Cohere
Leverage Cohere’s powerful command models and more.
Authentication
Set your CO_API_KEY environment variable.
Example
Use CohereChat with your Assistant:
Params
Name of the model.
Cohere model ID.
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
The maximum number of tokens to generate in the chat completion.
The number of highest probability vocabulary tokens to keep for top-k-filtering.
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.
Additional parameters for the Cohere API request.
Add chat history to the Cohere messages instead of using the conversation_id.
Cohere API Key.
Additional keyword arguments used when creating the CohereClient().
Provide your own CohereClient to use.
Was this page helpful?