部署指南

工程公司RAG部署指南.md

@@ -0,0 +1,320 @@
+# 工程公司RAG部署指南
+
+## mineru部署：
+
+conda create -n mineru python=3.10
+conda activate mineru
+pip install uv
+uv pip install mineru[all]
+
+设置国内路径：export MINERU_MODEL_SOURCE=modelscope
+启动并自动下载模型：mineru-vllm-server --port 9999
+
+如需使用其它端口，请修改./rag/document_load/pdf_load.py中server_url的默认值
+
+
+
+
+
+## RAG虚拟环境安装
+
+conda create -n app python=3.11
+conda activate app
+pip install -r requirements.txt
+
+torch单独安装：pip install torch==2.8.0 torchvision==0.19.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu121
+
+保存下面内容为requirements.txt文件
+accelerate==1.10.1
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.18
+aiosignal==1.3.2
+aiosqlite==0.21.0
+albucore==0.0.23
+albumentations==2.0.5
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.9.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+astor==0.8.1
+attrs==25.3.0
+beautifulsoup4==4.14.2
+blake3==1.0.8
+boto3==1.38.1
+botocore==1.38.1
+Brotli==1.1.0
+cachetools==6.2.1
+cbor2==5.7.0
+certifi==2025.1.31
+cffi==1.17.1
+chardet==5.2.0
+charset-normalizer==3.4.1
+click==8.2.0
+cloudpickle==3.1.1
+colorama==0.4.6
+coloredlogs==15.0.1
+colorlog==6.9.0
+compressed-tensors==0.11.0
+contourpy==1.3.2
+Crawl4AI==0.6.3
+cryptography==44.0.2
+cssselect==1.3.0
+cupy-cuda12x==13.6.0
+cycler==0.12.1
+dataclasses-json==0.6.7
+depyf==0.19.0
+dill==0.4.0
+diskcache==5.6.3
+distro==1.9.0
+dnspython==2.8.0
+doclayout_yolo==0.0.4
+edge-tts==7.0.1
+einops==0.8.1
+email-validator==2.3.0
+fake-http-header==0.3.5
+fake-useragent==2.2.0
+fast-langdetect==0.2.5
+fastapi==0.115.12
+fastapi-cli==0.0.13
+fastapi-cloud-cli==0.3.1
+fastrlock==0.8.3
+fasttext-predict==0.9.2.4
+ffmpy==0.6.3
+filelock==3.18.0
+flatbuffers==25.2.10
+fonttools==4.57.0
+frozendict==2.4.6
+frozenlist==1.6.0
+fsspec==2025.3.2
+ftfy==6.3.1
+gguf==0.17.1
+gradio==5.49.1
+gradio_client==1.13.3
+gradio_pdf==0.0.22
+greenlet==3.2.1
+groovy==0.1.2
+grpcio==1.67.1
+h11==0.14.0
+hf-xet==1.1.10
+httpcore==1.0.8
+httptools==0.7.1
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.35.3
+humanfriendly==10.0
+humanize==4.12.3
+idna==3.10
+imageio==2.37.0
+importlib_metadata==8.7.0
+interegular==0.3.3
+Jinja2==3.1.6
+jiter==0.9.0
+jmespath==1.0.1
+joblib==1.4.2
+json_repair==0.52.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+kiwisolver==1.4.8
+langchain==0.3.22
+langchain-community==0.3.18
+langchain-core==0.3.56
+langchain-text-splitters==0.3.8
+langsmith==0.3.34
+lark==1.2.2
+lazy_loader==0.4
+litellm==1.72.0
+llguidance==0.7.30
+llvmlite==0.44.0
+lm-format-enforcer==0.11.3
+loguru==0.7.3
+lxml==5.4.0
+magic-pdf==1.3.10
+magika==0.6.2
+Markdown==3.8
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib==3.10.1
+mdurl==0.1.2
+milvus-lite==2.4.12
+milvus-model==0.2.12
+milvus_cli==1.0.2
+mineru==2.5.4
+mineru_vl_utils==0.1.13
+minio==7.2.15
+mistral_common==1.8.5
+modelscope==1.31.0
+mpmath==1.3.0
+msgpack==1.1.2
+msgspec==0.19.0
+multidict==6.4.3
+mypy_extensions==1.1.0
+mysql-connector-python==9.3.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+ninja==1.13.0
+nltk==3.9.1
+numba==0.61.2
+numpy==1.26.4
+nvidia-cublas-cu12==12.8.4.1
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cuda-runtime-cu12==12.8.90
+nvidia-cudnn-cu12==9.10.2.21
+nvidia-cufft-cu12==11.3.3.83
+nvidia-cufile-cu12==1.13.1.3
+nvidia-curand-cu12==10.3.9.90
+nvidia-cusolver-cu12==11.7.3.90
+nvidia-cusparse-cu12==12.5.8.93
+nvidia-cusparselt-cu12==0.7.1
+nvidia-nccl-cu12==2.27.3
+nvidia-nvjitlink-cu12==12.8.93
+nvidia-nvtx-cu12==12.8.90
+ollama==0.4.8
+omegaconf==2.3.0
+onnxruntime==1.21.1
+openai==1.109.1
+openai-harmony==0.0.4
+opencv-python==4.11.0.86
+opencv-python-headless==4.11.0.86
+orjson==3.10.16
+outlines_core==0.2.11
+packaging==24.2
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post6
+pdfminer.six==20250506
+pdfplumber==0.11.6
+pdftext==0.6.3
+pillow==11.3.0
+playwright==1.52.0
+prometheus-fastapi-instrumentator==7.1.0
+prometheus_client==0.23.1
+propcache==0.3.1
+protobuf==6.30.2
+psutil==7.0.0
+py-cpuinfo==9.0.0
+pybase64==1.4.2
+pyclipper==1.3.0.post6
+pycountry==24.6.1
+pycparser==2.22
+pycryptodome==3.22.0
+pydantic==2.11.10
+pydantic-extra-types==2.10.6
+pydantic-settings==2.9.1
+pydantic_core==2.33.2
+pydub==0.25.1
+pyee==13.0.0
+Pygments==2.19.1
+pymilvus==2.5.4
+PyMuPDF==1.24.14
+pyOpenSSL==25.1.0
+pyparsing==3.2.3
+pypdf==6.1.1
+pypdfium2==4.30.0
+pyperclip==1.9.0
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+python-dotenv==1.1.0
+python-json-logger==4.0.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.1.0
+rank-bm25==0.2.2
+rapid-table==1.0.5
+ray==2.50.1
+redis==5.2.1
+referencing==0.36.2
+regex==2024.11.6
+reportlab==4.4.4
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==14.0.0
+rich-toolkit==0.15.1
+rignore==0.7.1
+robust-downloader==0.0.2
+rpds-py==0.25.1
+ruff==0.14.1
+s3transfer==0.12.0
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-image==0.25.2
+scikit-learn==1.6.1
+scipy==1.15.2
+seaborn==0.13.2
+semantic-version==2.10.0
+sentence-transformers==4.1.0
+sentencepiece==0.2.1
+sentry-sdk==2.42.0
+setproctitle==1.3.7
+shapely==2.1.0
+shellingham==1.5.4
+simsimd==6.2.1
+six==1.17.0
+sniffio==1.3.1
+snowballstemmer==2.2.0
+soundfile==0.13.1
+soupsieve==2.7
+soxr==1.0.0
+SQLAlchemy==2.0.40
+srt==3.5.3
+sse-starlette==2.3.3
+starlette==0.46.2
+stringzilla==3.12.5
+sympy==1.13.3
+tabulate==0.8.9
+tenacity==9.1.2
+tf-playwright-stealth==1.1.2
+thop==0.1.1.post2209072238
+threadpoolctl==3.6.0
+tifffile==2025.10.16
+tiktoken==0.9.0
+tokenizers==0.22.1
+tomlkit==0.13.3
+tqdm==4.67.1
+transformers==4.57.1
+triton==3.4.0
+typer==0.19.2
+typing-inspect==0.9.0
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+tzdata==2025.2
+ujson==5.10.0
+ultralytics==8.3.115
+ultralytics-thop==2.0.14
+urllib3==2.4.0
+uv==0.9.3
+uvicorn==0.34.2
+uvloop==0.22.1
+vllm==0.10.2
+watchfiles==1.1.1
+wcwidth==0.2.13
+websockets==15.0.1
+xformers==0.0.32.post1
+xgrammar==0.1.23
+xxhash==3.5.0
+yarl==1.20.0
+zipp==3.22.0
+zstandard==0.23.0
+
+
+
+
+
+## 其它：
+
+嵌入模型：https://www.modelscope.cn/models/intfloat/multilingual-e5-large-instruct
+重排序模型：https://www.modelscope.cn/models/maidalun/bce-reranker-base_v1
+下载后修改目录下的./rag/load_model.py中的模型路径
+
+修改./config中的相应配置
+
+因为运行环境的不同指定了不同的GPU，可在./rag_server.py顶部指定os.environ["CUDA_VISIBLE_DEVICES"]
+以及./rag/load_model.py中的device = "cuda:1" if torch.cuda.is_available() else "cpu"的cuda:1 为 cuda:x
+
+
+运行rag_server.py 默认6666端口