Guides Overview

Guide	Description
Creating Custom Components	Learn how to create custom components and use them in Pipelines.
Vector-Based vs Keyword-Based Retrievers	Learn about the types of Retrievers, how you can choose the best one for your use case, or how you can combine different approaches for hybrid retrieval.
Language Models	Learn about the different types of language models and when to use them.
Languages Other Than English	Adapt a Haystack system to work with languages other than English.
Domain Adaptation	Improve your system's performance on data from a specific domain.
Optimization	Speed up your system or improve its general performance.
Evaluation	Measure how well your system is performing.
Chatbot Integration	Build a chatbot that knows how to take advantage of Haystack's NLP power.
Table Question Answering	Perform retrieval and question answering on tabular data.
Model Distillation	Create a version of a pretrained model that sacrifices some accuracy for speed.
Metadata Filtering	Narrow down the dataset that you're working with based on metadata attached to your Documents.
Generative Pseudo Labelling	Adapt your dense Retriever to a new domain without human annotation.
Enabling GPU Acceleration	Use GPU to speed up your Haystack system.
Log Level	Configure what messages you want to display in the console output.
Telemetry	Learn about the information Haystack uses to bring improvements to its users.