Posts about rag. ← All posts
Vector search treats every chunk as independent. GraphRAG models the relationships between entities, communities, and concepts. For corpus-spanning questions ("what's the relationship between X and Y"), graph wins.
Embedding a question and embedding an answer often produce different vectors. HyDE generates a hypothetical answer to the question, embeds *that*, and retrieves on it. Retrieval quality goes up disproportionately.
Naive RAG retrieves on every query. Self-RAG decides whether to retrieve. CRAG decides whether the retrieved content is good enough or needs corrective retrieval. Two papers; both worth implementing.
An Indian banking deployment needs to handle Hindi, Marathi, Tamil, Bengali, and English in the same retrieval pipeline. Bhashini (the government's language stack) plus cross-lingual embeddings make it tractable.