be22752590
Prompt Modes Integration: - Create local_runtime.py with DOTS_PROMPT_MAP - Map OutputMode to native dots.ocr prompt modes (prompt_layout_all_en, prompt_ocr, etc.) - Support dict_promptmode_to_prompt from dots.ocr with fallback prompts - Add layout_only and region modes to OutputMode enum 2-Stage Q&A Pipeline: - Create qa_builder.py for 2-stage qa_pairs generation - Stage 1: PARSER (dots.ocr) → raw JSON via prompt_layout_all_en - Stage 2: LLM (DAGI Router) → Q&A pairs via mode=qa_build - Update endpoints.py to use 2-stage pipeline for qa_pairs mode - Add ROUTER_BASE_URL and ROUTER_TIMEOUT to config Updates: - Update inference.py to use local_runtime with native prompts - Update ollama_client.py to use same prompt map - Add PROMPT_MODES.md documentation
57 lines
2.0 KiB
Python
57 lines
2.0 KiB
Python
"""
|
|
Configuration for PARSER Service
|
|
"""
|
|
|
|
import os
|
|
from typing import Literal, Optional
|
|
from pydantic_settings import BaseSettings
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
"""Application settings"""
|
|
|
|
# Service
|
|
API_HOST: str = "0.0.0.0"
|
|
API_PORT: int = 9400
|
|
|
|
# PARSER Model
|
|
PARSER_MODEL_NAME: str = os.getenv("PARSER_MODEL_NAME", os.getenv("DOTS_OCR_MODEL_ID", "rednote-hilab/dots.ocr"))
|
|
PARSER_DEVICE: Literal["cuda", "cpu", "mps"] = os.getenv("PARSER_DEVICE", os.getenv("DEVICE", "cpu"))
|
|
PARSER_MAX_PAGES: int = int(os.getenv("PARSER_MAX_PAGES", "100"))
|
|
PARSER_MAX_RESOLUTION: str = os.getenv("PARSER_MAX_RESOLUTION", "4096x4096")
|
|
PARSER_BATCH_SIZE: int = int(os.getenv("PARSER_BATCH_SIZE", "1"))
|
|
|
|
# File handling
|
|
MAX_FILE_SIZE_MB: int = int(os.getenv("MAX_FILE_SIZE_MB", "50"))
|
|
TEMP_DIR: str = os.getenv("TEMP_DIR", "/tmp/parser")
|
|
|
|
# PDF processing
|
|
PDF_DPI: int = int(os.getenv("PDF_DPI", "200"))
|
|
PAGE_RANGE: Optional[str] = os.getenv("PAGE_RANGE", None) # e.g., "1-20" for pages 1-20
|
|
|
|
# Image processing
|
|
IMAGE_MAX_SIZE: int = int(os.getenv("IMAGE_MAX_SIZE", "2048")) # Max size for longest side
|
|
|
|
# Parser mode
|
|
USE_DUMMY_PARSER: bool = os.getenv("USE_DUMMY_PARSER", "false").lower() == "true"
|
|
ALLOW_DUMMY_FALLBACK: bool = os.getenv("ALLOW_DUMMY_FALLBACK", "true").lower() == "true"
|
|
|
|
# Runtime
|
|
RUNTIME_TYPE: Literal["local", "remote", "ollama"] = os.getenv("RUNTIME_TYPE", "local")
|
|
RUNTIME_URL: str = os.getenv("RUNTIME_URL", "http://parser-runtime:11435")
|
|
|
|
# Ollama configuration (if RUNTIME_TYPE=ollama)
|
|
OLLAMA_BASE_URL: str = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
|
|
|
|
# DAGI Router configuration (for qa_pairs 2-stage pipeline)
|
|
ROUTER_BASE_URL: str = os.getenv("ROUTER_BASE_URL", "http://router:9102")
|
|
ROUTER_TIMEOUT: int = int(os.getenv("ROUTER_TIMEOUT", "60"))
|
|
|
|
class Config:
|
|
env_file = ".env"
|
|
case_sensitive = True
|
|
|
|
|
|
settings = Settings()
|
|
|