Java client for txtai

txtai is an all-in-one embeddings database for semantic search, LLM orchestration and language model workflows.

This repository contains Java bindings for the txtai API.

Installation

Jitpack is the recommended way to integrate txtai with Java. See this link for how to install JitPack.

The following is an example adding txtai to a project's build.gradle file. The same attributes can be ported to other build systems per the JitPack link above.

implementation 'com.github.neuml:txtai.java:v8.0.0'

txtai can also be manually built from GitHub.

git clone https://github.com/neuml/txtai.java
cd txtai.java
./gradlew jar

The JAR will be available in ./build/libs

Examples

The examples directory has a series of examples that give an overview of txtai. See the list of examples below.

Example	Description
Introducing txtai	Overview of the functionality provided by txtai
Extractive QA with txtai	Extractive question-answering with txtai
Labeling with zero-shot classification	Labeling with zero-shot classification
Pipelines and workflows	Pipelines and workflows

txtai.java connects to a txtai api instance. See this link for details on how to start a new api instance.

Once an api instance is running, do the following to run the examples.

git clone https://github.com/neuml/txtai.java
cd txtai.java/examples
../gradlew embeddings|extractor|labels|pipelines