RAG from scratch: Part 9 (Query Translation -- HyDE)
From the video description
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.
Topics
Sources
Video by LangChain, played through YouTube.
- Indie Picks
Data and selection notes
Indie Picks uses video metadata for classification. The description above is an uploader excerpt, not an independent review.
Indie Picks: Independently collected SaaS and AI product videos, organized by a founder handbook. Topics and relevance are metadata-indexed; full-video editorial review has not been completed. Descriptions are uploader excerpts where available.
Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.
Selection checks
- SaaS & AI candidates: Matches the configured criteria
- Editor-approved picks: Editorial review is required