Merge branch 'feature/78-jenkins-authentication' of https://github.com/Yugansh5013/resources-ai-chatbot-plugin into feature/78-jenkins-authentication

Author: Yugansh5013

README.md

@@ -51,6 +51,14 @@ curl -X POST http://127.0.0.1:8000/api/chatbot/sessions
 
 See [docs/README.md](docs/README.md) for detailed explanations.
 
+## 🎥 Setup Video Tutorial
+
+[![Local Setup Video Tutorial](https://img.youtube.com/vi/1DnMNA4aLyE/0.jpg)](https://youtu.be/1DnMNA4aLyE)
+
+The tutorial shows how to fork the repo, set up the backend, download the LLM model, run the frontend, and verify the chatbot works.
+
+
+
 ## Troubleshooting
 
 **llama-cpp-python installation fails**: Ensure build tools are installed and use Python 3.11+

chatbot-core/api/services/chat_service.py

@@ -16,7 +16,8 @@
     RETRIEVER_AGENT_PROMPT,
     SPLIT_QUERY_PROMPT,
 )
-from api.services.memory import get_session
+
+from api.services.memory import get_session, get_session_async
 from api.services.file_service import format_file_context
 from api.tools.tools import TOOL_REGISTRY
 from api.tools.utils import (
@@ -462,7 +463,8 @@ async def get_chatbot_reply_stream(
     logger.info("Streaming message from session '%s'", session_id)
     logger.info("Handling user query: %s", user_input)
 
-    memory = get_session(session_id)
+    memory = await get_session_async(session_id)
+
     if memory is None:
         raise RuntimeError(
             f"Session '{session_id}' not found in memory store.")

chatbot-core/api/services/memory.py

@@ -2,7 +2,7 @@
 Handles in-memory chat session state (conversation memory).
 Provides utility functions for session lifecycle.
 """
-
+import asyncio
 import uuid
 import logging
 from datetime import datetime, timedelta
@@ -152,6 +152,12 @@ def get_session(session_id: str) -> ConversationBufferMemory | None:
 
         return memory
 
+async def get_session_async(session_id: str) -> ConversationBufferMemory | None:
+    """
+    Async wrapper for get_session to prevent event loop blocking.
+    """
+    return await asyncio.to_thread(get_session, session_id)
+
 
 def persist_session(session_id: str)-> None:
     """

docs/setup.md

@@ -43,6 +43,15 @@ For the setup instructions have been provided for *Linux* and *Windows*. Moreove
     ```bash
     pip install -r requirements.txt
     ```
+
+    > **Note:** The backend requires `python-multipart` for multipart form handling.
+    > This dependency is included in the requirements file, but if you encounter
+    > runtime errors related to multipart requests, ensure it is installed:
+    >
+    > ```bash
+    > pip install python-multipart
+    > ```
+
 5. **Set the `PYTHONPATH` to the current directory(`chatbot-core/`)**
     ```bash
     export PYTHONPATH=$(pwd)
@@ -57,6 +66,14 @@ For the setup instructions have been provided for *Linux* and *Windows*. Moreove
         * Download the file named `mistral-7b-instruct-v0.2.Q4_K_M.gguf`
         * Place the downloaded file in `api\models\mistral\`
 
+By default, the backend attempts to load the local GGUF model during
+startup. If the model file is missing, the server will fail to start.
+
+Contributors who do not need local inference can run the backend
+without a model by using test mode
+(see “Running without a local LLM model (test mode)” below).
+
+
 ## Installation Guide for Windows
 This guide provides step-by-step instructions for installing and running the Jenkins Chatbot on Windows systems.
 
@@ -103,6 +120,14 @@ This guide provides step-by-step instructions for installing and running the Jen
     ```bash
     pip install -r requirements-cpu.txt
     ```
+    > **Note:** The backend requires `python-multipart` for multipart form handling.
+    > This dependency is included in the requirements file, but if you encounter
+    > runtime errors related to multipart requests, ensure it is installed:
+    >
+    > ```powershell
+    > pip install python-multipart
+    > ```
+
     > **Note**: If you encounter any dependency issues, especially with NVIDIA packages, use the `requirements-cpu.txt` file which excludes GPU-specific dependencies.
 
 5. **Set the PYTHONPATH**
@@ -123,6 +148,13 @@ This guide provides step-by-step instructions for installing and running the Jen
         * Download the file named `mistral-7b-instruct-v0.2.Q4_K_M.gguf`
         * Place the downloaded file in `api\models\mistral\`
 
+By default, the backend attempts to load the local GGUF model during
+startup. If the model file is missing, the server will fail to start.
+
+Contributors who do not need local inference can run the backend
+without a model by using test mode
+(see “Running without a local LLM model (test mode)” below).
+
 ## Automatic setup
 
 To avoid running all the steps each time, we have provided a target in the `Makefile` to automate the setup process.
@@ -141,6 +173,33 @@ make setup-backend IS_CPU_REQ=1
 
 > **Note:** The target **does not** include the installation of the LLM.
 
+### What does `setup-backend` do?
+
+The `setup-backend` Makefile target prepares the Python backend by:
+- Creating a virtual environment in `chatbot-core/venv`
+- Installing backend dependencies from `requirements.txt`
+  (or `requirements-cpu.txt` when `IS_CPU_REQ=1` is set)
+
+You usually do not need to run this manually.
+The `make api` target automatically runs `setup-backend`
+if the backend has not already been set up.
+
+## Running without a local LLM model (test mode)
+
+By default, the backend loads a local GGUF model on startup.
+For contributors who do not need local inference, a test configuration
+is available.
+
+The backend includes a `config-testing.yml` file that disables local
+LLM loading. This configuration is activated when the
+`PYTEST_VERSION` environment variable is set.
+
+Example:
+
+```bash
+PYTEST_VERSION=1 make api
+```
+
 ## Common Troubleshooting
 
 This section covers common issues encountered during setup, especially when installing