Create a new extract job.
This endpoint creates an extraction job that runs single-pass LLM extraction
from a parse result or vector store search context. For agentic (decompose / ReAct)
extraction, use POST …/research instead; requests with use_agentic=True are rejected.
Args: request: Extract job request containing source_id and parameters
Returns: JobEntity: The created job entity
Raises: HTTPException: If source not found or workflow startup fails
Documentation Index
Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt
Use this file to discover all available pages before exploring further.
API key for authentication
Selected Account ID
Request model for creating an extract job from a parse result.
Successful Response
Job response model representing an asynchronous operation.
ID of the entity
ID of the project
Operation type (e.g., 'parse')
parse, batch_parse, extract, research, vector_store, chunk, summarization, create_index, update_index Current job status
pending, running, succeeded, partially_succeeded, failed, cancelled When the job was created
"job"Source document/file ID
Request correlation ID for tracing
When the job started processing
When the job completed
Job result payload when completed
Live progress payload (used by batch jobs)
Error message if job failed
Timeline of job execution events