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

# LangChain

The LangChain integration provides Chat and Embedding classes that automatically manage downloading models and starting servers.

Install `langchain-openai` in your environment:

```sh theme={null}
pip install langchain-openai
```

<Warning>
  Only `pip install` packages in your conda environment once all other packages and their dependencies have been installed. For more information on installing pip packages in your conda environment, see [Installing pip packages](/docs/getting-started/working-with-conda/packages/pip-install#using-pip-install-in-a-conda-environment).
</Warning>

<Warning>
  The `AnacondaQuantizedLLM` class is not currently supported due to llama.cpp limitations with the v1/completions endpoint. Use `AnacondaQuantizedModelChat` for chat completions and `AnacondaQuantizedModelEmbeddings` for embeddings.

  See [llama.cpp discussion](https://github.com/ggerganov/llama.cpp/discussions/9219) for details.
</Warning>

Here is a minimal setup example for using LangChain with Anaconda's models:

```py theme={null}
from langchain.prompts import ChatPromptTemplate
from anaconda_ai.integrations.langchain import AnacondaQuantizedModelChat, AnacondaQuantizedModelEmbeddings

prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
model = AnacondaQuantizedModelChat(model_name='meta-llama/llama-2-7b-chat-hf_Q4_K_M.gguf')

chain = prompt | model

message = chain.invoke({'topic': 'python'})
```

To use an already running server, pass `server/<server-name>` as the `model_name`:

```python theme={null}
model = AnacondaQuantizedModelChat(model_name='server/my-server')
```

You can pass server configuration options using the `extra_options` parameter:

```python theme={null}
model = AnacondaQuantizedModelChat(
    model_name='meta-llama/llama-2-7b-chat-hf_Q4_K_M.gguf',
    extra_options={
        'ctx_size': 4096,
        'n_gpu_layers': 20,
        'temperature': 0.7
    }
)
```

These options are passed directly to the inference server during startup.

For more information on using the `langchain-openai` package, see the [official documentation](https://github.com/langchain-ai/langchain/blob/master/README.md).