Activepieces Management Octri Preview
POST/v1/knowledge-base/files/search

Search knowledge base files by vector similarity

Searches knowledge base files using vector similarity. Supply knowledgeBaseFileIds and a 768-value queryEmbedding; use limit and similarityThreshold to control the results.

  • IdempotentThe SDK sends Idempotency-Key, so a retried request is only applied once.

4 body fields

Vector search criteria for the knowledge base.

knowledgeBaseFileIdsarray<string>required
The identifiers of the knowledge base files to search.
limitintegeroptional
The maximum number of results to return. Must be between 1 and 100; defaults to 5 when omitted.
Default:5
queryEmbeddingarray<number>required
The numeric embedding to search with. Must contain exactly 768 values.
similarityThresholdnumberoptional
The minimum similarity score for returned results. Must be between 0 and 1.

1 status code
200Returns the results of the vector similarity search.

Error handling

knowledgeBaseFileIds and queryEmbedding are required. queryEmbedding must contain exactly 768 numeric values; limit must be between 1 and 100 and defaults to 5, and similarityThreshold must be between 0 and 1 when supplied.