rag_api and rag-forge
A provides a production-ready RAG API implementation, while B offers benchmarking utilities to optimize the pipeline configurations that A would deploy—making them complementary tools where B helps tune A's chunking, embedding, and retrieval parameters.
About rag_api
danny-avila/rag_api
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector
Organizes embeddings by `file_id` to enable targeted, file-level vector retrieval with metadata filtering—particularly useful for multi-document RAG scenarios. Supports multiple embedding providers (OpenAI, Azure, Hugging Face, Bedrock, Ollama, Google) and vector backends beyond pgvector, with configurable chunking, batching, and async processing for scalability. Designed as a pluggable service for LibreChat but works as a standalone ID-based document indexing API with optional JWT authentication.
About rag-forge
Arthrocentesisgenusphylloxera328/rag-forge
Benchmark RAG pipeline configurations by testing chunking, embedding, and retrieval methods to identify the best setup for your documents and queries.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work