Sign in

v4

latestOpenAPI 3.1.02026-08-01420618.8 KB
Recall (Search)

Search memory entries

Search memory entries - Low latency for conversational

post/v4/search

Request body

containerTagstring

Optional tag this search should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to filter memories.

containerTagsstring[]

Optional tags this search should be containerized by. Search is scoped to memories under these tags.

thresholdnumber

Threshold / sensitivity for memories selection. 0 is least sensitive (returns most memories, more results), 1 is most sensitive (returns lesser memories, accurate results)

limitinteger

Maximum number of results to return

qstring required

Search query string

rerankboolean

If true, rerank the results based on the query. This is helpful if you want to ensure the most relevant results are returned.

aggregateboolean

If true, aggregates information from multiple memories to create new synthesized memories. The result will be a mix of aggregated and non-aggregated memories, reranked by relevance to the query. Works in conjunction with reranking.

rewriteQueryboolean

If true, rewrites the query to make it easier to find documents. This increases the latency by about 400ms

searchMode'memories' | 'hybrid' | 'documents'

Search mode. 'memories' searches only memory entries (default). 'hybrid' searches both memories and document chunks. 'documents' searches only document chunks.

filepathstring

Filter search results by filepath. Exact match for full paths, prefix match if ending with /

Response

Memory search results

timingnumber required

Search execution time in milliseconds

totalnumber required

Total number of results returned

Example response

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "The user prefers detailed API responses over minimal ones.",
      "chunk": "This is a chunk of content from a document...",
      "metadata": {
        "source": "conversation",
        "confidence": 0.9
      },
      "similarity": 0.89,
      "version": 3,
      "context": {
        "parents": [
          {
            "relation": "updates",
            "version": -1,
            "memory": "Earlier version: API rate limit is 50 req/min on the free tier."
          }
        ],
        "children": [
          {
            "relation": "extends",
            "version": 1,
            "memory": "Later version: API rate limit increased to 100 req/min on the free tier."
          }
        ]
      },
      "documents": [
        {
          "id": "doc_xyz789",
          "title": "API Rate Limiting Policy",
          "type": "web",
          "metadata": {
            "source": "upload",
            "language": "en"
          },
          "summary": "API rate limit policy: 100 req/min free, 1000 req/min pro."
        }
      ],
      "chunks": [
        {
          "content": "This is a chunk of content from the document...",
          "score": 0.85,
          "documentId": "doc_xyz789"
        }
      ]
    }
  ],
  "timing": 245,
  "total": 5
}