POST
/
api
/
chunk
/
count
Count chunks above threshold
curl --request POST \
  --url https://api.trieve.ai/api/chunk/count \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Dataset: <tr-dataset>' \
  --data '{
  "query": "Some search query",
  "score_threshold": 0.5,
  "search_type": "semantic"
}'
{
  "count": 1
}

Authorizations

​
Authorization
string
header
required

Headers

​
TR-Dataset
string<uuid>
required

The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.

Body

application/json

JSON request payload to count chunks for a search query

​
query
required

Query is the search query. This can be any string. The query will be used to create an embedding vector and/or SPLADE vector which will be used to find the result set. You can either provide one query, or multiple with weights. Multi-query only works with Semantic Search and is not compatible with cross encoder re-ranking or highlights.

​
search_type
enum<string>
required
Available options:
fulltext,
semantic,
bm25
​
filters
object

ChunkFilter is a JSON object which can be used to filter chunks. This is useful for when you want to filter chunks by arbitrary metadata. Unlike with tag filtering, there is a performance hit for filtering on metadata.

Example:
{
  "must": [
    {
      "field": "tag_set",
      "match_all": ["A", "B"]
    },
    {
      "field": "num_value",
      "range": { "gte": 10, "lte": 25 }
    }
  ]
}
​
limit
integer | null

Set limit to restrict the maximum number of chunks to count. This is useful for when you want to reduce the latency of the count operation. By default the limit will be the number of chunks in the dataset.

Required range: x >= 0
​
score_threshold
number | null

Set score_threshold to a float to filter out chunks with a score below the threshold. This threshold applies before weight and bias modifications. If not specified, this defaults to 0.0.

​
use_quote_negated_terms
boolean | null

If true, quoted and - prefixed words will be parsed from the queries and used as required and negated words respectively. Default is false.

Response

Number of chunks satisfying the query

​
count
integer
required
Required range: x >= 0