Switch to the upstream ChromaEmbeddingStore impl, support V2 API

Author: jmartisk

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

@@ -10,7 +10,7 @@
 import dev.langchain4j.data.document.Document;
 import dev.langchain4j.model.embedding.EmbeddingModel;
 import dev.langchain4j.store.embedding.EmbeddingStoreIngestor;
-import io.quarkiverse.langchain4j.chroma.ChromaEmbeddingStore;
+import dev.langchain4j.store.embedding.chroma.ChromaEmbeddingStore;
 
 @ApplicationScoped
 public class IngestorExampleWithChroma {

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

@@ -38,7 +38,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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`.
+The container image name to use, for container based DevServices providers.
 
 
 ifdef::add-copy-button-to-env-var[]
@@ -49,7 +49,7 @@ Environment variable: `+++QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_IMAGE_NAME+++`
 endif::add-copy-button-to-env-var[]
 --
 |string
-|`ghcr.io/chroma-core/chroma:0.4.15`
+|`ghcr.io/chroma-core/chroma:1.3.0`
 
 a|icon:lock[title=Fixed at build time] [[quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-devservices-port]] [.property-path]##link:#quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-devservices-port[`quarkus.langchain4j.chroma.devservices.port`]##
 ifdef::add-copy-button-to-config-props[]
@@ -82,7 +82,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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.
+Indicates if the Chroma 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 Chroma starts a new container.
 
 The discovery uses the `quarkus-dev-service-chroma` label. The value is configured using the `service-name` property.
 
@@ -107,7 +107,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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.
+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 Chroma 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.
 
@@ -248,6 +248,27 @@ endif::add-copy-button-to-env-var[]
 |boolean
 |`false`
 
+a| [[quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-api-version]] [.property-path]##link:#quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-api-version[`quarkus.langchain4j.chroma.api-version`]##
+ifdef::add-copy-button-to-config-props[]
+config_property_copy_button:+++quarkus.langchain4j.chroma.api-version+++[]
+endif::add-copy-button-to-config-props[]
+
+
+[.description]
+--
+The Chroma API version to use. V1 is deprecated (Chroma 0.x) and its support will be removed in the future. Please use Chroma 1.x which uses the V2 API.
+
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_CHROMA_API_VERSION+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_CHROMA_API_VERSION+++`
+endif::add-copy-button-to-env-var[]
+--
+a|`v1`, `v2`
+|`v2`
+
 |===
 
 ifndef::no-duration-note[]

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

@@ -38,7 +38,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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`.
+The container image name to use, for container based DevServices providers.
 
 
 ifdef::add-copy-button-to-env-var[]
@@ -49,7 +49,7 @@ Environment variable: `+++QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_IMAGE_NAME+++`
 endif::add-copy-button-to-env-var[]
 --
 |string
-|`ghcr.io/chroma-core/chroma:0.4.15`
+|`ghcr.io/chroma-core/chroma:1.3.0`
 
 a|icon:lock[title=Fixed at build time] [[quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-devservices-port]] [.property-path]##link:#quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-devservices-port[`quarkus.langchain4j.chroma.devservices.port`]##
 ifdef::add-copy-button-to-config-props[]
@@ -82,7 +82,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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.
+Indicates if the Chroma 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 Chroma starts a new container.
 
 The discovery uses the `quarkus-dev-service-chroma` label. The value is configured using the `service-name` property.
 
@@ -107,7 +107,7 @@ endif::add-copy-button-to-config-props[]
 
 [.description]
 --
-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.
+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 Chroma 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.
 
@@ -248,6 +248,27 @@ endif::add-copy-button-to-env-var[]
 |boolean
 |`false`
 
+a| [[quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-api-version]] [.property-path]##link:#quarkus-langchain4j-chroma_quarkus-langchain4j-chroma-api-version[`quarkus.langchain4j.chroma.api-version`]##
+ifdef::add-copy-button-to-config-props[]
+config_property_copy_button:+++quarkus.langchain4j.chroma.api-version+++[]
+endif::add-copy-button-to-config-props[]
+
+
+[.description]
+--
+The Chroma API version to use. V1 is deprecated (Chroma 0.x) and its support will be removed in the future. Please use Chroma 1.x which uses the V2 API.
+
+
+ifdef::add-copy-button-to-env-var[]
+Environment variable: env_var_with_copy_button:+++QUARKUS_LANGCHAIN4J_CHROMA_API_VERSION+++[]
+endif::add-copy-button-to-env-var[]
+ifndef::add-copy-button-to-env-var[]
+Environment variable: `+++QUARKUS_LANGCHAIN4J_CHROMA_API_VERSION+++`
+endif::add-copy-button-to-env-var[]
+--
+a|`v1`, `v2`
+|`v2`
+
 |===
 
 ifndef::no-duration-note[]

embedding-stores/chroma/deployment/pom.xml

@@ -29,6 +29,10 @@
             <groupId>org.testcontainers</groupId>
             <artifactId>chromadb</artifactId>
         </dependency>
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-chroma</artifactId>
+        </dependency>
         <dependency>
             <groupId>io.quarkiverse.langchain4j</groupId>
             <artifactId>quarkus-langchain4j-core-deployment</artifactId>

embedding-stores/chroma/deployment/src/main/java/io/quarkiverse/langchain4j/chroma/deployment/ChromaBuildConfig.java

@@ -34,10 +34,8 @@ interface ChromaDevServicesBuildTimeConfig {
 
         /**
          * The container image name to use, for container based DevServices providers.
-         * If you want to use Redis Stack modules (bloom, graph, search...), use:
-         * {@code redis/redis-stack:latest}.
          */
-        @WithDefault("ghcr.io/chroma-core/chroma:0.4.15")
+        @WithDefault("ghcr.io/chroma-core/chroma:1.3.0")
         String imageName();
 
         /**
@@ -48,10 +46,10 @@ interface ChromaDevServicesBuildTimeConfig {
         OptionalInt port();
 
         /**
-         * Indicates if the Redis server managed by Quarkus Dev Services is shared.
+         * Indicates if the Chroma 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.
+         * Otherwise, Dev Services for Chroma starts a new container.
          * <p>
          * The discovery uses the {@code quarkus-dev-service-chroma} label.
          * The value is configured using the {@code service-name} property.
@@ -64,7 +62,7 @@ interface ChromaDevServicesBuildTimeConfig {
         /**
          * The value of the {@code quarkus-dev-service-chroma} label attached to the started container.
          * This property is used when {@code shared} is set to {@code true}.
-         * In this case, before starting a container, Dev Services for Redis looks for a container with the
+         * In this case, before starting a container, Dev Services for Chroma looks for a container with the
          * {@code 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 {@code quarkus-dev-service-chroma} label set to the specified value.

embedding-stores/chroma/deployment/src/main/java/io/quarkiverse/langchain4j/chroma/deployment/ChromaDBContainer.java

@@ -0,0 +1,50 @@
+package io.quarkiverse.langchain4j.chroma.deployment;
+
+import org.testcontainers.containers.GenericContainer;
+import org.testcontainers.containers.wait.strategy.Wait;
+import org.testcontainers.utility.ComparableVersion;
+import org.testcontainers.utility.DockerImageName;
+
+/**
+ * Overriding the ChromaDBContainer from Testcontainers 1.20.x to support the v2 chroma api.
+ * FIXME: This is temporary until we upgrade to Testcontainers 1.21.
+ */
+public class ChromaDBContainer extends GenericContainer<org.testcontainers.chromadb.ChromaDBContainer> {
+
+    private static final DockerImageName DEFAULT_DOCKER_IMAGE = DockerImageName.parse("chromadb/chroma");
+
+    private static final DockerImageName GHCR_DOCKER_IMAGE = DockerImageName.parse("ghcr.io/chroma-core/chroma");
+
+    public ChromaDBContainer(String dockerImageName) {
+        this(DockerImageName.parse(dockerImageName));
+    }
+
+    public ChromaDBContainer(DockerImageName dockerImageName) {
+        this(dockerImageName, isVersion2(dockerImageName.getVersionPart()));
+    }
+
+    public ChromaDBContainer(DockerImageName dockerImageName, boolean isVersion2) {
+        super(dockerImageName);
+        String apiPath = isVersion2 ? "/api/v2/heartbeat" : "/api/v1/heartbeat";
+        dockerImageName.assertCompatibleWith(DEFAULT_DOCKER_IMAGE, GHCR_DOCKER_IMAGE);
+        withExposedPorts(8000);
+        waitingFor(Wait.forHttp(apiPath));
+    }
+
+    public String getEndpoint() {
+        return "http://" + getHost() + ":" + getFirstMappedPort();
+    }
+
+    private static boolean isVersion2(String version) {
+        if (version.equals("latest")) {
+            return true;
+        }
+
+        ComparableVersion comparableVersion = new ComparableVersion(version);
+        if (comparableVersion.isGreaterThanOrEqualTo("1.0.0")) {
+            return true;
+        }
+
+        return false;
+    }
+}

embedding-stores/chroma/deployment/src/main/java/io/quarkiverse/langchain4j/chroma/deployment/ChromaDevServicesProcessor.java

@@ -10,7 +10,6 @@
 import java.util.function.Supplier;
 
 import org.jboss.logging.Logger;
-import org.testcontainers.chromadb.ChromaDBContainer;
 import org.testcontainers.utility.DockerImageName;
 
 import io.quarkus.bootstrap.classloading.QuarkusClassLoader;

embedding-stores/chroma/deployment/src/main/java/io/quarkiverse/langchain4j/chroma/deployment/ChromaProcessor.java

@@ -8,7 +8,7 @@
 
 import dev.langchain4j.data.segment.TextSegment;
 import dev.langchain4j.store.embedding.EmbeddingStore;
-import io.quarkiverse.langchain4j.chroma.ChromaEmbeddingStore;
+import dev.langchain4j.store.embedding.chroma.ChromaEmbeddingStore;
 import io.quarkiverse.langchain4j.chroma.runtime.ChromaRecorder;
 import io.quarkiverse.langchain4j.deployment.EmbeddingStoreBuildItem;
 import io.quarkus.arc.deployment.SyntheticBeanBuildItem;
@@ -43,6 +43,7 @@ public void createBean(
         beanProducer.produce(SyntheticBeanBuildItem
                 .configure(CHROMA_EMBEDDING_STORE)
                 .types(ClassType.create(EmbeddingStore.class),
+                        ClassType.create(ChromaEmbeddingStore.class),
                         ParameterizedType.create(EmbeddingStore.class, ClassType.create(TextSegment.class)))
                 .defaultBean()
                 .setRuntimeInit()