Weaviate Store for Retrieval Augmented Generation (RAG)
When implementing Retrieval Augmented Generation (RAG), a robust document store is crucial. This guide demonstrates how to leverage a Weaviate database as the document store.
Leveraging the Weaviate embedding store
To make use of the Weaviate embedding store, you’ll need to include the following dependency:
<dependency>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-weaviate</artifactId>
</dependency>This extension includes a dev service. Therefore, if you’re operating in a container environment, a Weaviate instance will automatically start in dev and test mode.
Upon installing the extension, you can use the Weaviate document store with the following code:
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 dev.langchain4j.store.embedding.weaviate.WeaviateEmbeddingStore;
@ApplicationScoped
public class IngestorExampleWithWeaviate {
/**
* The embedding store (the database).
* The bean is provided by the quarkus-langchain4j-weaviate extension.
*/
@Inject
WeaviateEmbeddingStore 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);
}
}| When using Weaviate as an embedding store, you don’t need an in-process embedding model. Weaviate can generate embeddings using its built-in modules or delegate to an external provider, such as OpenAI’s embedding API or other compatible models. |
To use a remote Weaviate instance, you have to also set the host and port, in which case dev-services will not start another instance:
quarkus.langchain4j.weaviate.host=localhost
quarkus.langchain4j.weaviate.port=8080Configuration Settings
Customize the behavior of the extension by exploring various configuration options:
Configuration property fixed at build time - All other configuration properties are overridable at runtime
Configuration property |
Type |
Default |
|---|---|---|
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: |
boolean |
|
The container image name to use, for container based DevServices providers. If you want to use Redis Stack modules (bloom, graph, search…), use: Environment variable: |
string |
|
Optional fixed port the dev service will listen to. If not defined, the port will be chosen randomly. Environment variable: |
int |
|
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 Container sharing is only used in dev mode. Environment variable: |
boolean |
|
The value of the This property is used when you need multiple shared Weaviate servers. Environment variable: |
string |
|
Environment variables that are passed to the container. Environment variable: |
Map<String,String> |
|
The Weaviate API key to authenticate with. Environment variable: |
string |
|
The scheme, e.g. "https" of cluster URL. Find it under Details of your Weaviate cluster. Environment variable: |
string |
|
The URL of the Weaviate server. Environment variable: |
string |
|
The gRPC port of the Weaviate server. Defaults to 8080 Environment variable: |
int |
|
The gRPC port of the Weaviate server. Defaults to 50051 Environment variable: |
int |
|
The gRPC connection is secured. Environment variable: |
boolean |
|
Use gRPC instead of http for batch inserts only. Will still be used for search. Environment variable: |
boolean |
|
The object class you want to store, e.g. "MyGreatClass". Must start from an uppercase letter. Environment variable: |
string |
|
The name of the field that contains the text of a Environment variable: |
string |
|
If true (default), then Environment variable: |
boolean |
|
Consistency level: ONE, QUORUM (default) or ALL. Environment variable: |
|
|
Metadata keys that should be persisted. The default in Weaviate [], however it is required to specify at least one for the EmbeddingStore to work. Thus, we use "tags" as default Environment variable: |
list of string |
|
The name of the field where Environment variable: |
string |
|