Chroma Document Store

Chroma is a lightweight, open-source vector database designed for embedding-based search. It can be used as a document store in Retrieval-Augmented Generation (RAG) pipelines with Quarkus LangChain4j.

This guide explains how to configure and use Chroma as an embedding-aware document store.

Dependency

To enable Chroma integration in your Quarkus project, add the following Maven dependency:

<dependency>
    <groupId>io.quarkiverse.langchain4j</groupId>
    <artifactId>quarkus-langchain4j-chroma</artifactId>
    <version>1.0.2</version>
</dependency>

Dev Services Support

The Chroma extension provides Dev Services support: when running in development or test mode, a containerized Chroma instance will be started automatically, no manual configuration required.

If you wish to customize the container behavior, such as the image or exposed ports, you can use standard quarkus.devservices.* properties. For example:

quarkus.langchain4j.chroma.devservices.image-name=ghcr.io/chroma-core/chroma:latest

Refer to the configuration section below for more options.

Usage Example

Once the extension is installed and the dev service (or external Chroma instance) is available, you can use the Chroma document store as follows:

package io.quarkiverse.langchain4j.samples;

import static dev.langchain4j.data.document.splitter.DocumentSplitters.recursive;

import java.util.List;

import jakarta.enterprise.context.ApplicationScoped;
import jakarta.inject.Inject;

import dev.langchain4j.data.document.Document;
import dev.langchain4j.model.embedding.EmbeddingModel;
import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
import io.quarkiverse.langchain4j.chroma.ChromaEmbeddingStore;

@ApplicationScoped
public class IngestorExampleWithChroma {

    /**
     * The embedding store (the database).
     * The bean is provided by the quarkus-langchain4j-chroma extension.
     */
    @Inject
    ChromaEmbeddingStore store;

    /**
     * The embedding model (how is computed the vector of a document).
     * The bean is provided by the LLM (like openai) extension.
     */
    @Inject
    EmbeddingModel embeddingModel;

    public void ingest(List<Document> documents) {
        EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder()
                .embeddingStore(store)
                .embeddingModel(embeddingModel)
                .documentSplitter(recursive(500, 0))
                .build();
        // Warning - this can take a long time...
        ingestor.ingest(documents);
    }
}

This example demonstrates how to ingest content into Chroma, where it will be indexed and stored with its vector embedding.

Configuration

The Chroma extension can be configured using the following options:

Configuration property fixed at build time - All other configuration properties are overridable at runtime

Configuration property

Type

Default

quarkus.langchain4j.chroma.devservices.enabled

If DevServices has been explicitly enabled or disabled. DevServices is generally enabled by default, unless there is an existing configuration present.

When DevServices is enabled Quarkus will attempt to automatically configure and start a database when running in Dev or Test mode and when Docker is running.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_ENABLED

boolean

true

quarkus.langchain4j.chroma.devservices.image-name

The container image name to use, for container based DevServices providers. If you want to use Redis Stack modules (bloom, graph, search…​), use: redis/redis-stack:latest.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_IMAGE_NAME

string

ghcr.io/chroma-core/chroma:0.4.15

quarkus.langchain4j.chroma.devservices.port

Optional fixed port the dev service will listen to.

If not defined, the port will be chosen randomly.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_PORT

int

quarkus.langchain4j.chroma.devservices.shared

Indicates if the Redis server managed by Quarkus Dev Services is shared. When shared, Quarkus looks for running containers using label-based service discovery. If a matching container is found, it is used, and so a second one is not started. Otherwise, Dev Services for Redis starts a new container.

The discovery uses the quarkus-dev-service-chroma label. The value is configured using the service-name property.

Container sharing is only used in dev mode.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_SHARED

boolean

true

quarkus.langchain4j.chroma.devservices.service-name

The value of the quarkus-dev-service-chroma label attached to the started container. This property is used when shared is set to true. In this case, before starting a container, Dev Services for Redis looks for a container with the quarkus-dev-service-chroma label set to the configured value. If found, it will use this container instead of starting a new one. Otherwise, it starts a new container with the quarkus-dev-service-chroma label set to the specified value.

This property is used when you need multiple shared Chroma servers.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_SERVICE_NAME

string

chroma

quarkus.langchain4j.chroma.devservices.container-env."container-env"

Environment variables that are passed to the container.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_CONTAINER_ENV__CONTAINER_ENV_

Map<String,String>

quarkus.langchain4j.chroma.url

URL where the Chroma database is listening for requests

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_URL

string

required

quarkus.langchain4j.chroma.collection-name

The collection name.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_COLLECTION_NAME

string

default

quarkus.langchain4j.chroma.timeout

The timeout duration for the Chroma client. If not specified, 5 seconds will be used.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_TIMEOUT

Duration 

quarkus.langchain4j.chroma.log-requests

Whether requests to Chroma should be logged

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_LOG_REQUESTS

boolean

false

quarkus.langchain4j.chroma.log-responses

Whether responses from Chroma should be logged

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_LOG_RESPONSES

boolean

false
About the Duration format

To write duration values, use the standard java.time.Duration format. See the Duration#parse() Java API documentation for more information.

You can also use a simplified format, starting with a number:

  • If the value is only a number, it represents time in seconds.

  • If the value is a number followed by ms, it represents time in milliseconds.

In other cases, the simplified format is translated to the java.time.Duration format for parsing:

  • If the value is a number followed by h, m, or s, it is prefixed with PT.

  • If the value is a number followed by d, it is prefixed with P.

Notes

  • Chroma supports metadata, but filtering capabilities may depend on the current Chroma version and API behavior.

  • The embedding vector size must match the dimension of your embedding model.

  • The Chroma backend is typically local (SQLite-based), but distributed setups may be available depending on your deployment.

Summary

To use Chroma as a vector store for RAG with Quarkus LangChain4j:

  • Add the Chroma extension to your project.

  • Ensure your embedding model’s vector dimension matches your configuration.

  • Use Dev Services for a containerized Chroma instance in dev/test mode.

  • Use the ChromaEmbeddingStore to ingest and retrieve vectorized documents.