Python SDK for interacting with Okareo Cloud APIs
Project description
Okareo Python SDK
PyPI: https://pypi.org/project/okareo/
Python library for interacting with Okareo Cloud APIs
Documentation
Getting Started, Guides, and API docs
Installation
-
Install the package
pip install okareo
-
Get your API token from https://app.okareo.com/ (Note: You will need to register first.)
-
Go directly to the "2. Create your API Token" on the landing page in above app.
-
Set the environment variable
OKAREO_API_KEY
to your generated API token.
Get Started Example Notebooks
Please see and run this notebook:
https://github.com/okareo-ai/okareo-python-sdk/blob/main/examples/classification_eval.ipynb
See additional examples under:
https://github.com/okareo-ai/okareo-python-sdk/tree/main/examples
Using Okareo LangChain Callbacks Handler
We provide a LangChain callback handler that lets you easily integrate your current workflows with the Okareo platform.
If don't have LangChain dependencies installed in your environment, you can install the base ones (that will help you run the examples) with:
pip install okareo[langchain]
Integrating callbacks into your chain is as easy as importing the SDK in your module add adding the following
from okareo.callbacks import CallbackHandler
...
handler = CallbackHandler(mut_name="my-model", context_token="context-token")
llm = OpenAI(temperature=0.3, callbacks=[handler])
During the LangChain LLM runs we will collect input and output information so you can analyze it further with the Okareo toolkit.
You can also see an usage example in ./examples/langchain_callback_example.py
All rights reserved for Okareo Inc
Project details
Release history Release notifications | RSS feed
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 okareo-0.0.61.tar.gz
.
File metadata
- Download URL: okareo-0.0.61.tar.gz
- Upload date:
- Size: 80.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.14 Linux/6.5.0-1023-azure
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | caff8a1a2b652038ac25bcd3c8f1a90cec4d254f7c4a09ad7f145166a660c3a3 |
|
MD5 | 5a184c14adbb08b2a88d5e1e2b817a6d |
|
BLAKE2b-256 | ec95c439c5a2d9d2dad9e102951477617a83a8b52ad26e5cd7e7397f23807759 |
File details
Details for the file okareo-0.0.61-py3-none-any.whl
.
File metadata
- Download URL: okareo-0.0.61-py3-none-any.whl
- Upload date:
- Size: 189.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.14 Linux/6.5.0-1023-azure
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7a95b7218b0beaacee2120e973aeae27496b555cd39b655ee77aacb6d509c706 |
|
MD5 | 2e96b713f133606df3e02d481113001a |
|
BLAKE2b-256 | 482ae4084791dfd2eec2874f5419010667b20f95fc8e358affd225e5f1b06066 |