Sushi Kitchen
Back to Combos
Combo

Knowledge RAG

A turnkey solution for building retrieval-augmented generation (RAG) systems that can chat with your documents. AnythingLLM provides an intuitive interface for uploading documents and asking questions, while Qdrant serves as the high-performance vector database that stores document embeddings for semantic search. LiteLLM acts as a universal gateway that can connect to both local models (via Ollama) and cloud APIs, giving you flexibility in model selection. This combo solves the fundamental challenge of making your private documents queryable through natural language, enabling you to build knowledge bases that can answer complex questions by understanding context and relationships across your entire document collection.

Difficulty • intermediate

Core Services

3 required

AnythingLLM

Retrieval-augmented chat workspace bundling document ingestion, embedding, vector storage and multi-provider model connectivity into one container. Answers cite the source passages they were drawn from.

View details

Qdrant

Vector database written in Rust, pairing dense and sparse vectors with structured payloads so that metadata filters and nearest-neighbour search are resolved together in a single query.

View details

LiteLLM

Gateway fronting more than 100 model providers behind a single OpenAI-compatible API, adding routing rules, fallback chains, retries, per-key spend limits and request logging.

View details