Skip to main content
POST
/
api
/
v2
/
filter
/
chunks
Filter most relevant chunks
curl --request POST \
  --url https://paradigm.lighton.ai/api/v2/filter/chunks \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "chunk_ids": [
    "<string>"
  ],
  "model": "<string>"
}'
{
  "query": "<string>",
  "chunks": [
    {
      "uuid": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "text": "<string>",
      "metadata": {},
      "filter_score": 123
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer token authentication

Body

Request serializer for filtering document chunks based on a query.

​
query
string
required

The query string to filter document chunks against

​
chunk_ids
string[]
required

List of document chunk UUIDs to filter

​
model
string
required

Model to use for the filtering, must exist and be configured. If no model is given, will try to use the 'reranker' finetune.

​
n
integer | null

Maximum number of chunks to return (optional)

Response

Chunks retrieved

Response serializer for document chunk filtering results.

​
query
string
required

The original query used for filtering

​
chunks
object[]
required

List of filtered document chunks with their relevance scores

⌘I