Haystack Concepts Overview
Haystack provides all the tools you need to build a custom NLP application that works for you. This includes everything from prototyping, through annotating data, to deployment. This page lists all the concepts Haystack operates on.
| Component | Description |
|---|---|
| Agent | Uses a large language model to reason and answer complex queries that require multiple steps to find the correct answer. |
| Documents, Answers, and Labels | The core data structures of Haystack. |
| Document Stores | These store your Document corpus and connect to various backend databases. |
| Pipelines | Pipelines allow for easy configuration of Haystack's NLP components. |
| Ready-Made Pipelines | Template Pipelines that cover the most common use cases. |
| REST API | The REST API allows for quick deployment of pipelines as a service. |
| Annotation Tool | A tool for managing teams of annotators and facilitating the annotation of text for question answering and document search. |
| Pseudo Label Generator | Use Pseudo Label Generator to create training data for dense Retrievers without human annotation. |
Updated almost 2 years ago