n  Simply acknowledge the file and answer questions about it directly from the context.\n- URL Ingestion Tool:\n  Use this **only** when the user explicitly asks you to read, summarize, or analyze the content of a web URL (http:// or https://).\n  **Do NOT use this tool for filenames** (e.g., README.md, document.pdf, data.txt). These are file uploads, not URLs.\n  Only use this tool for actual web addresses that the user explicitly provides.\n  If unclear → ask a clarifying question.\n- Calculator / Expression Evaluation Tool:\n  Use this when the user asks to compare numbers, compute estimates, calculate totals, analyze pricing, or answer any question requiring mathematics or quantitative reasoning.\n  If the answer requires arithmetic, call the calculator tool rather than calculating internally.\n### Retrieval Decision Rules\nUse OpenSearch **whenever**:\n1. The question may be answered from internal or indexed data.\n2. The user references team names, product names, release plans, configurations, requirements, or official information.\n3. The user needs a factual, grounded answer.\nDo **not** use retrieval if:\n- The question is purely creative (e.g., storytelling, analogies) or personal preference.\n- The user simply wants text reformatted or rewritten from what is already present in the conversation.\nWhen uncertain → **Retrieve.** Retrieval is low risk and improves grounding.\n### File Upload vs URL Distinction\n**File uploads** (already in context):\n- Filenames like: README.md, document.pdf, notes.txt, data.csv\n- When you see file confirmation messages\n- Use conversation context directly - do NOT call URL tool\n**Web URLs** (need ingestion):\n- Start with http:// or https://\n- Examples: https://example.com, http://docs.site.org\n- User explicitly asks to fetch from web\n### Calculator Usage Rules\nUse the calculator when:\n- Performing arithmetic\n- Estimating totals\n- Comparing values\n- Modeling cost, time, effort, scale, or projections\nDo not perform math internally. **Call the calculator tool instead.**\n### Answer Construction Rules\n1. When asked: \"What is OpenRAG\", answer the following:\n\"OpenRAG is an open-source package for building agentic RAG systems. It supports integration with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:\n**Langflow** – Langflow is a powerful tool to build and deploy AI agents and MCP servers. [Read more](https://www.langflow.org/)\n**OpenSearch** – OpenSearch is an open source, search and observability suite that brings order to unstructured data at scale. [Read more](https://opensearch.org/)\n**Docling** – Docling simplifies document processing with advanced PDF understanding, OCR support, and seamless AI integrations. Parse PDFs, DOCX, PPTX, images & more. [Read more](https://www.docling.ai/)\"\n2. Synthesize retrieved or ingested content in your own words.\n3. Support factual claims with citations in the format:\n   (Source: <document_name_or_id>)\n4. If no supporting evidence is found:\n   Say: \"No relevant supporting sources were found for that request.\"\n5. Never invent facts or hallucinate details.\n6. Be concise, direct, and confident. \n7. Do not reveal internal chain-of-thought.",
             }
         ],
         "previous_response_id": previous_response_id,  # Parent response_id for branching
@@ -45,8 +47,8 @@ def get_conversation_thread(user_id: str, previous_response_id: str = None):
     return new_conversation
 
 
-def store_conversation_thread(user_id: str, response_id: str, conversation_state: dict):
-    """Store conversation both in memory (with function calls) and persist metadata to disk"""
+async def store_conversation_thread(user_id: str, response_id: str, conversation_state: dict):
+    """Store conversation both in memory (with function calls) and persist metadata to disk (async, non-blocking)"""
     # 1. Store full conversation in memory for function call preservation
     if user_id not in active_conversations:
         active_conversations[user_id] = {}
@@ -67,13 +69,14 @@ def store_conversation_thread(user_id: str, response_id: str, conversation_state
         "created_at": conversation_state.get("created_at"),
         "last_activity": conversation_state.get("last_activity"),
         "previous_response_id": conversation_state.get("previous_response_id"),
+        "filter_id": conversation_state.get("filter_id"),
         "total_messages": len(
             [msg for msg in messages if msg.get("role") in ["user", "assistant"]]
         ),
         # Don't store actual messages - Langflow has them
     }
 
-    conversation_persistence.store_conversation_thread(
+    await conversation_persistence.store_conversation_thread(
         user_id, response_id, metadata_only
     )
 
@@ -132,6 +135,7 @@ async def async_response_stream(
 
         full_response = ""
         chunk_count = 0
+        detected_tool_call = False  # Track if we've detected a tool call
         async for chunk in response:
             chunk_count += 1
             logger.debug(
@@ -155,6 +159,17 @@ async def async_response_stream(
                 else:
                     delta_text = str(chunk.delta)
                 full_response += delta_text
+            
+            # Enhanced logging for tool call detection (Granite 3.3 8b investigation)
+            chunk_attrs = dir(chunk) if hasattr(chunk, '__dict__') else []
+            tool_related_attrs = [attr for attr in chunk_attrs if 'tool' in attr.lower() or 'call' in attr.lower() or 'retrieval' in attr.lower()]
+            if tool_related_attrs:
+                logger.info(
+                    "Tool-related attributes found in chunk",
+                    chunk_count=chunk_count,
+                    attributes=tool_related_attrs,
+                    chunk_type=type(chunk).__name__
+                )
 
             # Send the raw event as JSON followed by newline for easy parsing
             try:
@@ -166,7 +181,57 @@ async def async_response_stream(
                     chunk_data = chunk.__dict__
                 else:
                     chunk_data = str(chunk)
-
+                
+                # Log detailed chunk structure for investigation (especially for Granite 3.3 8b)
+                if isinstance(chunk_data, dict):
+                    # Check for any fields that might indicate tool usage
+                    potential_tool_fields = {
+                        k: v for k, v in chunk_data.items() 
+                        if any(keyword in str(k).lower() for keyword in ['tool', 'call', 'retrieval', 'function', 'result', 'output'])
+                    }
+                    if potential_tool_fields:
+                        logger.info(
+                            "Potential tool-related fields in chunk",
+                            chunk_count=chunk_count,
+                            fields=list(potential_tool_fields.keys()),
+                            sample_data=str(potential_tool_fields)[:500]
+                        )
+
+                # Middleware: Detect implicit tool calls and inject standardized events
+                # This helps Granite 3.3 8b and other models that don't emit standard markers
+                if isinstance(chunk_data, dict) and not detected_tool_call:
+                    # Check if this chunk contains retrieval results
+                    has_results = any([
+                        'results' in chunk_data and isinstance(chunk_data.get('results'), list),
+                        'outputs' in chunk_data and isinstance(chunk_data.get('outputs'), list),
+                        'retrieved_documents' in chunk_data,
+                        'retrieval_results' in chunk_data,
+                    ])
+                    
+                    if has_results:
+                        logger.info(
+                            "Detected implicit tool call in backend, injecting synthetic event",
+                            chunk_fields=list(chunk_data.keys())
+                        )
+                        # Inject a synthetic tool call event before this chunk
+                        synthetic_event = {
+                            "type": "response.output_item.done",
+                            "item": {
+                                "type": "retrieval_call",
+                                "id": f"synthetic_{chunk_count}",
+                                "name": "Retrieval",
+                                "tool_name": "Retrieval",
+                                "status": "completed",
+                                "inputs": {"implicit": True, "backend_detected": True},
+                                "results": chunk_data.get('results') or chunk_data.get('outputs') or 
+                                         chunk_data.get('retrieved_documents') or 
+                                         chunk_data.get('retrieval_results') or []
+                            }
+                        }
+                        # Send the synthetic event first
+                        yield (json.dumps(synthetic_event, default=str) + "\n").encode("utf-8")
+                        detected_tool_call = True  # Mark that we've injected a tool call
+                
                 yield (json.dumps(chunk_data, default=str) + "\n").encode("utf-8")
             except Exception as e:
                 # Fallback to string representation
@@ -219,15 +284,26 @@ async def async_response(
 
         response = await client.responses.create(**request_params)
 
-        response_text = response.output_text
-        logger.info("Response generated", log_prefix=log_prefix, response=response_text)
+        # Check if response has output_text using getattr to avoid issues with special objects
+        output_text = getattr(response, "output_text", None)
+        if output_text is not None:
+            response_text = output_text
+            logger.info("Response generated", log_prefix=log_prefix, response=response_text)
 
-        # Extract and store response_id if available
-        response_id = getattr(response, "id", None) or getattr(
-            response, "response_id", None
-        )
+            # Extract and store response_id if available
+            response_id = getattr(response, "id", None) or getattr(
+                response, "response_id", None
+            )
 
-        return response_text, response_id, response
+            return response_text, response_id, response
+        else:
+            msg = "Nudge response missing output_text"
+            error = getattr(response, "error", None)
+            if error:
+                error_msg = getattr(error, "message", None)
+                if error_msg:
+                    msg = error_msg
+            raise ValueError(msg)
     except Exception as e:
         logger.error("Exception in non-streaming response", error=str(e))
         import traceback
@@ -314,6 +390,7 @@ async def async_chat(
     user_id: str,
     model: str = "gpt-4.1-mini",
     previous_response_id: str = None,
+    filter_id: str = None,
 ):
     logger.debug(
         "async_chat called", user_id=user_id, previous_response_id=previous_response_id
@@ -334,6 +411,10 @@ async def async_chat(
         "Added user message", message_count=len(conversation_state["messages"])
     )
 
+    # Store filter_id in conversation state if provided
+    if filter_id:
+        conversation_state["filter_id"] = filter_id
+
     response_text, response_id, response_obj = await async_response(
         async_client,
         prompt,
@@ -363,7 +444,7 @@ async def async_chat(
     # Store the conversation thread with its response_id
     if response_id:
         conversation_state["last_activity"] = datetime.now()
-        store_conversation_thread(user_id, response_id, conversation_state)
+        await store_conversation_thread(user_id, response_id, conversation_state)
         logger.debug(
             "Stored conversation thread", user_id=user_id, response_id=response_id
         )
@@ -389,6 +470,7 @@ async def async_chat_stream(
     user_id: str,
     model: str = "gpt-4.1-mini",
     previous_response_id: str = None,
+    filter_id: str = None,
 ):
     # Get the specific conversation thread (or create new one)
     conversation_state = get_conversation_thread(user_id, previous_response_id)
@@ -399,6 +481,10 @@ async def async_chat_stream(
     user_message = {"role": "user", "content": prompt, "timestamp": datetime.now()}
     conversation_state["messages"].append(user_message)
 
+    # Store filter_id in conversation state if provided
+    if filter_id:
+        conversation_state["filter_id"] = filter_id
+
     full_response = ""
     response_id = None
     async for chunk in async_stream(
@@ -437,7 +523,7 @@ async def async_chat_stream(
         # Store the conversation thread with its response_id
         if response_id:
             conversation_state["last_activity"] = datetime.now()
-            store_conversation_thread(user_id, response_id, conversation_state)
+            await store_conversation_thread(user_id, response_id, conversation_state)
             logger.debug(
                 f"Stored conversation thread for user {user_id} with response_id: {response_id}"
             )
@@ -452,6 +538,7 @@ async def async_langflow_chat(
     extra_headers: dict = None,
     previous_response_id: str = None,
     store_conversation: bool = True,
+    filter_id: str = None,
 ):
     logger.debug(
         "async_langflow_chat called",
@@ -478,6 +565,10 @@ async def async_langflow_chat(
             message_count=len(conversation_state["messages"]),
         )
 
+        # Store filter_id in conversation state if provided
+        if filter_id:
+            conversation_state["filter_id"] = filter_id
+
     response_text, response_id, response_obj = await async_response(
         langflow_client,
         prompt,
@@ -520,7 +611,7 @@ async def async_langflow_chat(
     # Store the conversation thread with its response_id
     if response_id:
         conversation_state["last_activity"] = datetime.now()
-        store_conversation_thread(user_id, response_id, conversation_state)
+        await store_conversation_thread(user_id, response_id, conversation_state)
 
         # Claim session ownership for this user
         try:
@@ -562,6 +653,7 @@ async def async_langflow_chat_stream(
     user_id: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
+    filter_id: str = None,
 ):
     logger.debug(
         "async_langflow_chat_stream called",
@@ -578,6 +670,10 @@ async def async_langflow_chat_stream(
     user_message = {"role": "user", "content": prompt, "timestamp": datetime.now()}
     conversation_state["messages"].append(user_message)
 
+    # Store filter_id in conversation state if provided
+    if filter_id:
+        conversation_state["filter_id"] = filter_id
+
     full_response = ""
     response_id = None
     collected_chunks = []  # Store all chunks for function call data
@@ -622,7 +718,7 @@ async def async_langflow_chat_stream(
         # Store the conversation thread with its response_id
         if response_id:
             conversation_state["last_activity"] = datetime.now()
-            store_conversation_thread(user_id, response_id, conversation_state)
+            await store_conversation_thread(user_id, response_id, conversation_state)
 
             # Claim session ownership for this user
         try:
@@ -638,8 +734,8 @@ async def async_langflow_chat_stream(
             )
 
 
-def delete_user_conversation(user_id: str, response_id: str) -> bool:
-    """Delete a conversation for a user from both memory and persistent storage"""
+async def delete_user_conversation(user_id: str, response_id: str) -> bool:
+    """Delete a conversation for a user from both memory and persistent storage (async, non-blocking)"""
     deleted = False
 
     try:
@@ -650,7 +746,7 @@ def delete_user_conversation(user_id: str, response_id: str) -> bool:
             deleted = True
 
         # Delete from persistent storage
-        conversation_deleted = conversation_persistence.delete_conversation_thread(user_id, response_id)
+        conversation_deleted = await conversation_persistence.delete_conversation_thread(user_id, response_id)
         if conversation_deleted:
             logger.debug(f"Deleted conversation {response_id} from persistent storage for user {user_id}")
             deleted = True

{openrag-0.1.31 → openrag-0.2.0}/src/api/auth.py

@@ -1,5 +1,6 @@
 from starlette.requests import Request
 from starlette.responses import JSONResponse
+from utils.telemetry import TelemetryClient, Category, MessageId
 
 
 async def auth_init(request: Request, auth_service, session_manager):
@@ -40,8 +41,11 @@ async def auth_callback(request: Request, auth_service, session_manager):
             connection_id, authorization_code, state, request
         )
 
+        await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_OAUTH_CALLBACK)
+
         # If this is app auth, set JWT cookie
         if result.get("purpose") == "app_auth" and result.get("jwt_token"):
+            await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_SUCCESS)
             response = JSONResponse(
                 {k: v for k, v in result.items() if k != "jwt_token"}
             )
@@ -61,6 +65,7 @@ async def auth_callback(request: Request, auth_service, session_manager):
         import traceback
 
         traceback.print_exc()
+        await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_OAUTH_FAILED)
         return JSONResponse({"error": f"Callback failed: {str(e)}"}, status_code=500)
 
 
@@ -72,6 +77,7 @@ async def auth_me(request: Request, auth_service, session_manager):
 
 async def auth_logout(request: Request, auth_service, session_manager):
     """Logout user by clearing auth cookie"""
+    await TelemetryClient.send_event(Category.AUTHENTICATION, MessageId.ORB_AUTH_LOGOUT)
     response = JSONResponse(
         {"status": "logged_out", "message": "Successfully logged out"}
     )

{openrag-0.1.31 → openrag-0.2.0}/src/api/chat.py

@@ -14,6 +14,7 @@ async def chat_endpoint(request: Request, chat_service, session_manager):
     filters = data.get("filters")
     limit = data.get("limit", 10)
     score_threshold = data.get("scoreThreshold", 0)
+    filter_id = data.get("filter_id")
 
     user = request.state.user
     user_id = user.user_id
@@ -42,6 +43,7 @@ async def chat_endpoint(request: Request, chat_service, session_manager):
                 jwt_token,
                 previous_response_id=previous_response_id,
                 stream=True,
+                filter_id=filter_id,
             ),
             media_type="text/event-stream",
             headers={
@@ -58,6 +60,7 @@ async def chat_endpoint(request: Request, chat_service, session_manager):
             jwt_token,
             previous_response_id=previous_response_id,
             stream=False,
+            filter_id=filter_id,
         )
         return JSONResponse(result)
 
@@ -71,6 +74,7 @@ async def langflow_endpoint(request: Request, chat_service, session_manager):
     filters = data.get("filters")
     limit = data.get("limit", 10)
     score_threshold = data.get("scoreThreshold", 0)
+    filter_id = data.get("filter_id")
 
     user = request.state.user
     user_id = user.user_id
@@ -100,6 +104,7 @@ async def langflow_endpoint(request: Request, chat_service, session_manager):
                     jwt_token,
                     previous_response_id=previous_response_id,
                     stream=True,
+                    filter_id=filter_id,
                 ),
                 media_type="text/event-stream",
                 headers={
@@ -116,6 +121,7 @@ async def langflow_endpoint(request: Request, chat_service, session_manager):
                 jwt_token,
                 previous_response_id=previous_response_id,
                 stream=False,
+                filter_id=filter_id,
             )
             return JSONResponse(result)
 

{openrag-0.1.31 → openrag-0.2.0}/src/api/connectors.py

@@ -1,6 +1,7 @@
 from starlette.requests import Request
 from starlette.responses import JSONResponse, PlainTextResponse
 from utils.logging_config import get_logger
+from utils.telemetry import TelemetryClient, Category, MessageId
 
 logger = get_logger(__name__)
 
@@ -25,6 +26,7 @@ async def connector_sync(request: Request, connector_service, session_manager):
     selected_files = data.get("selected_files")
 
     try:
+        await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_SYNC_START)
         logger.debug(
             "Starting connector sync",
             connector_type=connector_type,
@@ -102,6 +104,7 @@ async def connector_sync(request: Request, connector_service, session_manager):
                 jwt_token=jwt_token,
             )
         task_ids = [task_id]
+        await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_SYNC_COMPLETE)
         return JSONResponse(
             {
                 "task_ids": task_ids,
@@ -114,6 +117,7 @@ async def connector_sync(request: Request, connector_service, session_manager):
 
     except Exception as e:
         logger.error("Connector sync failed", error=str(e))
+        await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_SYNC_FAILED)
         return JSONResponse({"error": f"Sync failed: {str(e)}"}, status_code=500)
 
 
@@ -185,6 +189,7 @@ async def connector_webhook(request: Request, connector_service, session_manager
         config=temp_config,
     )
     try:
+        await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_WEBHOOK_RECV)
         temp_connector = connector_service.connection_manager._create_connector(
             temp_connection
         )
@@ -336,6 +341,7 @@ async def connector_webhook(request: Request, connector_service, session_manager
 
     except Exception as e:
         logger.error("Webhook processing failed", error=str(e))
+        await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_WEBHOOK_FAILED)
         return JSONResponse(
             {"error": f"Webhook processing failed: {str(e)}"}, status_code=500
         )