Adding support for Pgvector

docs/modules/ROOT/examples/io/quarkiverse/langchain4j/samples/IngestorExampleWithPgvector.java

@@ -0,0 +1,41 @@
+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.pgvector.PgVectorEmbeddingStore;
+
+@ApplicationScoped
+public class IngestorExampleWithPgvector {
+
+    /**
+     * The embedding store (the database).
+     * The bean is provided by the quarkus-langchain4j-pgvector extension.
+     */
+    @Inject
+    PgVectorEmbeddingStore 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);
+    }
+}

docs/modules/ROOT/pages/includes/quarkus-langchain4j-pgvector.adoc

@@ -0,0 +1,114 @@
+
+:summaryTableId: quarkus-langchain4j-pgvector
+[.configuration-legend]
+icon:lock[title=Fixed at build time] Configuration property fixed at build time - All other configuration properties are overridable at runtime
+[.configuration-reference.searchable, cols="80,.^10,.^10"]
+|===
+
+h|[[quarkus-langchain4j-pgvector_configuration]]link:#quarkus-langchain4j-pgvector_configuration[Configuration property]
+
+h|Type
+h|Default
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.table]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.table[quarkus.langchain4j.pgvector.table]`
+
+
+[.description]
+--
+The table name for storing embeddings
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_TABLE+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_TABLE+++`
+endif::add-copy-button-to-env-var[]
+--|string 
+|`embeddings`
+
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.dimension]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.dimension[quarkus.langchain4j.pgvector.dimension]`
+
+
+[.description]
+--
+The dimension of the embedding vectors. This has to be the same as the dimension of vectors produced by the embedding model that you use. For example, AllMiniLmL6V2QuantizedEmbeddingModel produces vectors of dimension 384. OpenAI's text-embedding-ada-002 produces vectors of dimension 1536.
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_DIMENSION+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_DIMENSION+++`
+endif::add-copy-button-to-env-var[]
+--|int 
+|required icon:exclamation-circle[title=Configuration property is required]
+
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.use-index]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.use-index[quarkus.langchain4j.pgvector.use-index]`
+
+
+[.description]
+--
+Use index or not
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_USE_INDEX+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_USE_INDEX+++`
+endif::add-copy-button-to-env-var[]
+--|boolean 
+|`false`
+
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.index-list-size]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.index-list-size[quarkus.langchain4j.pgvector.index-list-size]`
+
+
+[.description]
+--
+index size
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_INDEX_LIST_SIZE+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_INDEX_LIST_SIZE+++`
+endif::add-copy-button-to-env-var[]
+--|int 
+|`0`
+
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.create-table]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.create-table[quarkus.langchain4j.pgvector.create-table]`
+
+
+[.description]
+--
+Create table or not
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_CREATE_TABLE+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_CREATE_TABLE+++`
+endif::add-copy-button-to-env-var[]
+--|boolean 
+|`true`
+
+
+a| [[quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.drop-table-first]]`link:#quarkus-langchain4j-pgvector_quarkus.langchain4j.pgvector.drop-table-first[quarkus.langchain4j.pgvector.drop-table-first]`
+
+
+[.description]
+--
+Drop table or not
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_PGVECTOR_DROP_TABLE_FIRST+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_PGVECTOR_DROP_TABLE_FIRST+++`
+endif::add-copy-button-to-env-var[]
+--|boolean 
+|`false`
+
+|===

docs/modules/ROOT/pages/pgvector-store.adoc

@@ -0,0 +1,42 @@
+= Pgvector Document Store for Retrieval Augmented Generation (RAG)
+
+include::./includes/attributes.adoc[]
+
+When implementing Retrieval Augmented Generation (RAG), a capable document store is necessary. This guide will explain how to leverage a pgvector database as the document store.
+
+== Leveraging the pgvector Document Store
+
+To utilize the Redis document store, you'll need to include the following dependency:
+
+[source,xml,subs=attributes+]
+----
+<dependency>
+    <groupId>io.quarkiverse.langchain4j</groupId>
+    <artifactId>quarkus-langchain4j-pgvector</artifactId>
+    <version>{project-version}</version>
+</dependency>
+----
+
+This extension will check for a default datasource, ensure you have defined at least one datasource. For detailed guidance, refer to the link:https://quarkus.io/guides/datasource[CONFIGURE DATA SOURCES IN QUARKUS].
+
+IMPORTANT: If you plan to use `devservices` be sure to use this property : `quarkus.datasource.devservices.image-name=ankane/pgvector:v0.5.1`.
+
+IMPORTANT: The pgvector store requires the dimension of the vector to be set. Add the `quarkus.langchain4j.pgvector.dimension` property to your `application.properties` file and set it to the dimension of the vector. The dimension depends on the embedding model you use.
+For example, `AllMiniLmL6V2QuantizedEmbeddingModel` produces vectors of dimension 384. OpenAI’s `text-embedding-ada-002` produces vectors of dimension 1536.
+
+Upon installing the extension, you can utilize the pgvector store using the following code:
+
+[source,java]
+----
+include::{examples-dir}/io/quarkiverse/langchain4j/samples/IngestorExampleWithPgvector.java[]
+----
+
+== Configuration Settings
+
+Customize the behavior of the extension by exploring various configuration options:
+
+include::includes/quarkus-langchain4j-pgvector.adoc[leveloffset=+1,opts=optional]
+
+== Under the Hood
+
+Each ingested document is saved as a row in a Postgres table, containing the embedding column stored as a vector.

docs/modules/ROOT/pages/pinecone-store.adoc

@@ -16,20 +16,6 @@ To make use of the Pinecone document store, you'll need to include the following
 </dependency>
 ----
 
-The required configuration properties to make the extension work are
-`quarkus.langchain4j.pinecone.api-key`,
-`quarkus.langchain4j.pinecone.environment`,
-`quarkus.langchain4j.pinecone.index-name`, and
-`quarkus.langchain4j.pinecone.project-id`. The specified index will be
-created if it doesn't exist yet.
-
-Upon installing the extension, you can utilize the Pinecone embedding store using the following code:
-
-[source,java]
-----
-include::{examples-dir}/io/quarkiverse/langchain4j/samples/IngestorExampleWithPinecone.java[]
-----
-
 == Configuration Settings
 
 Customize the behavior of the extension by exploring various configuration options:

docs/pom.xml

@@ -63,6 +63,11 @@
             <artifactId>quarkus-langchain4j-pinecone-deployment</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>io.quarkiverse.langchain4j</groupId>
+            <artifactId>quarkus-langchain4j-pgvector-deployment</artifactId>
+            <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>io.quarkiverse.langchain4j</groupId>
             <artifactId>quarkus-langchain4j-hugging-face-deployment</artifactId>
@@ -121,6 +126,7 @@
                                     <include>quarkus-langchain4j-redis.adoc</include>
                                     <include>quarkus-langchain4j-chroma.adoc</include>
                                     <include>quarkus-langchain4j-pinecone.adoc</include>
+                                    <include>quarkus-langchain4j-pgvector.adoc</include>
                                     <filtering>false</filtering>
                                 </resource>
                                 <resource>

pgvector/deployment/pom.xml

@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd" xmlns="http://maven.apache.org/POM/4.0.0"
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+  <modelVersion>4.0.0</modelVersion>
+  <parent>
+    <groupId>io.quarkiverse.langchain4j</groupId>
+    <artifactId>quarkus-langchain4j-pgvector-parent</artifactId>
+    <version>999-SNAPSHOT</version>
+  </parent>
+  <artifactId>quarkus-langchain4j-pgvector-deployment</artifactId>
+  <name>Quarkus langchain4j-pgvector - Deployment</name>
+  <dependencies>
+     <dependency>
+        <groupId>io.quarkiverse.langchain4j</groupId>
+        <artifactId>quarkus-langchain4j-pgvector</artifactId>
+        <version>${project.version}</version>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkus</groupId>
+        <artifactId>quarkus-arc-deployment</artifactId>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkus</groupId>
+        <artifactId>quarkus-jackson-deployment</artifactId>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkus</groupId>
+        <artifactId>quarkus-agroal-deployment</artifactId>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkus</groupId>
+        <artifactId>quarkus-jdbc-postgresql-deployment</artifactId>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkiverse.langchain4j</groupId>
+        <artifactId>quarkus-langchain4j-core-deployment</artifactId>
+        <version>${project.version}</version>
+    </dependency>
+    <dependency>
+        <groupId>io.quarkus</groupId>
+        <artifactId>quarkus-junit5-internal</artifactId>
+        <scope>test</scope>
+    </dependency>
+    <dependency>
+        <groupId>org.assertj</groupId>
+        <artifactId>assertj-core</artifactId>
+        <version>${assertj.version}</version>
+        <scope>test</scope>
+    </dependency>
+    <dependency>
+        <groupId>org.wiremock</groupId>
+        <artifactId>wiremock-standalone</artifactId>
+        <version>${wiremock.version}</version>
+        <scope>test</scope>
+    </dependency>
+    <dependency>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-embeddings-all-minilm-l6-v2-q</artifactId>
+        <version>${langchain4j.version}</version>
+        <scope>test</scope>
+    </dependency>
+  </dependencies>
+  <build>
+    <plugins>
+      <plugin>
+        <artifactId>maven-compiler-plugin</artifactId>
+        <configuration>
+          <annotationProcessorPaths>
+            <path>
+              <groupId>io.quarkus</groupId>
+              <artifactId>quarkus-extension-processor</artifactId>
+              <version>${quarkus.version}</version>
+            </path>
+          </annotationProcessorPaths>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+</project>

pgvector/deployment/src/main/java/io/quarkiverse/langchain4j/pgvector/deployment/Langchain4jPgvectorProcessor.java

@@ -0,0 +1,59 @@
+package io.quarkiverse.langchain4j.pgvector.deployment;
+
+import jakarta.enterprise.context.ApplicationScoped;
+
+import org.jboss.jandex.ClassType;
+import org.jboss.jandex.DotName;
+import org.jboss.jandex.ParameterizedType;
+
+import com.pgvector.PGvector;
+
+import dev.langchain4j.data.segment.TextSegment;
+import dev.langchain4j.store.embedding.EmbeddingStore;
+import io.agroal.api.AgroalDataSource;
+import io.quarkiverse.langchain4j.pgvector.PgVectorEmbeddingStore;
+import io.quarkiverse.langchain4j.pgvector.runtime.PgVectorEmbeddingStoreConfig;
+import io.quarkiverse.langchain4j.pgvector.runtime.PgVectorEmbeddingStoreRecorder;
+import io.quarkus.arc.deployment.SyntheticBeanBuildItem;
+import io.quarkus.deployment.annotations.BuildProducer;
+import io.quarkus.deployment.annotations.BuildStep;
+import io.quarkus.deployment.annotations.ExecutionTime;
+import io.quarkus.deployment.annotations.Record;
+import io.quarkus.deployment.builditem.FeatureBuildItem;
+import io.quarkus.deployment.builditem.nativeimage.ReflectiveClassBuildItem;
+
+class Langchain4jPgvectorProcessor {
+
+    public static final DotName PGVECTOR_EMBEDDING_STORE = DotName.createSimple(PgVectorEmbeddingStore.class);
+
+    private static final String FEATURE = "langchain4j-pgvector";
+
+    @BuildStep
+    FeatureBuildItem feature() {
+        return new FeatureBuildItem(FEATURE);
+    }
+
+    @BuildStep
+    @Record(ExecutionTime.RUNTIME_INIT)
+    public void createBean(
+            BuildProducer<SyntheticBeanBuildItem> beanProducer,
+            PgVectorEmbeddingStoreRecorder recorder,
+            PgVectorEmbeddingStoreConfig config) {
+        beanProducer.produce(SyntheticBeanBuildItem
+                .configure(PGVECTOR_EMBEDDING_STORE)
+                .types(ClassType.create(EmbeddingStore.class),
+                        ParameterizedType.create(EmbeddingStore.class, ClassType.create(TextSegment.class)))
+                .setRuntimeInit()
+                .defaultBean()
+                .scope(ApplicationScoped.class)
+                .addInjectionPoint(ClassType.create(DotName.createSimple(AgroalDataSource.class)))
+                .createWith(recorder.embeddingStoreFunction(config))
+                .done());
+
+    }
+
+    @BuildStep
+    public ReflectiveClassBuildItem reflectiveClass() {
+        return ReflectiveClassBuildItem.builder(PGvector.class).build();
+    }
+}