langchain/docs/docs/integrations/providers/ollama.mdx

# Ollama

>[Ollama](https://ollama.ai/) is a python library. It allows you to run open-source large language models, 
> such as LLaMA2, locally.
>
>`Ollama` bundles model weights, configuration, and data into a single package, defined by a Modelfile. 
>It optimizes setup and configuration details, including GPU usage.
>For a complete list of supported models and model variants, see the [Ollama model library](https://ollama.ai/library).

See [this guide](/docs/guides/development/local_llms#quickstart) for more details 
on how to use `Ollama` with LangChain.

## Installation and Setup

Follow [these instructions](https://github.com/jmorganca/ollama?tab=readme-ov-file#ollama)
to set up and run a local Ollama instance.
To use, you should set up the environment variables `ANYSCALE_API_BASE` and
`ANYSCALE_API_KEY`.


## LLM

```python
from langchain_community.llms import Ollama
```

See the notebook example [here](/docs/integrations/llms/ollama).

## Chat Models

### Chat Ollama

```python
from langchain_community.chat_models import ChatOllama
```

See the notebook example [here](/docs/integrations/chat/ollama).

### Ollama functions

```python
from langchain_experimental.llms.ollama_functions import OllamaFunctions
```

See the notebook example [here](/docs/integrations/chat/ollama_functions).

## Embedding models

```python
from langchain_community.embeddings import OllamaEmbeddings
```

See the notebook example [here](/docs/integrations/text_embedding/ollama).