[Haystack](https://haystack.deepset.ai/) is an end-to-end LLM framework that enables you to build applications powered by LLMs, Transformer models, vector search and more. Whether you want to perform retrieval-augmented generation (RAG), documentation search, question answering or answer generation, you can use state-of-the-art embedding models and LLMs with Haystack to build end-to-end NLP applications to solve your use case.
Haystack is built around the concept of pipelines. A pipeline is a powerful structure that performs an NLP task. It's made up of components connected together. For example, you can connect a [retriever](https://docs.haystack.deepset.ai/v2.0/docs/retrievers) and a [generator](https://docs.haystack.deepset.ai/v2.0/docs/generators) to build a Generative Question Answering pipeline that uses your own data.
👉 To build a minimal RAG pipeline that uses GPT-4 on your own data, use the [RAG Pipeline Recipe](https://docs.haystack.deepset.ai/v2.0/recipes/20-rag-pipeline)
⚛️ **[Components](https://docs.haystack.deepset.ai/v2.0/docs/components):** Each Component achieves one thing. Such as preprocessing documents, retrieving documents, using specific language models to answer questions, and so on. Components can `.connect()` to each other to form a complete pipeline.
🏃♀️ **[Pipelines](https://docs.haystack.deepset.ai/v2.0/docs/pipelines):** This is the standard Haystack structure that builds on top of your data to perform various NLP tasks such as retrieval augmented generation, question answering and more. Pipelines in Haystack are Directed Multigraphs composed of components. Components can receive inputs from other components and produce outputs that can be forwarded to other components.
🗂️ **[DocumentStores](https://docs.haystack.deepset.ai/docs/document_store):** A DocumentStore is database where you store your text data for Haystack to access. Haystack DocumentStores are available with ElasticSearch, Opensearch, Weaviate, Pinecone, FAISS and more. For a full list of available DocumentStores, check out our [documentation](https://docs.haystack.deepset.ai/docs/document_store).
- Build **retrieval augmented generation (RAG)** by making use of one of the available vector databases and customizing your LLM interaction, the sky is the limit 🚀
- Build applications that can make complex decisions making to answer complex queries: such as systems that can resolve complex customer queries, do knowledge search on many disconnected resources and so on.
-**Latest models**: Haystack allows you to use and compare models available from OpenAI, Cohere and Hugging Face, as well as your own local models or models hosted on SageMaker. Use the latest LLMs or Transformer-based models (for example: BERT, RoBERTa, MiniLM).
| 🎓 [Tutorials](https://haystack.deepset.ai/tutorials) | See what Haystack can do with our Notebooks & Scripts |
| 🎉 [Haystack Extras](https://github.com/deepset-ai/haystack-extras) | A repository that lists extra Haystack packages and components that can be installed separately. |
| 🔰 [Demos](https://github.com/deepset-ai/haystack-demos) | A repository containing Haystack demo applications with Docker Compose and a REST API |
For a detailed installation guide see [the official documentation](https://docs.haystack.deepset.ai/docs/installation). There you’ll find instructions for custom installations handling Windows and Apple Silicon.
you need to install further dependencies. The following command installs the [latest release](https://github.com/deepset-ai/haystack/releases) of Haystack and all its dependencies:
If you want to install only the dependencies needed for model inference on your local hardware (not remote API endpoints), such as torch and sentence-transformers, you can use the following command:
```sh
pip install 'farm-haystack[inference]' ## installs torch, sentence-transformers, sentencepiece, and huggingface-hub
If you want to try out the newest features that are not in an official release yet, you can install the unstable version from the main branch with the following command:
If you want to contribute to the Haystack repo, check our [Contributor Guidelines](https://github.com/deepset-ai/haystack/blob/main/CONTRIBUTING.md) first.
See the list of [dependencies](https://github.com/deepset-ai/haystack/blob/main/pyproject.toml) to check which ones you want to install (for example, `[all]`, `[dev]`, or other).
Haystack comes packaged with a REST API so that you can deploy it as a service. Run the following command from the root directory of the Haystack repo to install REST_API:
You can find some of our hosted demos with instructions to run them locally too on our [haystack-demos](https://github.com/deepset-ai/haystack-demos) repository
If you have a feature request or a bug report, feel free to open an [issue in Github](https://github.com/deepset-ai/haystack/issues). We regularly check these and you can expect a quick response. If you'd like to discuss a topic, or get more general advice on how to make Haystack work for your project, you can start a thread in [Github Discussions](https://github.com/deepset-ai/haystack/discussions) or our [Discord channel](https://discord.gg/haystack). We also check [𝕏 (Twitter)](https://twitter.com/haystack_ai) and [Stack Overflow](https://stackoverflow.com/questions/tagged/haystack).
We are very open to the community's contributions - be it a quick fix of a typo, or a completely new feature! You don't need to be a Haystack expert to provide meaningful improvements. To learn how to get started, check out our [Contributor Guidelines](https://github.com/deepset-ai/haystack/blob/main/CONTRIBUTING.md) first.
