Haystack is an open source NLP framework by deepset to help you build production ready search systems or applications powered by various NLP tasks such as Question Answering. Haystack is designed to help you build systems that work intelligently over large document collections. It achieves this with the concept of Pipelines consisting of various Nodes such as a DocumentStore, a Retriever and a Reader.
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
| Name | Colab | Source Code |
|---|---|---|
| Basic QA Pipeline |  |
Source Code |
| Fine Tune a Model on Your Data | |
Source Code |
| Basic QA Pipeline Without Elasticsearch | |
Source Code |
| FAQ Style QA | |
Source Code |
| Evaluation | |
Source Code |
| Better Retrieval via Embedding Retrieval | |
Source Code |
| RAG Generator | |
Source Code |
| Preprocessing | |
Source Code |
| DPR Training | |
Source Code |
| Knowledge Graph | |
Source Code |
| Pipelines | |
Source Code |
| Long-Form Question Answering | |
Source Code |
| Question Generation | |
Source Code |
| Query Classifier | |
Source Code |
| Table QA | |
Source Code |
| Document Classifier at Index Time | |
Source Code |
| Audio | |
Source Code |
| Generative Pseudo Labeling | |
Source Code |
| Text-to-Image search | |
Source Code |