Cohere Provider

Use Cohere's Command models through SimplerLLM's unified interface.

Overview

SimplerLLM provides seamless integration with Cohere's API, allowing you to use their Command models with just a few lines of code.

Using Cohere Models

Model Examples

# Command R+ (example)
model_name="command-r-plus"

# Command R (example)
model_name="command-r"

# You can use any model from Cohere's catalog

Finding Available Models

Visit Cohere's official model documentation for the complete list.

Setup and Authentication

Get Your API Key

1. Go to Cohere Dashboard

2. Sign up or log in

3. Create a new API key

Configure Environment Variables

# .env file
COHERE_API_KEY=your-cohere-api-key-here

Basic Usage

from SimplerLLM.language.llm import LLM, LLMProvider

# Create Cohere LLM instance
llm = LLM.create(
    provider=LLMProvider.COHERE,
    model_name="command-r-plus"
)

# Generate a response
response = llm.generate_response(
    prompt="Explain machine learning in simple terms"
)

print(response)

With Custom Parameters

llm = LLM.create(
    provider=LLMProvider.COHERE,
    model_name="command-r-plus",  # Use any Cohere model name
    temperature=0.7,
    max_tokens=1000
)

response = llm.generate_response(
    prompt="Write a creative short story"
)

print(response)

Advanced Features

Structured JSON Output

from pydantic import BaseModel, Field
from SimplerLLM.language.llm_addons import generate_pydantic_json_model

class Summary(BaseModel):
    title: str = Field(description="Title")
    points: list[str] = Field(description="Key points")

llm = LLM.create(provider=LLMProvider.COHERE, model_name="command-r-plus")

result = generate_pydantic_json_model(
    llm_instance=llm,
    prompt="Summarize the benefits of cloud computing",
    model_class=Summary
)

print(f"Title: {result.title}")