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

# Ollama Provider

> Use local Ollama models with PraisonAI TypeScript

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    U[Input] --> A[Agent]
    A --> O[Output]

    classDef agent fill:#8B0000,color:#fff
    classDef tool fill:#189AB4,color:#fff

    class A agent
    class U,O tool
```

# Ollama Provider

Run models locally with Ollama.

## Environment Variables

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export OLLAMA_BASE_URL=http://localhost:11434
```

## Supported Modalities

| Modality | Supported |
| - | - |
| Text/Chat | ✅ |
| Embeddings | ✅ |
| Tools | ✅ |

## Prerequisites

1. Install Ollama: [https://ollama.ai](https://ollama.ai)
2. Pull a model: `ollama pull llama3.2`

## Quick Start

**1. Simple Usage**

```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import { Agent } from 'praisonai';

const agent = new Agent({
  name: 'LocalAgent',
  instructions: 'You are a helpful assistant.',
  llm: 'ollama/llama3.2'
});

const response = await agent.chat('Hello!');
```

**2. With Configuration**

Adjust provider credentials and model settings for production — see the sections above.

## Available Models

| Model | Description |
| - | - |
| `llama3.2` | Llama 3.2 |
| `llama3.1` | Llama 3.1 |
| `mistral` | Mistral 7B |
| `codellama` | Code Llama |
| `phi3` | Phi-3 |

## Related

> [card] [Ollama CLI Usage](https://praison.ai/docs/js/providers/ollama-cli.md)
>
> Ollama CLI Usage

> [card] [Local Providers](https://praison.ai/docs/js/providers.md)
>
> Local Providers


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.