Multi-Document RAG with Reranking

Search across multiple document collections, rerank chunks by relevance using a cross-encoder, and generate a cited, structured answer from multiple sources.

You will learn to:

• Index and query documents from multiple distinct sources in a single vector store
• Understand why initial vector search returns noisy results and why reranking helps
• Integrate Cohere Rerank to score retrieved chunks by true relevance
• Instruct an LLM to cite specific source documents in its generated answers
• Measure citation accuracy and answer quality using an evaluation set