wxai-langchain enables the use of IBM watsonx.ai in LangChain projects. This is not supported by IBM.
Project description
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
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.
pip install -e '.[dev]'
Examples:
- Create a new
.env
fileexamples/0.0.4
with contents
API_KEY=
PROJECT_ID=
- Run the examples with
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,
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.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file wxai-langchain-0.0.4.tar.gz
.
File metadata
- Download URL: wxai-langchain-0.0.4.tar.gz
- Upload date:
- Size: 11.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.9.6 readme-renderer/40.0 requests/2.28.1 requests-toolbelt/1.0.0 urllib3/1.26.16 tqdm/4.65.0 importlib-metadata/6.1.0 keyring/24.2.0 rfc3986/1.5.0 colorama/0.4.6 CPython/3.9.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2539b541c477371cc74179bc045b399af812cc3a89f6259b7dd2e72c49d4e22e |
|
MD5 | e4155da854d2b989fc78f7f6ece144e9 |
|
BLAKE2b-256 | a8fcba1fd629340f23262ddbb4c2c74cde465e5529806e8369d8253dd16616e6 |
File details
Details for the file wxai_langchain-0.0.4-py3-none-any.whl
.
File metadata
- Download URL: wxai_langchain-0.0.4-py3-none-any.whl
- Upload date:
- Size: 8.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.8.0 pkginfo/1.9.6 readme-renderer/40.0 requests/2.28.1 requests-toolbelt/1.0.0 urllib3/1.26.16 tqdm/4.65.0 importlib-metadata/6.1.0 keyring/24.2.0 rfc3986/1.5.0 colorama/0.4.6 CPython/3.9.13
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5ecce8187cfc9c172f0b377d8f661780ad6c8f5da2367a6d0524e47be72f0124 |
|
MD5 | 67e5696fb83574cee1c7115a322e4835 |
|
BLAKE2b-256 | 938aa44759fb3fa9d29f09b49dd4fbbde116f1c2a163e0e637f654b805753f0d |