Files
MinerU/magic-pdf.template.json
T
myhloli 0a468eca6e feat(llm_aided): add title optimization feature
- Implement llm_aided_title function to optimize document titles using LLM
- Update pdf_parse_union_core_v2.py to include title optimization
- Modify ocr_mkcontent.py to use optimized title levels- Add openai SDK dependency in setup.py
2024-12-25 18:03:38 +08:00

43 lines
1.2 KiB
JSON

{
"bucket_info":{
"bucket-name-1":["ak", "sk", "endpoint"],
"bucket-name-2":["ak", "sk", "endpoint"]
},
"models-dir":"/tmp/models",
"layoutreader-model-dir":"/tmp/layoutreader",
"device-mode":"cpu",
"layout-config": {
"model": "layoutlmv3"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true
},
"table-config": {
"model": "rapid_table",
"enable": false,
"max_time": 400
},
"llm-aided-config": {
"formula_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-7b-instruct",
"enable": false
},
"text_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-7b-instruct",
"enable": false
},
"title_aided": {
"api_key": "your_api_key",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen2.5-32b-instruct",
"enable": false
}
},
"config_version": "1.1.0"
}