Skip to main content
POST
/
v1
/
artifacts
/
chunked-content
Retrieve Full Document Content in Chunks
curl --request POST \
  --url https://{base_url}/gpt/v1/artifacts/chunked-content \
  --header 'Content-Type: application/json' \
  --data '
{
  "context_filter": {
    "collection": "pgpt_collection",
    "artifacts": [
      "artifact_id_1, artifact_id_2"
    ],
    "metadata_filter": [
      {
        "key": "file_id",
        "operator": "==",
        "value": "artifact_id_1"
      }
    ]
  }
}
'
{
  "data": [
    {
      "artifact_id": "annual_report_2023",
      "content": [
        {
          "type": "text",
          "text": "ANNUAL REPORT 2023\n\nExecutive Summary\n\nFiscal year 2023 marked a transformative period for our organization with record-breaking performance across all key metrics."
        },
        {
          "type": "text",
          "text": "Revenue Analysis\n\nTotal revenue reached $12.4M, representing a 34% increase year-over-year. Growth was driven primarily by enterprise customer acquisition and subscription renewals."
        }
      ]
    },
    {
      "artifact_id": "quarterly_summary_q4",
      "content": [
        {
          "type": "text",
          "text": "Q4 QUARTERLY SUMMARY\n\nQuarter Overview\n\nThe fourth quarter concluded our strongest year on record, with significant achievements in customer satisfaction and operational efficiency."
        }
      ]
    }
  ]
}

Body

application/json

Request body for retrieving chunked document content.

Contains context filtering options to select specific documents by collection, artifacts, and metadata criteria, plus optional token limiting for chat optimization.

The request body defines filtering criteria and chunking parameters for retrieving documents split into chat-ready content blocks with citations.

Request body for retrieving full document content with filtering options.

​
context_filter
ContextFilter · object
required

Filter to select documents to retrieve. Supports filtering by collection, artifacts, and metadata.

​
max_tokens
integer | null

Maximum number of tokens to return in the content. If not set, returns full content of the documents.

Required range: x >= 1

Response

Successful chunked content retrieval

Response containing chunked document content for chat usage.

​
data
ChunkedContentDocumentResponse · object[]
required

List of documents with their content split into chunks for chat usage