Extract chunks from knowledge base

This endpoint can be used to retrieve top n chunks per query. The query can be a single string or a list of strings. The collection field can be used to specify the collection to query, which defaults to base_collection. An optional integer n can be provided in order to retrieve top n chunks, which defaults to 5 if not specified. Response: Returns an array of results, one for each input query.

POST /api/v2/query

Try it

Extract chunks from knowledge base

cURL

curl --request POST \
  --url https://paradigm.lighton.ai/api/v2/query \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "collection": "<string>",
  "n": 123
}
'

200

[
  {
    "chunks": [
      {
        "uuid": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
        "text": "<string>",
        "metadata": {},
        "score": 123
      }
    ],
    "query": "<string>"
  }
]

Authorizations

Authorization · string · header · required

Bearer token authentication

Body

Request serializer for retrieving top n chunks per query.

query · string · required

A single string or a list of strings representing the search queries

collection · string | null

The collection to query, defaults to 'base_collection' if not specified

n · integer | null

Number of top chunks to retrieve per query, defaults to 5 if not specified

Response

200

application/json

Successful response

chunks · object[] · required

List of retrieved document chunks with their relevance scores

Show child attributes

chunks. uuid · string<uuid> · required

Unique identifier for the document chunk

chunks. text · string · required

Text content of the document chunk

chunks. metadata · object · required

Metadata associated with the document chunk

Show child attributes

chunks.metadata. {key} · any

chunks. score · number<double> · required

Relevance score for this chunk relative to the query

query · string

The original query used for retrieval