Files
ragflow/rag/llm/ocr_model.py

99 lines
3.8 KiB
Python
Raw Permalink Normal View History

#
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import json
import logging
import os
from typing import Any, Optional
from deepdoc.parser.mineru_parser import MinerUParser
class Base:
def __init__(self, key: str | dict, model_name: str, **kwargs):
self.model_name = model_name
def parse_pdf(self, filepath: str, binary=None, **kwargs) -> tuple[Any, Any]:
raise NotImplementedError("Please implement parse_pdf!")
class MinerUOcrModel(Base, MinerUParser):
_FACTORY_NAME = "MinerU"
def __init__(self, key: str | dict, model_name: str, **kwargs):
Base.__init__(self, key, model_name, **kwargs)
raw_config = {}
if key:
try:
raw_config = json.loads(key)
except Exception:
raw_config = {}
# nested {"api_key": {...}} from UI
# flat {"MINERU_*": "..."} payload auto-provisioned from env vars
config = raw_config.get("api_key", raw_config)
if not isinstance(config, dict):
config = {}
def _resolve_config(key: str, env_key: str, default=""):
# lower-case keys (UI), upper-case MINERU_* (env auto-provision), env vars
return config.get(key, config.get(env_key, os.environ.get(env_key, default)))
self.mineru_api = _resolve_config("mineru_apiserver", "MINERU_APISERVER", "")
self.mineru_output_dir = _resolve_config("mineru_output_dir", "MINERU_OUTPUT_DIR", "")
self.mineru_backend = _resolve_config("mineru_backend", "MINERU_BACKEND", "pipeline")
self.mineru_server_url = _resolve_config("mineru_server_url", "MINERU_SERVER_URL", "")
self.mineru_delete_output = bool(int(_resolve_config("mineru_delete_output", "MINERU_DELETE_OUTPUT", 1)))
# Redact sensitive config keys before logging
redacted_config = {}
for k, v in config.items():
if any(
sensitive_word in k.lower()
for sensitive_word in ("key", "password", "token", "secret")
):
redacted_config[k] = "[REDACTED]"
else:
redacted_config[k] = v
logging.info(
f"Parsed MinerU config (sensitive fields redacted): {redacted_config}"
)
MinerUParser.__init__(self, mineru_api=self.mineru_api, mineru_server_url=self.mineru_server_url)
def check_available(self, backend: Optional[str] = None, server_url: Optional[str] = None) -> tuple[bool, str]:
backend = backend or self.mineru_backend
server_url = server_url or self.mineru_server_url
return self.check_installation(backend=backend, server_url=server_url)
def parse_pdf(self, filepath: str, binary=None, callback=None, parse_method: str = "raw", **kwargs):
ok, reason = self.check_available()
if not ok:
raise RuntimeError(f"MinerU server not accessible: {reason}")
sections, tables = MinerUParser.parse_pdf(
self,
filepath=filepath,
binary=binary,
callback=callback,
output_dir=self.mineru_output_dir,
backend=self.mineru_backend,
server_url=self.mineru_server_url,
delete_output=self.mineru_delete_output,
parse_method=parse_method,
Feature/mineru improvements (#11938) 我已在下面的评论中用中文重复说明。 ### What problem does this PR solve? ## Summary This PR enhances the MinerU document parser with additional configuration options, giving users more control over PDF parsing behavior and improving support for multilingual documents. ## Changes ### Backend (`deepdoc/parser/mineru_parser.py`) - Added configurable parsing options: - **Parse Method**: `auto`, `txt`, or `ocr` — allows users to choose the extraction strategy - **Formula Recognition**: Toggle for enabling/disabling formula extraction (useful to disable for Cyrillic documents where it may cause issues) - **Table Recognition**: Toggle for enabling/disabling table extraction - Added language code mapping (`LANGUAGE_TO_MINERU_MAP`) to translate RAGFlow language settings to MinerU-compatible language codes for better OCR accuracy - Improved parser configuration handling to pass these options through the processing pipeline ### Frontend (`web/`) - Created new `MinerUOptionsFormField` component that conditionally renders when MinerU is selected as the layout recognition engine - Added UI controls for: - Parse method selection (dropdown) - Formula recognition toggle (switch) - Table recognition toggle (switch) - Added i18n translations for English and Chinese - Integrated the options into both the dataset creation dialog and dataset settings page ### Integration - Updated `rag/app/naive.py` to forward MinerU options to the parser - Updated task service to handle the new configuration parameters ## Why MinerU is a powerful document parser, but the default settings don't work well for all document types. This PR allows users to: 1. Choose the best parsing method for their documents 2. Disable formula recognition for Cyrillic/non-Latin scripts where it causes issues 3. Control table extraction based on document needs 4. Benefit from automatic language detection for better OCR results ## Testing - [x] Tested MinerU parsing with different parse methods - [x] Verified UI renders correctly when MinerU is selected/deselected - [x] Confirmed settings persist correctly in dataset configuration ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [x] Refactoring - [ ] Performance Improvement - [ ] Other (please describe): --------- Co-authored-by: user210 <user210@rt> Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-12-16 07:15:25 +02:00
**kwargs
)
return sections, tables