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

# Haystack

[Haystack](https://haystack.deepset.ai/) is an open-source, end-to-end framework for building modular, production-ready LLM applications. With SambaNova, you can power Haystack pipelines with state-of-the-art models.

## Prerequisites

* A [SambaCloud](https://cloud.sambanova.ai/) account and API key
* Python 3.8 or higher

## Installation and setup

1. Create a virtual environment

```bash
python -m venv .venv
source .venv/bin/activate
```

2. Install Haystack

```bash
pip install haystack-ai
```

3. Set your SambaNova API key

```bash
export api_key="your_sambanova_api_key"
```

## Example use cases

* Answer questions from a webpage
* Build Retrieval-Augmented Generation (RAG) pipelines
* Orchestrate modular LLM components with SambaNova models

## Example notebooks

You can explore example notebooks to see how to build different LLM pipelines with SambaCloud and Haystack.

* Webpage Q\&A Guide: Build a pipeline that answers questions from a webpage
* RAG guide: Implement Retrieval-Augmented Generation (RAG) with Haystack and SambaCloud

See the [Haystack example notebook](https://github.com/sambanova/integrations/blob/main/haystack/haystack_sambanova_examples.ipynb).