Haystack Tutorials

Haystack is an open source framework by deepset for building production-ready LLM applications, retrieval-augmented generative pipelines and state-of-the-art search systems that work intelligently over large document collections. It lets you quickly try out the latest models in natural language processing (NLP) while being flexible and easy to use.

This is the repository where we keep all the Haystack tutorials 📓 👇 These tutorials are also published to the Haystack Website.

To contribute to the tutorials, please check out our Contributing Guidelines.

Tutorials

| Code | Colab | | :--------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Your First QA Pipeline with Retrieval-Augmentation | | | Generating Structured Output with Loop-Based Auto-Correction | | | Serializing Pipelines | | | Preprocessing Different File Types | | | Metadata Filtering | | | Classifying Documents & Queries by Language | | | Creating a Hybrid Retrieval Pipeline | | | Build an Extractive QA Pipeline | | | Evaluating RAG Pipelines | | | Building Pipelines with Conditional Routing | | | Embedding Metadata for Improved Retrieval | | | Building a Chat Application with Function Calling | | | Query Classification with TransformersTextRouter | | | Retrieving a Context Window Around a Sentence | | | | Build a Tool-Calling Agent | | | | Creating Custom SuperComponents | | | | Creating a Multi-Agent System with Haystack | | |