HyDE-augmented embeddings search (Hypothetical Document Embeddings)
obsidian_hyde_searchGenerates a synthetic answer to your query, embeds it instead of the raw question, and retrieves relevant notes from your Obsidian vault. Improves accuracy on vague queries.
Instructions
v3.1.0 — HyDE retrieval (Gao et al 2023). Caller agent generates a synthetic answer to its own question, passes it as hypothetical_answer; the server embeds the answer (not the question) and retrieves against the answer-shaped vector. Typically beats raw-query embedding by +2-5 NDCG@10 on under-specified queries (e.g. "what did I learn about X" — the question vector is generic; the answer vector is topically anchored). Uses the same .embed.db as obsidian_embeddings_search. The agent SHOULD generate the hypothetical answer with no vault access (otherwise the loop is circular); 1-3 sentences in the same style/register as your notes. If hypothetical_answer is empty, falls back to embedding the raw query. Requires enquire-mcp build-embeddings first.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max hits (default 10) | |
| query | Yes | The original user question. Echoed in the response for audit-trail; does NOT influence retrieval when hypothetical_answer is non-empty. | |
| folder | No | Restrict to a subfolder (vault-relative) | |
| min_score | No | Drop hits below this cosine score (default 0.3). | |
| hypothetical_answer | Yes | A 1-3 sentence synthetic answer the agent generates to its own query (without vault access). This is what gets embedded. Make it topically dense + match the register/style of your vault notes. |