Skip to main content
POST
/
v1
/
primitives
/
search
curl --request POST \
  --url https://{base_url}/gpt/v1/primitives/search \
  --header 'Content-Type: application/json' \
  --data '
{
  "type": "semantic_search",
  "text": "Q3 2023 sales performance",
  "context_filter": {
    "collections": [
      "reports"
    ]
  },
  "limit": 10,
  "expand": true
}
'
{
  "object": "list",
  "model": "private-gpt",
  "data": [
    {
      "object": "context.chunk",
      "score": 0.89,
      "document": {
        "object": "ingest.document",
        "artifact": "q3_report",
        "doc_metadata": {
          "title": "Q3 2023 Report",
          "file_name": "Q3_Sales.pdf"
        }
      },
      "text": "Q3 sales increased by 25% compared to Q2, driven primarily by new customer acquisitions in the enterprise segment.",
      "previous_texts": [
        "Q2 comparison shows steady growth trends."
      ],
      "next_texts": [
        "Regional breakdown indicates strongest performance in North America."
      ]
    },
    {
      "object": "context.chunk",
      "score": 0.76,
      "document": {
        "object": "ingest.document",
        "artifact": "q3_report",
        "doc_metadata": {
          "title": "Q3 2023 Report",
          "page_number": 5
        }
      },
      "text": "Sales performance metrics exceeded targets across all key verticals during the third quarter."
    }
  ]
}

Body

application/json

Request body for searching document chunks using different strategies.

Supports three search types:

  • semantic_search: Find chunks based on semantic similarity to the text query
  • keywords_search: Find chunks containing specific keywords (coming soon)
  • hybrid_search: Combine semantic and keyword matching (coming soon)

The request body defines search criteria, context filtering options, result limits, and expansion settings for retrieving relevant document chunks.

The body is of type any.

Response

Successful chunk retrieval