# RAGLight > RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources. - **Type:** MCP server - **Install:** `agentstack add mcp-bessouat40-raglight` - **Verified:** Yes β€” security-reviewed for prompt injection and unsafe behavior - **Seller:** [Bessouat40](https://agentstack.voostack.com/s/bessouat40) - **Installs:** 0 - **Category:** [Databases](https://agentstack.voostack.com/c/databases) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [Bessouat40](https://github.com/Bessouat40) - **Source:** https://github.com/Bessouat40/RAGLight - **Website:** https://raglight.mintlify.app/ ## Install ```sh agentstack add mcp-bessouat40-raglight ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # RAGLight [](https://pepy.tech/projects/raglight) [](https://github.com/Bessouat40/RAGLight/actions/workflows/test.yml) **RAGLight** is a lightweight and modular Python library for implementing **Retrieval-Augmented Generation (RAG)**. It enhances the capabilities of Large Language Models (LLMs) by combining document retrieval with natural language inference. Designed for simplicity and flexibility, RAGLight provides modular components to easily integrate various LLMs, embeddings, and vector stores, making it an ideal tool for building context-aware AI solutions. --- ## πŸ“š Table of Contents - [Requirements](#⚠️-requirements) - [Features](#features) - [Import library](#import-library-πŸ› οΈ) - [Chat with Your Documents Instantly With CLI](#chat-with-your-documents-instantly-with-cli-πŸ’¬) - [Ignore Folders Feature](#ignore-folders-feature-🚫) - [Ignore Folders in Configuration Classes](#ignore-folders-in-configuration-classes-🚫) - [Deploy as a REST API (raglight serve)](#deploy-as-a-rest-api-raglight-serve-🌐) - [Start the server](#start-the-server) - [Launch the Chat UI](#launch-the-chat-ui-πŸ’¬) - [Endpoints](#endpoints) - [Configuration via environment variables](#configuration-via-environment-variables) - [Deploy with Docker Compose](#deploy-with-docker-compose) - [Environment Variables](#environment-variables) - [Providers and Databases](#providers-and-databases) - [LLM](#llm) - [Embeddings](#embeddings) - [Vector Store](#vector-store) - [Quick Start](#quick-start-πŸš€) - [Knowledge Base](#knowledge-base) - [RAG](#rag) - [Agentic RAG](#agentic-rag) - [MCP Integration](#mcp-integration) - [Use Custom Pipeline](#use-custom-pipeline) - [Override Default Processors](#override-default-processors) - [Hybrid Search](#hybrid-search-bm25--semantic--rrf-) - [Qdrant Vector Store](#qdrant-vector-store-️) - [Query Reformulation](#query-reformulation-✍️) - [Streaming Output](#streaming-output-⚑) - [Conversation History](#conversation-history-πŸ’¬) - [AWS Bedrock](#aws-bedrock-☁️) - [Observability with Langfuse](#observability-with-langfuse) - [Use RAGLight with Docker](#use-raglight-with-docker) - [Build your image](#build-your-image) - [Run your image](#run-your-image) --- > ## ⚠️ Requirements > > Actually RAGLight supports : > > - Ollama > - Google Gemini > - LMStudio > - vLLM > - OpenAI API > - Mistral API > - AWS Bedrock > > If you use LMStudio, you need to have the model you want to use loaded in LMStudio. > If you use AWS Bedrock, configure your AWS credentials (env vars, `~/.aws/credentials`, or IAM role) β€” no extra install needed. ## Features - **Embeddings Model Integration**: Plug in your preferred embedding models (e.g., HuggingFace **all-MiniLM-L6-v2**) for compact and efficient vector embeddings. - **LLM Agnostic**: Seamlessly integrates with different LLMs from different providers (Ollama, LMStudio, Mistral, OpenAI, Google Gemini, AWS Bedrock). - **RAG Pipeline**: Combines document retrieval and language generation in a unified workflow. - **Agentic RAG Pipeline**: Use Agent to improve your RAG performances. - πŸ”Œ **MCP Integration**: Add external tool capabilities (e.g. code execution, database access) via MCP servers. - **Flexible Document Support**: Ingest and index various document types (e.g., PDF, TXT, DOCX, Python, Javascript, ...). - **Extensible Architecture**: Easily swap vector stores, embedding models, or LLMs to suit your needs. - πŸ” **Hybrid Search (BM25 + Semantic + RRF)**: Combine keyword-based BM25 retrieval with dense vector search using Reciprocal Rank Fusion for best-of-both-worlds results. - ✍️ **Query Reformulation**: Automatically rewrites follow-up questions into standalone queries using conversation history, improving retrieval accuracy in multi-turn conversations. - πŸ’¬ **Conversation History**: Full multi-turn history supported across all providers (Ollama, OpenAI, Mistral, LMStudio, Gemini, Bedrock) with optional `max_history` cap. - ⚑ **Streaming Output**: Token-by-token streaming via `generate_streaming()` on all providers β€” drop-in alongside `generate()` with no extra configuration. - ☁️ **AWS Bedrock**: Use Claude, Titan, Llama and other Bedrock models for both LLM inference and embeddings. - πŸ“Š **Langfuse Observability (v3+)**: Trace every RAG call end-to-end β€” retrieve, rerank, and generate β€” directly in your Langfuse dashboard. --- ## Import library πŸ› οΈ Install the base library: ```bash pip install raglight ``` RAGLight uses **optional extras** for vector store backends, so you only install what you need: | Extra | Package installed | Notes | | -------------------- | ----------------- | ----------------------------------------------------- | | `raglight[chroma]` | `chromadb` | Requires a C++ compiler on Windows | | `raglight[qdrant]` | `qdrant-client` | Pure Python β€” works on Windows without a C++ compiler | | `raglight[langfuse]` | `langfuse` | Observability tracing | ```bash pip install "raglight[qdrant]" # Qdrant only (Windows-friendly) pip install "raglight[chroma]" # ChromaDB only pip install "raglight[chroma,qdrant]" # both pip install "raglight[qdrant,langfuse]" # Qdrant + observability ``` --- ## Chat with Your Documents Instantly With CLI πŸ’¬ For the quickest and easiest way to get started, RAGLight provides an interactive command-line wizard. It will guide you through every step, from selecting your documents to chatting with them, without writing a single line of Python. Prerequisite: Ensure you have a local LLM service like Ollama running. Just run this one command in your terminal: ```bash raglight chat ``` You can also launch the Agentic RAG wizard with: ```bash raglight agentic-chat ``` The wizard will guide you through the setup process. Here is what it looks like: The wizard will ask you for: - πŸ“‚ Data Source: The path to your local folder containing the documents. - 🚫 Ignore Folders: Configure which folders to exclude during indexing (e.g., `.venv`, `node_modules`, `__pycache__`). - πŸ’Ύ Vector Database: Where to store the indexed data and what to name it. - 🧠 Embeddings Model: Which model to use for understanding your documents. - πŸ€– Language Model (LLM): Which LLM to use for generating answers. After configuration, it will automatically index your documents and start a chat session. ### Ignore Folders Feature 🚫 RAGLight automatically excludes common directories that shouldn't be indexed, such as: - Virtual environments (`.venv`, `venv`, `env`) - Node.js dependencies (`node_modules`) - Python cache files (`__pycache__`) - Build artifacts (`build`, `dist`, `target`) - IDE files (`.vscode`, `.idea`) - And many more... You can customize this list during the CLI setup or use the default configuration. This ensures that only relevant code and documentation are indexed, improving performance and reducing noise in your search results. ### Ignore Folders in Configuration Classes 🚫 The ignore folders feature is also available in all configuration classes, allowing you to specify which directories to exclude during indexing: - **RAGConfig**: Use `ignore_folders` parameter to exclude folders during RAG pipeline indexing - **AgenticRAGConfig**: Use `ignore_folders` parameter to exclude folders during AgenticRAG pipeline indexing - **VectorStoreConfig**: Use `ignore_folders` parameter to exclude folders during vector store operations All configuration classes use `Settings.DEFAULT_IGNORE_FOLDERS` as the default value, but you can override this with your custom list: ```python # Example: Custom ignore folders for any configuration custom_ignore_folders = [ ".venv", "venv", "node_modules", "__pycache__", ".git", "build", "dist", "temp_files", # Your custom folders "cache" ] # Use in any configuration class config = RAGConfig( llm=Settings.DEFAULT_LLM, provider=Settings.OLLAMA, ignore_folders=custom_ignore_folders # Override default ) ``` See the complete example in [examples/ignore_folders_config_example.py](examples/ignore_folders_config_example.py) for all configuration types. --- ## Deploy as a REST API (raglight serve) 🌐 `raglight serve` starts a **FastAPI** server configured entirely via environment variables β€” no Python code required. ### Start the server ```bash raglight serve ``` Options : ``` --host Host to bind (default: 0.0.0.0) --port Port to listen on (default: 8000) --reload Enable auto-reload for development (default: false) --workers Number of worker processes (default: 1) --ui Launch the Streamlit chat UI alongside the API (default: false) --ui-port Port for the Streamlit UI (default: 8501) ``` Example : ```bash RAGLIGHT_LLM_MODEL=mistral-small-latest \ RAGLIGHT_LLM_PROVIDER=Mistral \ raglight serve --port 8080 ``` Langfuse tracing example: ```bash LANGFUSE_HOST=http://localhost:3000 \ LANGFUSE_PUBLIC_KEY=pk-lf-... \ LANGFUSE_SECRET_KEY=sk-lf-... \ raglight serve ``` > Langfuse tracing is enabled automatically when `LANGFUSE_HOST` (or `LANGFUSE_BASE_URL`), > `LANGFUSE_PUBLIC_KEY` and `LANGFUSE_SECRET_KEY` are all set in the environment. > Requires `pip install "raglight[langfuse]"`. ### Launch the Chat UI πŸ’¬ Add `--ui` to start a **Streamlit chat interface** alongside the REST API β€” no extra setup required: ```bash raglight serve --ui ``` | Address | Service | | ----------------------- | ---------------------------- | | `http://localhost:8000` | REST API + Swagger (`/docs`) | | `http://localhost:8501` | Streamlit chat UI | The UI lets you: - **Chat** with your documents β€” full conversation history, markdown rendering - **Upload files** directly from the browser (PDF, TXT, code…) - **Ingest a directory** by providing a path on the server machine - **Switch LLM on the fly** β€” the sidebar's βš™οΈ Model settings panel lets you change provider, model, and API base URL without restarting the server (`AWSBedrock` and `GoogleGemini` included) Use `--ui-port` to change the Streamlit port: ```bash raglight serve --ui --port 8000 --ui-port 3000 ``` Both processes share the same configuration (env vars) and are terminated together when you stop the server. ### Endpoints | Method | Path | Body | Response | | ------ | ---------------- | ----------------------------------------------------------------------------------------- | -------------------------------------------------------------------- | | `GET` | `/health` | β€” | `{"status": "ok"}` | | `POST` | `/generate` | `{"question": "..."}` | `{"answer": "..."}` | | `POST` | `/ingest` | `{"data_path": "...", "file_paths": [...], "github_url": "...", "github_branch": "main"}` | `{"message": "..."}` | | `POST` | `/ingest/upload` | `multipart/form-data` β€” field `files` (one or more files) | `{"message": "..."}` | | `GET` | `/collections` | β€” | `{"collections": [...]}` | | `GET` | `/config` | β€” | `{"llm_provider": "...", "llm_model": "...", "llm_api_base": "..."}` | | `POST` | `/config` | `{"llm_provider": "...", "llm_model": "...", "llm_api_base": "..."}` | `{"llm_provider": "...", "llm_model": "...", "llm_api_base": "..."}` | The interactive API documentation (Swagger UI) is automatically available at `http://localhost:8000/docs`. #### Examples with curl ```bash # Health check curl http://localhost:8000/health # Ask a question curl -X POST http://localhost:8000/generate \ -H "Content-Type: application/json" \ -d '{"question": "What is RAGLight?"}' # Ingest a local folder curl -X POST http://localhost:8000/ingest \ -H "Content-Type: application/json" \ -d '{"data_path": "./my_documents"}' # Ingest a GitHub repository curl -X POST http://localhost:8000/ingest \ -H "Content-Type: application/json" \ -d '{"github_url": "https://github.com/Bessouat40/RAGLight", "github_branch": "main"}' # Upload files directly (multipart) curl -X POST http://localhost:8000/ingest/upload \ -F "files=@./rapport.pdf" \ -F "files=@./notes.txt" # List collections curl http://localhost:8000/collections ``` ### Configuration via environment variables All server settings are read from `RAGLIGHT_*` environment variables. Copy `examples/serve_example/.env.example` to `.env` and adjust the values. | Variable | Default | Description | | ------------------------------ | ------------------------ | -------------------------------------------------------------------------- | | `RAGLIGHT_LLM_MODEL` | `llama3` | LLM model name | | `RAGLIGHT_LLM_PROVIDER` | `Ollama` | LLM provider (`Ollama`, `Mistral`, `OpenAI`, `LmStudio`, `GoogleGemini`) | | `RAGLIGHT_LLM_API_BASE` | `http://localhost:11434` | LLM API base URL | | `RAGLIGHT_EMBEDDINGS_MODEL` | `all-MiniLM-L6-v2` | Embeddings model name | | `RAGLIGHT_EMBEDDINGS_PROVIDER` | `HuggingFace` | Embeddings provider (`HuggingFace`, `Ollama`, `OpenAI`, `GoogleGemini`) | | `RAGLIGHT_EMBEDDINGS_API_BASE` | `http://localhost:11434` | Embeddings API base URL | | `RAGLIGHT_DB` | `Chroma` | Vector store backend (`Chroma` or `Qdrant`) | | `RAGLIGHT_PERSIST_DIR` | `./raglight_db` | Local persistence directory (used when `RAGLIGHT_DB_HOST` is not set) | | `RAGLIGHT_COLLECTION` | `default` | Collection name | | `RAGLIGHT_K` | `5` | Number of documents retrieved per query | | `RAGLIGHT_SYSTEM_PROMPT` | _(default prompt)_ | Custom system prompt for the LLM | | `RAGLIGHT_DB_HOST` | β€” | Remote vector store host (leave unset for local on-disk storage) | | `RAGLIGHT_DB_PORT` | β€” | Remote vector store port | | `RAGLIGHT_API_TIMEOUT` | `300` | Request timeout in seconds for the Streamlit UI (increase for slow models) | ### Deploy with Docker Compose The quickest way to deploy in production : ```bash cd examples/serve_example cp .env.example .env # edit values as needed docker-compose up ``` The `docker-compose.yml` uses `extra_hosts: host.docker.internal:host-gateway` so the container can reach an Ollama instance running on the host machine. --- ## Environment Variables You can set several environment variables to change **RAGLight** settings : **Provider credentials & URLs** - `MISTRAL_API_KEY` if you want to use Mistral API - `OLLAMA_CLIEN … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source β€” we do not rehost the code. - **Author:** [Bessouat40](https://github.com/Bessouat40) - **Source:** [Bessouat40/RAGLight](https://github.com/Bessouat40/RAGLight) - **License:** MIT - **Homepage:** https://raglight.mintlify.app/ Install and usage instructions live in the source repository linked above. ## Pricing - **Free** β€” Free ## Security capabilities Automated source analysis of v0.1.0 β€” what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source β€” more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** β€” security scan: passed β€” Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-bessouat40-raglight - Seller: https://agentstack.voostack.com/s/bessouat40 - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack β€” the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.