Curated tool combinations for common AI/ML use cases. Each stack shows repos that work well together — click to see what each tool does and why it belongs in the stack.
A document Q&A system that embeds your data, stores it in a vector database, retrieves semantically relevant chunks, and generates grounded answers with citations.
Orchestration framework — chains retrieval, prompts, and LLM calls together
rag-retrievalEmbedded vector store — stores and queries document embeddings locally
rag-retrievalEmbedding model — converts text to dense vectors for semantic search
nlp-textAPI server — exposes your RAG pipeline as a REST endpoint
dev-toolsStacks are curated based on knowledge graph compatibility edges and community usage patterns. Star counts are approximate. Ask Reporium to explore alternatives or get personalized stack recommendations.