Skip to main content
POST
/
api
/
r2r
/
v3
/
chunks
/
search
Search Chunks
curl --request POST \
  --url https://api.intelligence.io.solutions/api/r2r/v3/chunks/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "search_settings": {
    "model": "<string>",
    "temperature": 123,
    "top_p": 123,
    "max_tokens_to_sample": 123,
    "stream": true,
    "functions": [
      "<any>"
    ],
    "tools": [
      "<any>"
    ],
    "add_generation_kwargs": [
      "<any>"
    ],
    "api_base": "<string>",
    "response_format": [
      {
        "Base Model": {}
      }
    ],
    "extended_thinking": false,
    "thinking_budget": 123,
    "reasoning_effort": "<string>"
  }
}'
{
  "results": [
    {
      "id": "3f3d47f3-8baf-58eb-8bc2-0171fb1c6e09",
      "document_id": "3e157b3a-8469-51db-90d9-52e7d896b49b",
      "collection_ids": [
        "collection_ids"
      ],
      "text": "Example text from the document",
      "metadata": {
        "associated_query": "What is the capital of France?",
        "title": "example_document.pdf"
      },
      "owner_id": "2acb499e-8428-543b-bd85-0d9098718220",
      "score": 0.23943702876567796
    }
  ]
}
This endpoint allows for complex filtering of search results using PostgreSQL-based queries. Filters can be applied to various fields such as document_id, and internal metadata values. Allowed operators include eq, neq, gt, gte, lt, lte, like, ilike, in, and nin.

Authorizations

Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json
query
string<json>
required

JSON object defining search criteria (e.g., document_id, text patterns)

search_settings
object

Main search settings class that combines shared settings with specialized settings for chunks and graph.

Response

200

results
object[]
I