?Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 與 ChatGLM 等語言模型的本地知識(shí)庫問答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain。
? ? ? ? 開源網(wǎng)址：https://github.com/chatchat-space/Langchain-Chatchat
?? ? ? ? 因?yàn)檫@是自己畢設(shè)項(xiàng)目所需，利用虛擬機(jī)實(shí)驗(yàn)一下是否能成功部署。項(xiàng)目參考：Langchain-Chatchat-win10本地安裝部署成功筆記（CPU）_file "d:\ai\virtual-digital-human\langchain-chatch-CSDN博客
其中有些是自己遇到的坑也會(huì)在這里說一下。
一、實(shí)驗(yàn)環(huán)境
可以查看目前使用的系統(tǒng)版本信息。
cat /proc/versionLinux version 5.15.133.1-microsoft-standard-WSL2 (root@1c602f52c2e4) (gcc (GCC) 11.2.0, GNU ld (GNU Binutils) 2.37) #1 SMP Thu Oct 5 21:02:42 UTC 2023如果安裝有顯卡驅(qū)動(dòng)，可以使用下面的代碼來查看顯卡信息。
nvidia-smi #查看顯卡信息
Sat Mar 9 19:31:33 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.40.06 Driver Version: 551.23 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3090 On | 00000000:AF:00.0 Off | N/A |
| 32% 25C P8 6W / 350W | 134MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA GeForce RTX 3090 On | 00000000:D8:00.0 Off | N/A |
| 32% 24C P8 11W / 350W | 144MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 227 G /Xwayland N/A |
| 1 N/A N/A 227 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
二、安裝步驟
1、安裝 Anaconda軟件，用于管理python虛擬環(huán)境
自己使用的是清華鏡像：Index of /anaconda/archive/ | 清華大學(xué)開源軟件鏡像站 | Tsinghua Open Source Mirror
wget下載命令如下：
?wget -c 'https://repo.anaconda.com/archive/Anaconda3-2023.09-0-Linux-x86_64.sh' -P <下載到的文件的位置>?2、創(chuàng)建python運(yùn)行虛擬環(huán)境
?
可以通過?conda info --envs 檢查環(huán)境是否創(chuàng)建完成。
# conda environments:
#
base /home/david/anaconda3
NAD /home/david/anaconda3/envs/NAD
chat /home/david/anaconda3/envs/chat
chat_demo /home/david/anaconda3/envs/chat_demo
進(jìn)入已經(jīng)創(chuàng)建好的虛擬環(huán)境：conda activate 環(huán)境名稱
$ conda activate chat_demo
(chat_demo) $ python --version
Python 3.11.7
3、安裝pytorch
~$ pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 -i https://pypi.tuna.tsinghua.edu.cn/simpleLooking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting torch
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/2c/df/5810707da6f2fd4be57f0cc417987c0fa16a2eecf0b1b71f82ea555dc619/torch-2.2.1-cp311-cp311-manylinux1_x86_64.whl (755.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 755.6/755.6 MB 2.4 MB/s eta 0:00:00
Collecting torchvision
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/3a/49/12fc5188602c68a789a0fdaee63d176a71ad5c1e34d25aeb8554abe46089/torchvision-0.17.1-cp311-cp311-manylinux1_x86_64.whl (6.9 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.9/6.9 MB 6.6 MB/s eta 0:00:00
Collecting torchaudio
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/a6/57/ccebdda4db80e384166c70d8645fa998637051b3b19aca1fd8de80602afb/torchaudio-2.2.1-cp311-cp311-manylinux1_x86_64.whl (3.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.3/3.3 MB 6.7 MB/s eta 0:00:00
Collecting filelock (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/81/54/84d42a0bee35edba99dee7b59a8d4970eccdd44b99fe728ed912106fc781/filelock-3.13.1-py3-none-any.whl (11 kB)
Collecting typing-extensions>=4.8.0 (from torch)
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/f9/de/dc04a3ea60b22624b51c703a84bbe0184abcd1d0b9bc8074b5d6b7ab90bb/typing_extensions-4.10.0-py3-none-any.whl (33 kB)
Collecting sympy (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d2/05/e6600db80270777c4a64238a98d442f0fd07cc8915be2a1c16da7f2b9e74/sympy-1.12-py3-none-any.whl (5.7 MB)
Collecting networkx (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d5/f0/8fbc882ca80cf077f1b246c0e3c3465f7f415439bdea6b899f6b19f61f70/networkx-3.2.1-py3-none-any.whl (1.6 MB)
Collecting jinja2 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/30/6d/6de6be2d02603ab56e72997708809e8a5b0fbfee080735109b40a3564843/Jinja2-3.1.3-py3-none-any.whl (133 kB)
Collecting fsspec (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/ad/30/2281c062222dc39328843bd1ddd30ff3005ef8e30b2fd09c4d2792766061/fsspec-2024.2.0-py3-none-any.whl (170 kB)
Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b6/9f/c64c03f49d6fbc56196664d05dba14e3a561038a81a638eeb47f4d4cfd48/nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)
Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/eb/d5/c68b1d2cdfcc59e72e8a5949a37ddb22ae6cade80cd4a57a84d4c8b55472/nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)
Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/7e/00/6b218edd739ecfc60524e585ba8e6b00554dd908de2c9c66c1af3e44e18d/nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)
Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/ff/74/a2e2be7fb83aaedec84f391f082cf765dfb635e7caa9b49065f73e4835d8/nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)
Collecting nvidia-cublas-cu12==12.1.3.1 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/37/6d/121efd7382d5b0284239f4ab1fc1590d86d34ed4a4a2fdb13b30ca8e5740/nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)
Collecting nvidia-cufft-cu12==11.0.2.54 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/86/94/eb540db023ce1d162e7bea9f8f5aa781d57c65aed513c33ee9a5123ead4d/nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)
Collecting nvidia-curand-cu12==10.3.2.106 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/44/31/4890b1c9abc496303412947fc7dcea3d14861720642b49e8ceed89636705/nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)
Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)
Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)
Collecting nvidia-nccl-cu12==2.19.3 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/38/00/d0d4e48aef772ad5aebcf70b73028f88db6e5640b36c38e90445b7a57c45/nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)
Collecting nvidia-nvtx-cu12==12.1.105 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/da/d3/8057f0587683ed2fcd4dbfbdfdfa807b9160b809976099d36b8f60d08f03/nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)
Collecting triton==2.2.0 (from torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/bd/ac/3974caaa459bf2c3a244a84be8d17561f631f7d42af370fc311defeca2fb/triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)
Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch)
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/58/d1/d1c80553f9d5d07b6072bc132607d75a0ef3600e28e1890e11c0f55d7346/nvidia_nvjitlink_cu12-12.4.99-py3-none-manylinux2014_x86_64.whl (21.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 21.1/21.1 MB 6.6 MB/s eta 0:00:00
Collecting numpy (from torchvision)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/3a/d0/edc009c27b406c4f9cbc79274d6e46d634d139075492ad055e3d68445925/numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.3 MB)
Collecting pillow!=8.3.*,>=5.3.0 (from torchvision)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/66/9c/2e1877630eb298bbfd23f90deeec0a3f682a4163d5ca9f178937de57346c/pillow-10.2.0-cp311-cp311-manylinux_2_28_x86_64.whl (4.5 MB)
Collecting MarkupSafe>=2.0 (from jinja2->torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/97/18/c30da5e7a0e7f4603abfc6780574131221d9148f323752c2755d48abad30/MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (28 kB)
Collecting mpmath>=0.19 (from sympy->torch)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl (536 kB)
Installing collected packages: mpmath, typing-extensions, sympy, pillow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, networkx, MarkupSafe, fsspec, filelock, triton, nvidia-cusparse-cu12, nvidia-cudnn-cu12, jinja2, nvidia-cusolver-cu12, torch, torchvision, torchaudio
Successfully installed MarkupSafe-2.1.5 filelock-3.13.1 fsspec-2024.2.0 jinja2-3.1.3 mpmath-1.3.0 networkx-3.2.1 numpy-1.26.4 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.99 nvidia-nvtx-cu12-12.1.105 pillow-10.2.0 sympy-1.12 torch-2.2.1 torchaudio-2.2.1 torchvision-0.17.1 triton-2.2.0 typing-extensions-4.10.0
驗(yàn)證是否安裝成功：
~$ python
Python 3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> x = torch.rand(5,3)
>>> print(x)
tensor([[0.8278, 0.8746, 0.1025],
[0.7528, 0.6855, 0.7386],
[0.6271, 0.1371, 0.1849],
[0.4098, 0.3203, 0.7615],
[0.5088, 0.7645, 0.8044]])
4、拉取Langchain-Chatchat源代碼
?有兩種方式獲取源代碼，一種是獲取最新代碼，一種是獲取指定版本的源代碼。
# 拉取倉庫
git clone https://github.com/chatchat-space/Langchain-Chatchat.git# 指定版本獲取代碼
git clone -b v0.2.6 https://github.com/chatchat-space/Langchain-Chatchat.git在拉取源代碼之前先安裝 git
5、安裝依賴包
cd Langchain-Chatchat
pip3 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
Found existing installation: triton 2.2.0
Uninstalling triton-2.2.0:
Successfully uninstalled triton-2.2.0
Attempting uninstall: pillow
Found existing installation: pillow 10.2.0
Uninstalling pillow-10.2.0:
Successfully uninstalled pillow-10.2.0
Attempting uninstall: nvidia-nccl-cu12
Found existing installation: nvidia-nccl-cu12 2.19.3
Uninstalling nvidia-nccl-cu12-2.19.3:
Successfully uninstalled nvidia-nccl-cu12-2.19.3
Attempting uninstall: numpy
Found existing installation: numpy 1.26.4
Uninstalling numpy-1.26.4:
Successfully uninstalled numpy-1.26.4
Attempting uninstall: torch
Found existing installation: torch 2.2.1
Uninstalling torch-2.2.1:
Successfully uninstalled torch-2.2.1
Attempting uninstall: torchvision
Found existing installation: torchvision 0.17.1
Uninstalling torchvision-0.17.1:
Successfully uninstalled torchvision-0.17.1
Attempting uninstall: torchaudio
Found existing installation: torchaudio 2.2.1
Uninstalling torchaudio-2.2.1:
Successfully uninstalled torchaudio-2.2.1
Successfully installed PyMuPDF-1.23.16 PyMuPDFb-1.23.9 SQLAlchemy-2.0.25 Shapely-2.0.3 XlsxWriter-3.2.0 accelerate-0.24.1 aiofiles-23.2.1 aiohttp-3.9.3 aioprometheus-23.12.0 aiosignal-1.3.1 altair-5.2.0 antlr4-python3-runtime-4.9.3 anyio-4.3.0 arxiv-2.1.0 attrs-23.2.0 backoff-2.2.1 beautifulsoup4-4.12.3 blinker-1.7.0 blis-0.7.11 brotli-1.1.0 cachetools-5.3.3 catalogue-2.0.10 certifi-2024.2.2 cffi-1.16.0 chardet-5.2.0 charset-normalizer-3.3.2 click-8.1.7 cloudpathlib-0.16.0 coloredlogs-15.0.1 confection-0.1.4 contourpy-1.2.0 cryptography-42.0.5 cycler-0.12.1 cymem-2.0.8 dataclasses-json-0.6.4 deepdiff-6.7.1 deprecated-1.2.14 deprecation-2.1.0 distro-1.9.0 duckduckgo-search-3.9.9 effdet-0.4.1 einops-0.7.0 emoji-2.10.1 et-xmlfile-1.1.0 faiss-cpu-1.7.4 fastapi-0.109.0 feedparser-6.0.10 filetype-1.2.0 flatbuffers-24.3.7 fonttools-4.49.0 frozenlist-1.4.1 fschat-0.2.35 gitdb-4.0.11 gitpython-3.1.42 greenlet-3.0.3 h11-0.14.0 h2-4.1.0 hpack-4.0.0 httpcore-1.0.4 httptools-0.6.1 httpx-0.26.0 httpx_sse-0.4.0 huggingface-hub-0.21.4 humanfriendly-10.0 hyperframe-6.0.1 idna-3.6 importlib-metadata-7.0.2 iniconfig-2.0.0 iopath-0.1.10 joblib-1.3.2 jsonpatch-1.33 jsonpath-python-1.0.6 jsonpointer-2.4 jsonschema-4.21.1 jsonschema-specifications-2023.12.1 kiwisolver-1.4.5 langchain-0.0.354 langchain-community-0.0.20 langchain-core-0.1.23 langchain-experimental-0.0.47 langcodes-3.3.0 langdetect-1.0.9 langsmith-0.0.87 layoutparser-0.3.4 llama-index-0.9.35 lxml-5.1.0 markdown-3.5.2 markdown-it-py-3.0.0 markdown2-2.4.13 markdownify-0.11.6 marshmallow-3.21.1 matplotlib-3.8.3 mdurl-0.1.2 metaphor-python-0.1.23 msg-parser-1.2.0 msgpack-1.0.8 multidict-6.0.5 murmurhash-1.0.10 mypy-extensions-1.0.0 nest-asyncio-1.6.0 nh3-0.2.15 ninja-1.11.1.1 nltk-3.8.1 numexpr-2.8.6 numpy-1.24.4 nvidia-nccl-cu12-2.18.1 olefile-0.47 omegaconf-2.3.0 onnx-1.15.0 onnxruntime-1.15.1 openai-1.9.0 opencv-python-4.9.0.80 openpyxl-3.1.2 ordered-set-4.1.0 orjson-3.9.15 packaging-23.2 pandas-2.0.3 pathlib-1.0.1 pdf2image-1.17.0 pdfminer.six-20231228 pdfplumber-0.11.0 pikepdf-8.4.1 pillow-9.5.0 pillow-heif-0.15.0 pluggy-1.4.0 portalocker-2.8.2 preshed-3.0.9 prompt-toolkit-3.0.43 protobuf-4.25.3 psutil-5.9.8 pyarrow-15.0.1 pyclipper-1.3.0.post5 pycocotools-2.0.7 pycparser-2.21 pydantic-1.10.13 pydeck-0.8.1b0 pygments-2.17.2 pyjwt-2.8.0 pypandoc-1.13 pyparsing-3.1.2 pypdf-4.1.0 pypdfium2-4.27.0 pytesseract-0.3.10 pytest-7.4.3 python-dateutil-2.9.0.post0 python-decouple-3.8 python-docx-1.1.0 python-dotenv-1.0.1 python-iso639-2024.2.7 python-magic-0.4.27 python-multipart-0.0.9 python-pptx-0.6.23 pytz-2024.1 pyyaml-6.0.1 quantile-python-1.1 rapidfuzz-3.6.2 rapidocr_onnxruntime-1.3.8 ray-2.9.3 referencing-0.33.0 regex-2023.12.25 requests-2.31.0 rich-13.7.1 rpds-py-0.18.0 safetensors-0.4.2 scikit-learn-1.4.1.post1 scipy-1.12.0 sentence_transformers-2.2.2 sentencepiece-0.2.0 sgmllib3k-1.0.0 shortuuid-1.0.12 simplejson-3.19.2 six-1.16.0 smart-open-6.4.0 smmap-5.0.1 sniffio-1.3.1 socksio-1.0.0 soupsieve-2.5 spacy-3.7.2 spacy-legacy-3.0.12 spacy-loggers-1.0.5 srsly-2.4.8 sse_starlette-1.8.2 starlette-0.35.0 streamlit-1.30.0 streamlit-aggrid-0.3.4.post3 streamlit-antd-components-0.3.1 streamlit-chatbox-1.1.11 streamlit-feedback-0.1.3 streamlit-modal-0.1.0 streamlit-option-menu-0.3.12 strsimpy-0.2.1 svgwrite-1.4.3 tabulate-0.9.0 tenacity-8.2.3 thinc-8.2.3 threadpoolctl-3.3.0 tiktoken-0.5.2 timm-0.9.16 tokenizers-0.15.2 toml-0.10.2 toolz-0.12.1 torch-2.1.2 torchaudio-2.1.2 torchvision-0.16.2 tornado-6.4 tqdm-4.66.1 transformers-4.37.2 transformers_stream_generator-0.0.4 triton-2.1.0 typer-0.9.0 typing-inspect-0.9.0 tzdata-2024.1 tzlocal-5.2 unstructured-0.12.5 unstructured-client-0.21.1 unstructured-inference-0.7.23 unstructured.pytesseract-0.3.12 urllib3-2.2.1 uvicorn-0.28.0 uvloop-0.19.0 validators-0.22.0 vllm-0.2.7 wasabi-1.1.2 watchdog-3.0.0 watchfiles-0.21.0 wavedrom-2.0.3.post3 wcwidth-0.2.13 weasel-0.3.4 websockets-12.0 wrapt-1.16.0 xformers-0.0.23.post1 xlrd-2.0.1 yarl-1.9.4 youtube-search-2.1.2 zipp-3.17.0
6、下載模型
下載兩個(gè)模型：M3e-base 內(nèi)置模型和 chatglm3-6b 模型。
git lfs install
git clone https://gitee.com/hf-models/m3e-base.git
git clone https://gitee.com/hf-models/chatglm3-6b.git如果需要上 huggingface.co 獲取模型可能需要科學(xué)上網(wǎng)工具。
7、修改配置文件
批量修改配置文件名
批量復(fù)制configs目錄下所有的配置文件，去掉example后綴：
# cd Langchain-Chatchat
# 批量復(fù)制configs目錄下所有配置文件，去掉example
python copy_config_example.py修改model_config.py文件
修改m3e-base的模型本地路徑(注意是雙反斜杠"\\")：
修改server_config.py
0.2.6之前版本，需要修改0.0.0.0為127.0.0.1不然會(huì)報(bào)錯(cuò)。
# 各服務(wù)器默認(rèn)綁定host。如改為"0.0.0.0"需要修改下方所有XX_SERVER的host
DEFAULT_BIND_HOST = "127.0.0.1" if sys.platform != "win32" else "127.0.0.1"8、初始化數(shù)據(jù)庫
python init_database.py --recreate-vs
配置里面模型的運(yùn)行設(shè)置設(shè)置為 auto （還是建議用顯卡跑）
9、一鍵啟動(dòng)項(xiàng)目
運(yùn)行：
python startup.py -a==============================Langchain-Chatchat Configuration==============================
操作系統(tǒng)：Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35.
python版本：3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0]
項(xiàng)目版本：v0.2.10
langchain版本：0.0.354. fastchat版本：0.2.35
當(dāng)前使用的分詞器：ChineseRecursiveTextSplitter
當(dāng)前啟動(dòng)的LLM模型：['chatglm3-6b'] @ cuda
{'device': 'cuda',
'host': '127.0.0.1',
'infer_turbo': False,
'model_path': 'model/chatglm3-6b',
'model_path_exists': True,
'port': 20002}
當(dāng)前Embbedings模型： m3e-base @ cuda
==============================Langchain-Chatchat Configuration==============================
2024-03-09 20:18:03,837 - startup.py[line:655] - INFO: 正在啟動(dòng)服務(wù)：
2024-03-09 20:18:03,838 - startup.py[line:656] - INFO: 如需查看 llm_api 日志，請(qǐng)前往 /home/david/20240207/Langchain-Chatchat/logs
/home/david/anaconda3/envs/chat_demo/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: 模型啟動(dòng)功能將于 Langchain-Chatchat 0.3.x重寫,支持更多模式和加速啟動(dòng)，0.2.x中相關(guān)功能將廢棄
warn_deprecated(
2024-03-09 20:18:10 | ERROR | stderr | INFO: Started server process [329625]
2024-03-09 20:18:10 | ERROR | stderr | INFO: Waiting for application startup.
2024-03-09 20:18:10 | ERROR | stderr | INFO: Application startup complete.
2024-03-09 20:18:10 | ERROR | stderr | INFO: Uvicorn running on http://127.0.0.1:20000 (Press CTRL+C to quit)
2024-03-09 20:18:10 | INFO | model_worker | Loading the model ['chatglm3-6b'] on worker 7b784767 ...
Loading checkpoint shards: 0%| | 0/7 [00:00<?, ?it/s]
2024-03-09 20:18:11 | ERROR | stderr | /home/david/anaconda3/envs/chat_demo/lib/python3.11/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
2024-03-09 20:18:11 | ERROR | stderr | return self.fget.__get__(instance, owner)()
Loading checkpoint shards: 14%|████████████▍ | 1/7 [00:03<00:21, 3.62s/it]
Loading checkpoint shards: 29%|████████████████████████▊ | 2/7 [00:07<00:18, 3.74s/it]
Loading checkpoint shards: 43%|█████████████████████████████████████▎ | 3/7 [00:08<00:10, 2.74s/it]
Loading checkpoint shards: 57%|█████████████████████████████████████████████████▋ | 4/7 [00:10<00:06, 2.09s/it]
Loading checkpoint shards: 71%|██████████████████████████████████████████████████████████████▏ | 5/7 [00:11<00:03, 1.76s/it]
Loading checkpoint shards: 86%|██████████████████████████████████████████████████████████████████████████▌ | 6/7 [00:12<00:01, 1.63s/it]
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:13<00:00, 1.31s/it]
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:13<00:00, 1.90s/it]
2024-03-09 20:18:24 | ERROR | stderr |
2024-03-09 20:18:30 | INFO | model_worker | Register to controller
INFO: Started server process [329963]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:7861 (Press CTRL+C to quit)
==============================Langchain-Chatchat Configuration==============================
操作系統(tǒng)：Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35.
python版本：3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0]
項(xiàng)目版本：v0.2.10
langchain版本：0.0.354. fastchat版本：0.2.35
當(dāng)前使用的分詞器：ChineseRecursiveTextSplitter
當(dāng)前啟動(dòng)的LLM模型：['chatglm3-6b'] @ cuda
{'device': 'cuda',
'host': '127.0.0.1',
'infer_turbo': False,
'model_path': 'model/chatglm3-6b',
'model_path_exists': True,
'port': 20002}
當(dāng)前Embbedings模型： m3e-base @ cuda
服務(wù)端運(yùn)行信息：
OpenAI API Server: http://127.0.0.1:20000/v1
Chatchat API Server: http://127.0.0.1:7861
Chatchat WEBUI Server: http://127.0.0.1:8501
==============================Langchain-Chatchat Configuration==============================
You can now view your Streamlit app in your browser.
URL: http://127.0.0.1:8501
配置成功！
常用命令：
sudo usermod -a -G sudo username? ? ? ? 為用戶添加sudo權(quán)限
取消代理
git config --global --unset http.proxy
git config --global --unset https.proxy
?10、本地瀏覽器打開Linux遠(yuǎn)程服務(wù)器網(wǎng)頁
在需要進(jìn)行端口轉(zhuǎn)發(fā)：
ssh -L 8501:127.0.0.1:8501 llama@172.17.135.6 -N
在瀏覽器（推薦使用Firefox）中打開?http://localhost:8501/即可進(jìn)入webUI。
文章來源：http://www.zghlxwxcb.cn/news/detail-844561.html
踩坑
1、使用 chatglm2-6b-int4 量化模型?，啟動(dòng)項(xiàng)目報(bào)錯(cuò)：
AttributeError: 'NoneType' object has no attribute 'int4WeightExtractionHalf'解決辦法：文章來源地址http://www.zghlxwxcb.cn/news/detail-844561.html
pip install cpm_kernels到了這里，關(guān)于Langchain-Chatchat-Ubuntu服務(wù)器本地安裝部署筆記的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
