New RAGLight feature : deploy a RAG pipeline as a REST API with one command

Most RAG tutorials end with "wrap it in FastAPI yourself." I got tired of writing the same boilerplate and built it once. I’ve been working on an open-source project called RAGLight . The goal is to make it easy to prototype RAG and Agentic RAG pipelines locally. Recent feature: You can now deploy a RAG pipeline as a REST API with one command: pip install raglight raglight serve --port 8000 The API is configured entirely via environment variables (LLM provider, embeddings, vector database). Currently supports: Ollama, OpenAI, Mistral, Gemini, HuggingFace, ChromaDB Repo : https://github.com/Bessouat40/RAGLight Documentation : https://raglight.mintlify.app/documentation/rest-api Curious to hear feedback from people building RAG systems.