AI/ML●●Solid
Deploy a RAG pipeline as a REST API using RAGLight
Modular RAG with MCP integration, but Langchain and LlamaIndex already dominate.
Ship It
bessouat40
313mo ago
Back to browse
GitHub Repository
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.
664 starsPython
RAGLight, serve a RAG pipeline as a REST API and chat UI in one command
by bessouat40·Mar 5, 2026·1 point·0 comments
AI Analysis
●MidShip It
RAG library with serve command, but Langchain, LlamaIndex, and Verba already dominate.
Strengths
- •Modular design lets you swap LLM and embedding providers without rewriting
- •Docker Compose deployment ready, no complex orchestration needed
- •MCP integration enables connecting external tools and data sources cleanly
Weaknesses
- •RAG-as-a-service is saturated; no clear differentiation from established frameworks
- •Limited provider support (Ollama, LMStudio, OpenAI) vs competitors' ecosystems
Category
Target Audience
Backend developers, ML engineers building RAG applications
Similar To
LangChain · LlamaIndex · Verba
Post Description
I added a `serve` command to RAGLight, a modular RAG library I've been building.
raglight serve # FastAPI server (ingest, query, list collections) raglight serve --ui # same + Streamlit chat UI
Config is env vars (LLM provider, embeddings provider, collection name, port).Similar Projects
AI/ML●Mid
Run Hugging Face models with a single command
Yet another model runner when Ollama already dominates this space.
SlickShip It
dataversity
232mo ago
Developer Tools●Mid
MD Serve – Serve a directory of Markdown files as rendered HTML
Yet another Markdown server when markserv, docsify, and mkdocs already exist.
Ship It
kalonis
202mo ago
Infrastructure●●●Banger
Dust – Device Unified Serving Toolkit (CUDA for Phones)
CUDA for phones: native runtimes, thin bridges, real demos shipping GGUF and ONNX inference.
Ship ItSolve My ProblemNiche Gem
ruizprogelio
313mo ago
AI/ML●●Solid
Stop Using LangChain
LangChain alternative with 2 dependencies and async-native architecture from the start.
Big BrainSolve My Problem
aminau
301mo ago
Developer Tools●Mid
Host any GGUF model in one command
Ollama and llama.cpp server already do this with more maturity and model support.
Ship It
gauravvij137
302mo ago