LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Python ai-agentsdata-engineeringdocument-aigenerative-aiidpjson-extractionllmmcp-serverocrpdf-extractionprompt-engineeringstructured-output
"""Contract constants for the global search endpoint: parameter bounds,
match tiers and the OSS type keys. Cloud-only type keys are deliberately
absent: cloud apps define and register their own.
"""
from enum import IntEnum
class SearchParams:
QUERY = "q"
TYPES = "types"
LIMIT = "limit"
# A shorter query answers an empty result, not an error.
MIN_QUERY_LENGTH = 2
MAX_QUERY_LENGTH = 100
DEFAULT_LIMIT = 5
MAX_LIMIT = 20
class MatchTier(IntEnum):
"""Ranking tiers, best first. The value is the sort key; the label is
what the response's ``match`` field carries.
"""
NAME_PREFIX = 0
NAME = 1
DESCRIPTION_PREFIX = 2
DESCRIPTION = 3
@property
def label(self) -> str:
return self.name.lower()
class OSSSearchType:
"""Type keys contributed by OSS."""
PROMPT_STUDIO_PROJECT = "prompt_studio_project"
WORKFLOW = "workflow"
API_DEPLOYMENT = "api_deployment"
ETL_PIPELINE = "etl_pipeline"
TASK_PIPELINE = "task_pipeline"
ADAPTER = "adapter"
CONNECTOR = "connector"