Semantic Search

Semantic vector search over stored memories.

Embeds the query text, runs HNSW nearest-neighbour search, and returns ranked text chunks with similarity scores. No planner LLM call.

Scoped to the current tenant (org_id + user_id).

post/search

Request

Base URL
https://api.getmetacognition.com (the document declares no server; this is the origin it was published from)
Auth
HTTP bearer
TypeScript
https://skmtc.dev/metacognition/apis/tex-api/docs/search/post.ts
A function with typed inputs. Its response is checked against the schema.

querystring required

Natural language search query

top_kinteger

Number of results to return

min_scorenumber nullable

Minimum similarity score (0-1)

labelstring nullable

Filter by node label/type

metadata_filterobject nullable

Key-value metadata filters

Successful Response

query_embedding_msinteger

Time to embed query (ms)

search_msinteger

Time to search HNSW index (ms)

No recorded changes to this operation across all 1 revision of this API.