mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-19 13:23:16 +08:00
1b0cf67a57
* GLM3支持传入提示词 支持传入提示词的Agent ChatGLM3-6B * 软连接处理 1. 有效的软连接处理，参考了 #2125 2. 更新了依赖，现在fschat原生支持GLM3的全功能 * 更新了支持的模型列表和依赖 1. 推荐用户使用GLM3-6B取代2代GLM模型 2. 推荐用户使用性能更强的bge模型 3 推荐使用vllm和torch的最新稳定版本
53 lines
855 B
Plaintext
53 lines
855 B
Plaintext
# API requirements
|
|
|
|
langchain>=0.0.334
|
|
langchain-experimental>=0.0.42
|
|
fschat[model_worker]>=0.2.33
|
|
xformers>=0.0.22.post7
|
|
openai~=0.28.1
|
|
sentence_transformers
|
|
transformers>=4.35.2
|
|
torch==2.1.0
|
|
torchvision
|
|
torchaudio
|
|
fastapi>=0.104
|
|
nltk>=3.8.1
|
|
uvicorn~=0.23.1
|
|
starlette~=0.27.0
|
|
pydantic<2
|
|
unstructured[all-docs]>=0.11.0
|
|
python-magic-bin; sys_platform == 'win32'
|
|
SQLAlchemy==2.0.19
|
|
faiss-cpu
|
|
accelerate>=0.24.1
|
|
spacy
|
|
PyMuPDF
|
|
rapidocr_onnxruntime
|
|
|
|
requests
|
|
pathlib
|
|
pytest
|
|
numexpr
|
|
strsimpy
|
|
markdownify
|
|
tiktoken
|
|
tqdm
|
|
websockets
|
|
numpy~=1.24.4
|
|
pandas~=2.0.3
|
|
einops
|
|
transformers_stream_generator>=0.0.4
|
|
|
|
vllm>=0.2.0; sys_platform == "linux"
|
|
|
|
# online api libs
|
|
zhipuai
|
|
dashscope>=1.10.0 # qwen
|
|
qianfan
|
|
# volcengine>=1.0.106 # fangzhou
|
|
|
|
# uncomment libs if you want to use corresponding vector store
|
|
# pymilvus==2.1.3 # requires milvus==2.1.3
|
|
# psycopg2
|
|
# pgvector
|