Skip to main content
POST
/
v1
/
tools
/
tabular-data-analysis
Tabular Data Analysis
curl --request POST \
  --url https://{base_url}/gpt/v1/tools/tabular-data-analysis \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "context_filter": {
    "collection": "pgpt_collection",
    "artifacts": [
      "artifact_id_1, artifact_id_2"
    ],
    "metadata_filter": [
      {
        "key": "file_id",
        "operator": "==",
        "value": "artifact_id_1"
      }
    ]
  }
}
'
{
  "content": [
    {
      "type": "text",
      "text": "Average revenue across departments: Sales - $1.2M, Marketing - $850K..."
    }
  ],
  "is_error": false
}

Body

application/json

Request body for analyzing tabular data using a natural language query. Includes filters to scope the documents containing structured data.

Request body for tabular data analysis using the tool.

​
query
string
required

The analysis question or prompt related to tabular data.

Example:

"Show average revenue by department over the last 3 quarters."

​
context_filter
ContextFilter · object
required

Filters to select specific context from ingested documents.

Response

Tabular analysis completed successfully.

Response returned from tool-based operations.

​
content
(TextBlock · object | ImageBlock · object | AudioBlock · object | BinaryBlock · object | ResourceLinkBlock · object | ResourceBlock · object | SourceBlock · object | ToolUseBlock · object | ThinkingBlock · object | TLDRBlock · object)[]
required

List of content blocks generated by the tool. Blocks can include plain text, citations, source attributions, or images.

Text content block containing natural language text.

​
is_error
boolean
default:false

True if the tool encountered an error during execution.