Metadata-Version: 2.1
Name: bsrag-langchain
Version: 0.3.8.3
Summary: 
Author: jun.xiang
Author-email: jun.xiang@extremevision.com.cn
Requires-Python: >=3.10,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: argilla (>=1.29.0,<2.0.0) ; python_version < "3.13"
Requires-Dist: bisheng-pyautogen (>=0.3.2,<0.4.0)
Requires-Dist: bisheng-ragas (>=1.0.0,<2.0.0)
Requires-Dist: cohere (>=5.13.12,<6.0.0)
Requires-Dist: colorlog (>=6.9.0,<7.0.0)
Requires-Dist: elasticsearch (>=8.17.1,<9.0.0)
Requires-Dist: filetype (>=1.2.0,<2.0.0)
Requires-Dist: flask (>=3.1.0,<4.0.0)
Requires-Dist: gradio (<=5.0.0)
Requires-Dist: jieba (>=0.42.1,<0.43.0)
Requires-Dist: langchain-community (<0.3.16)
Requires-Dist: langchain-openai (>=0.1.5,<0.2.0)
Requires-Dist: langgraph (>=0.0.50,<0.0.51)
Requires-Dist: llama-index (>=0.9.48,<0.10.0)
Requires-Dist: loguru (>=0.7.1,<0.8.0)
Requires-Dist: matplotlib (>=3.10.0,<4.0.0)
Requires-Dist: minio (>=7.2.15,<8.0.0)
Requires-Dist: openai (>=1.14.3,<2.0.0)
Requires-Dist: opencv-python (>=4.5.5.64,<5.0.0.0)
Requires-Dist: pillow (>=9.5.0,<10.0.0)
Requires-Dist: pydantic (>=2.0,<3.0)
Requires-Dist: pymupdf (>=1.23.8,<2.0.0)
Requires-Dist: pypdfium2 (>=4.30.1,<5.0.0)
Requires-Dist: pypinyin (>=0.53.0,<0.54.0)
Requires-Dist: sentence-transformers (>=3.4.1,<4.0.0)
Requires-Dist: shapely (>=2.0.2,<3.0.0)
Requires-Dist: sympy (==1.13.1)
Requires-Dist: torch (>=2.6.0,<3.0.0)
Requires-Dist: transformers (<=4.47.0)
Requires-Dist: websocket-client (>=1.8.0,<2.0.0)
Requires-Dist: zhipu (>=1.0.1,<2.0.0)
Requires-Dist: zhipuai (>=2.1.5.20250106,<3.0.0.0)
Description-Content-Type: text/markdown

## What is bisheng-langchain?

bisheng-langchain is an open-source langchain extending library built to power building LLM application.
bisheng-langchain provides more components to support Chinese LLMs and and Chinese based token environments for prompt engineering and ICL template.


The project is a sub-module of [bisheng](https://github.com/dataelement/bisheng).


## Key features

- Retrival Enhancement components, like ESIndex, DBIndex, GraphIndex 
- Supporting Open LLMs and embeddings models 
- High performance QAs Chains
- High Semanticly Chinese token processing


## Quick start

### Start with Bisheng Platform.

We provide a open cloud service for easily use. See [free trial](https://bisheng.dataelem.com/).


### Install bisheng-langchain

- Install from pip: `pip install bisheng-langchain`
- [Quick Start Guide](https://m7a7tqsztt.feishu.cn/wiki/CTXNwpqGKiMs5FkKlPJcylfonuD)


## Documentation

For guidance on installation, development, deployment, and administration, 
check out [bisheng-langchain Dev Docs](https://dataelem.feishu.cn/wiki/Xaq8wKQjkiYEHNkXuYLc7JkxnPf). 


## Acknowledgments

bisheng-langchain adopts dependencies from the following:

- Thanks to [langchain](https://github.com/langchain-ai/langchain) for the main framework.

