Skip to main content

Search for documents

POST 

/ai/embeddings/similarity-search

Perform a similarity search on a Telnyx Storage Bucket, returning the most similar num_docs document chunks to the query.

Currently the only available distance metric is cosine similarity which will return a distance between 0 and 1. The lower the distance, the more similar the returned document chunks are to the query. A certainty will also be returned, which is a value between 0 and 1 where the higher the certainty, the more similar the document. You can read more about Weaviate distance metrics here: Weaviate Docs

If a bucket was embedded using a custom loader, such as intercom, the additional metadata will be returned in the loader_metadata field.

Request

Body

required

    bucket_name Bucket Namerequired
    query Queryrequired
    num_of_docs Num Of Docs

    Default value: 3

Responses

200: Successful Response

Schema

    data

    object[]

    required

  • Array [

  • document_chunk Document Chunkrequired
    distance Distancerequired

    metadata

    object

    required

    source Sourcerequired
    checksum Checksumrequired
    embedding Embeddingrequired
    filename Filenamerequired
    certainty Certainty
    loader_metadata object
  • ]

422: Validation Error

Schema

    detail

    object[]

  • Array [

  • loc

    object[]

    required

  • Array [

  • anyOf

    string

  • ]

  • msg Messagerequired
    type Error Typerequired
  • ]

Loading...