# HyDE

> Have the LLM write a hypothetical answer document, embed it, and use it as the retrieval query.

- **Category**: Agentic AI
- **Subcategory**: Retrieval & RAG
- **Canonical URL**: https://designpattern.fyi/patterns/hyde/

---

## Description
**Intent**: Have the LLM write a hypothetical answer document, embed it, and use it as the retrieval query.
**Context**: A team is using dense vector retrieval to find documents that match user queries, but the queries are short and underspecified — often a few words — while the passages in the corpus are long, well-formed, and written in a different style. The team also does not have labelled query-document relevance pairs that would let them train a query encoder to bridge the asymmetry.
**Solution**: On query: prompt the LLM to draft a hypothetical answer to the query. Embed the hypothetical answer. Retrieve top-k by similarity to that embedding (not the original query). Pass the retrieved chunks into normal RAG.


## Use Cases
- Short user queries underperform on dense retrieval against long documents.
- An LLM call to draft a hypothetical answer fits the latency and cost budget.
- Recall on the first stage of RAG is the current bottleneck.





## Trade-offs


### Advantages

- Zero-shot improvement; no encoder fine-tuning.

- Particularly strong on short, underspecified queries.




### Considerations & Drawbacks

- Off-topic hallucinations cause retrieval drift.

- One extra LLM call per query.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/hyde/)