Metadata-Version: 2.1
Name: wxai-langchain
Version: 0.0.4
Summary: wxai-langchain enables the use of IBM watsonx.ai in LangChain projects. This is not supported by IBM.
Author-email: Cong Nguyen <cong.nguyen@au1.ibm.com>
Project-URL: source, https://github.com/rampadc/wxai-langchain
Project-URL: Homepage, https://github.com/rampadc/wxai-langchain
Keywords: watsonx.ai,wxai,langchain
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: urllib3<2
Requires-Dist: requests>=2.31.0
Requires-Dist: pydantic<=1.10.10
Requires-Dist: langchain>=0.0.200
Requires-Dist: ibm_cloud_sdk_core>=3.16.7
Requires-Dist: aiohttp>=3.8.4
Requires-Dist: ibm-watson-machine-learning>=1.0.311
Provides-Extra: dev
Requires-Dist: python-dotenv>=1.0.0; extra == "dev"
Requires-Dist: datasets==2.11.0; extra == "dev"

# IBM watsonx.ai LangChain interface

This is a Python library to add a LangChain interface to IBM watsonx.ai. This is not an IBM project and is not supported by IBM.

GitHub repo: https://github.com/rampadc/wxai-langchain

```shell
pip install wxai-langchain==0.0.4
```

## v0.0.4

Version 0.0.4 is a breaking change and uses ibm-watson-machine-learning SDK to use the syntatic sugars that comes with the SDK.

```shell
pip install -e '.[dev]'
```

Examples:

1. Create a new `.env` file `examples/0.0.4` with contents

```
API_KEY=
PROJECT_ID=
```

2. Run the examples with 

```shell
python examples/0.0.4/<example-file>.py
```

## v0.0.2

Version 0.0.2 does not use ibm-watson-machine-learning SDK.

To install,

```shell
pip install wxai-langchain==0.0.2
```

To use, see the examples folder. This LangChain interface is not compatible with IBM's GenAI GenerateParams schema object.
Always use a JSON for the model's parameters as shown in the examples.
