cohere-python
cohere-python copied to clipboard
cohere-ai
Python Library for Accessing the Cohere API
Currently, if a user inputs the wrong type into a function call, we respond with a generic "wrong type, check https://docs.cohere.ai/{endpoint}-reference" which is provided by the backend. Giving more verbose...
* Duplicate list item * Assertions in tests * Few logic issues cleaned up
**SDK Version (required)** Provide the version you are using. ```console ❯ python Python 3.11.4 (main, Feb 2 2024, 19:01:43) [Clang 14.0.0 (clang-1400.0.29.202)] on darwin Type "help", "copyright", "credits" or "license"...
**Describe the improvement** I am installing `cohere-python` in a docker image. I don't use any AWS service, nevertheless the library still installs the `boto3` dependency that takes around 25 MB...
SDK version: 5.3.0 Hi, I have created fine-tuned classify model from the dashboard. Then, I tried to use it using the Python SDK. Here's a code I wrote: co =...
This PR regenerates code to match the latest API Definition.
![fern-api[bot] avatar](https://avatars.githubusercontent.com/in/244756?v=4 "fern-api[bot] avatar"){kind=avatar}
Allow users to configure `embed_batch_size` or `ThreadPoolExecutor` size when calling `Client.embed`
It looks like batching was added in #437 - thank you for implementing this, it's very helpful. I notice that batching, as defined [here](https://github.com/cohere-ai/cohere-python/blob/main/src/cohere/client.py#L135), depends on a [fixed batch size](https://github.com/cohere-ai/cohere-python/blob/main/src/cohere/config.py#L1)....
In the [fine tuning docs](https://docs.cohere.com/reference/createfinetunedmodel) it mentions: ``` BASE_MODEL OBJECT name string The name of the base model. ``` What are the valid values for the base model? Can this...
