Hybrid RAG Lab

Combine dense (semantic) and BM25 (lexical) retrieval with Reciprocal Rank Fusion, then generate a grounded answer from the fused context.

GuidedNo API keys in Lab

Guided execution

This Lab replays a recorded Cookbook execution in your browser — no API keys required here. Running the Cookbook locally uses your own provider credentials.

Example question

Pick one question, then run the recorded pipeline.

What should I do when a customer's internet keeps cutting out unexpectedly?How do I fix error E_CONN_42?How do I load user profiles with NebulaAPI v2.3 without blocking?

Execution

Choose a question and run the recorded pipeline to compare dense and BM25 retrieval, then see how RRF fuses them.

You will see: Chunking → Embeddings → BM25 index → Dense → Lexical → RRF → Prompt → LLM → Answer

Previous Lab

Start with Basic RAG — learn the minimal retrieval → generation pipeline.

Continue Learning

Deeper explanations in the DataAIHub knowledge graph.

Implementation

Run the same pipeline locally from the public Cookbook.

Related Tools

Canonical tools often used in hybrid RAG stacks.

Lab ID hybrid-rag · guided / precomputed