RAG from scratch: Part 9 (Query Translation — HyDE)

HyDE (Hypothetical Document Embeddings) is an approach to improve retrieval that generates hypothetical documents that could be used to answer the user input question. These documents, drawn from the LLMs knowledge, are embedded and used to retrieve documents from an index. The idea is that hypothetical documents may be better aligned with the indexes documents than the raw user question.

Slides:
https://docs.google.com/presentation/d/10MmB_QEiS4m00xdyu-92muY-8jC3CdaMpMXbXjzQXsM/edit?usp=sharing

Code:
https://github.com/langchain-ai/rag-from-scratch/blob/main/rag_from_scratch_5_to_9.ipynb

Reference:
https://arxiv.org/pdf/2212.10496.pdf