> ## Documentation Index
> Fetch the complete documentation index at: https://docs.enconvo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Cohere

> Configure Cohere models in EnConvo

## Overview

Cohere builds enterprise-focused language models optimized for search, retrieval-augmented generation (RAG), and text understanding. Their Command R family excels at grounded generation with citations, making them ideal for knowledge-intensive workflows.

## Supported Models

| Model          | Description            | Best For                        |
| -------------- | ---------------------- | ------------------------------- |
| **Command R+** | Most capable, with RAG | Complex reasoning, research     |
| **Command R**  | Balanced, with RAG     | General tasks, grounded answers |
| **Embed**      | Text embedding model   | Semantic search, similarity     |

## Setup

<Steps>
  <Step title="Get API Key">
    1. Go to [Cohere Dashboard](https://dashboard.cohere.com)
    2. Sign in or create an account
    3. Navigate to **API Keys**
    4. Copy your default API key or create a new one
  </Step>

  <Step title="Configure in EnConvo">
    1. Open **Settings** → **AI Provider**
    2. Select **Cohere**
    3. Go to **Credentials** module
    4. Enter your API key
  </Step>

  <Step title="Select Model">
    Choose your preferred model from the dropdown
  </Step>
</Steps>

## Configuration

| Setting         | Description           | Default    |
| --------------- | --------------------- | ---------- |
| **Credentials** | API key configuration | Required   |
| **Model Name**  | Model to use          | Command R+ |
| **Temperature** | Creativity (0-2)      | Medium (1) |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the Cohere credential settings. If validation fails, confirm the API key is active in the Cohere dashboard.
  </Step>

  <Step title="Choose the right Command model">
    Use Command R+ for complex grounded answers and Command R for lighter RAG or summarization tasks.
  </Step>

  <Step title="Pair with Knowledge Base">
    For document Q\&A, combine Cohere with EnConvo's Knowledge Base so the prompt includes retrieved context.
  </Step>
</Steps>

## Pricing

Check [Cohere Pricing](https://cohere.com/pricing) for current rates.

| Model      | Input     | Output    |
| ---------- | --------- | --------- |
| Command R+ | \$2.50/1M | \$10/1M   |
| Command R  | \$0.15/1M | \$0.60/1M |

<Note>
  Cohere offers a generous free tier (rate-limited) for development and prototyping, with no credit card required.
</Note>

## Why Cohere?

<CardGroup cols={2}>
  <Card title="Grounded Generation" icon="quote-left">
    Command R models can cite sources, reducing hallucinations
  </Card>

  <Card title="Enterprise Ready" icon="building">
    SOC 2 compliant with data privacy guarantees
  </Card>

  <Card title="RAG Optimized" icon="magnifying-glass">
    Built-in support for retrieval-augmented generation
  </Card>

  <Card title="Multilingual" icon="language">
    Strong performance across 100+ languages
  </Card>
</CardGroup>

## Best Practices

<AccordionGroup>
  <Accordion title="Model Selection">
    * **Command R+**: Research, document analysis, complex Q\&A with citations
    * **Command R**: Everyday chat, summarization, lightweight grounded tasks
    * **Embed**: Building search indexes, semantic similarity, clustering
  </Accordion>

  <Accordion title="RAG Workflows">
    Cohere models are specifically tuned for RAG. Pair them with EnConvo's Knowledge Base feature for best results when working with your own documents.
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Invalid API key">
    * Verify the key is copied correctly from [dashboard.cohere.com](https://dashboard.cohere.com)
    * Check if the key has been revoked
    * Ensure your account is active
  </Accordion>

  <Accordion title="Rate limits on free tier">
    * Free tier is limited to a set number of API calls per minute
    * Upgrade to a production key for higher limits
    * Use Command R instead of Command R+ to stay within quota
  </Accordion>

  <Accordion title="Unexpected responses">
    * Adjust temperature for more or less creative outputs
    * Ensure you are using the correct model for your use case
    * Check the Cohere status page for service issues
  </Accordion>
</AccordionGroup>