Cohere’s LLM models are available for use with the Phidata

​
Authentication

Set your CO_API_KEY environment variable.

export CO_API_KEY=***

​
Example

Use CohereChat with your Assistant:

from phi.assistant import Assistant
from phi.tools.duckduckgo import DuckDuckGo
from phi.llm.cohere import CohereChat

assistant = Assistant(
    llm=CohereChat(model="command-r"),
    tools=[DuckDuckGo()],
    show_tool_calls=True,
)
assistant.print_response("Whats happening in France?", markdown=True)

​
Params

name
str
default: "cohere"

Name of the model.

model
str
default: "command-r"

Cohere model ID.

temperature
float

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.

max_tokens
int

The maximum number of tokens to generate in the chat completion.

top_k
int

The number of highest probability vocabulary tokens to keep for top-k-filtering.

top_p
float

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

frequency_penalty
float

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.

presence_penalty
float

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.

request_params
Dict[str, Any]

Additional parameters for the Cohere API request.

add_chat_history
bool
default: "False"

Add chat history to the Cohere messages instead of using the conversation_id.

api_key
str

Cohere API Key.

client_params
Dict[str, Any]

Additional keyword arguments used when creating the CohereClient().

cohere_client
CohereClient

Provide your own CohereClient to use.

Was this page helpful?

Anthropic ClaudeIntroduction