Integration with vearch (langchain4j#525)

support langchain4j#425 . Due to my local environment problem (`vearch` docker
container start failed in Apple M1), I do the integration test in remote
`vearch` (I start up `vearch` container in remote host using docker),
and it works fine. (But I don't check using `Testcontainers` to start
up)

Two more things need discussion and your opinion:

1. There is a translation between `RelevantScore` and `CosineSimilarity`
in `findRelevant` method, I don't know if that's correct, because
`vearch` do not support cosine similarity, so I use inner product
instead (same as cosine similarity if vector is normalized). Should we
normalize vector before adding it to the embedding store?
2. There are many contraints in creating `vearch` space (retrieval types
have different parameters). Should we check it or just let users to
check themselves? (see [Create
Space](https://vearch.readthedocs.io/en/latest/use_op/op_space.html#create-space)).
Currently I implement it by using many inner static class (see
`RetrievalParam` and `RetrievalType`, in `SpaceEngine` it will do some
constraint check.)

langchain4j-bom/pom.xml

@@ -185,6 +185,12 @@
                 <version>${project.version}</version>
             </dependency>
 
+            <dependency>
+                <groupId>dev.langchain4j</groupId>
+                <artifactId>langchain4j-vearch</artifactId>
+                <version>${project.version}</version>
+            </dependency>
+
             <!-- code execution engines -->
 
             <dependency>
@@ -207,6 +213,18 @@
                 <version>${project.version}</version>
             </dependency>
 
+            <dependency>
+                <groupId>dev.langchain4j</groupId>
+                <artifactId>langchain4j-document-loader-github</artifactId>
+                <version>${project.version}</version>
+            </dependency>
+
+            <dependency>
+                <groupId>dev.langchain4j</groupId>
+                <artifactId>langchain4j-document-loader-azure-storage-blob</artifactId>
+                <version>${project.version}</version>
+            </dependency>
+
             <!-- document parsers -->
 
             <dependency>

langchain4j-core/src/main/java/dev/langchain4j/data/embedding/Embedding.java

@@ -45,6 +45,21 @@ public List<Float> vectorAsList() {
         return list;
     }
 
+    /**
+     * Normalize vector
+     */
+    public void normalize() {
+        double norm = 0.0;
+        for (float f : vector) {
+            norm += f * f;
+        }
+        norm = Math.sqrt(norm);
+
+        for (int i = 0; i < vector.length; i++) {
+            vector[i] /= norm;
+        }
+    }
+
     /**
      * Returns the dimension of the vector.
      * @return the dimension of the vector.

langchain4j-core/src/test/java/dev/langchain4j/data/embedding/EmbeddingTest.java

@@ -48,4 +48,13 @@ public void test_from() {
                 .isEqualTo(new Embedding(new float[]{1.0f, 2.0f, 3.0f}));
     }
 
+    @Test
+    void test_normalize() {
+        Embedding embedding = new Embedding(new float[]{6f, 8f});
+        embedding.normalize();
+
+        Embedding expect = new Embedding(new float[]{0.6f, 0.8f});
+        assertThat(embedding).isEqualTo(expect);
+    }
+
 }

langchain4j-vearch/pom.xml

@@ -0,0 +1,101 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <parent>
+        <groupId>dev.langchain4j</groupId>
+        <artifactId>langchain4j-parent</artifactId>
+        <version>0.26.0-SNAPSHOT</version>
+        <relativePath>../langchain4j-parent/pom.xml</relativePath>
+    </parent>
+
+    <artifactId>langchain4j-vearch</artifactId>
+    <packaging>jar</packaging>
+
+    <name>LangChain4j integration with Vearch</name>
+
+    <dependencies>
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-core</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>com.squareup.retrofit2</groupId>
+            <artifactId>retrofit</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>com.squareup.retrofit2</groupId>
+            <artifactId>converter-gson</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>com.squareup.okhttp3</groupId>
+            <artifactId>okhttp</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>org.projectlombok</groupId>
+            <artifactId>lombok</artifactId>
+            <scope>provided</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-api</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>org.junit.jupiter</groupId>
+            <artifactId>junit-jupiter-engine</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.assertj</groupId>
+            <artifactId>assertj-core</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-embeddings-all-minilm-l6-v2-q</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>dev.langchain4j</groupId>
+            <artifactId>langchain4j-core</artifactId>
+            <classifier>tests</classifier>
+            <type>test-jar</type>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.testcontainers</groupId>
+            <artifactId>testcontainers</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.testcontainers</groupId>
+            <artifactId>junit-jupiter</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.tinylog</groupId>
+            <artifactId>tinylog-impl</artifactId>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.tinylog</groupId>
+            <artifactId>slf4j-tinylog</artifactId>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+
+</project>

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/BulkRequest.java

@@ -0,0 +1,16 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+import java.util.List;
+import java.util.Map;
+
+@Getter
+@Setter
+@Builder
+class BulkRequest {
+
+    private List<Map<String, Object>> documents;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/BulkResponse.java

@@ -0,0 +1,17 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import com.google.gson.annotations.SerializedName;
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class BulkResponse {
+
+    private Integer status;
+    private String error;
+    @SerializedName("_id")
+    private String id;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/CreateDatabaseRequest.java

@@ -0,0 +1,13 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class CreateDatabaseRequest {
+
+    private String name;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/CreateDatabaseResponse.java

@@ -0,0 +1,14 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class CreateDatabaseResponse {
+
+    private Long id;
+    private String name;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/CreateSpaceRequest.java

@@ -0,0 +1,24 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import dev.langchain4j.store.embedding.vearch.ModelParam;
+import dev.langchain4j.store.embedding.vearch.SpaceEngine;
+import dev.langchain4j.store.embedding.vearch.SpacePropertyParam;
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+import java.util.List;
+import java.util.Map;
+
+@Getter
+@Setter
+@Builder
+class CreateSpaceRequest {
+
+    private String name;
+    private Integer partitionNum;
+    private Integer replicaNum;
+    private SpaceEngine engine;
+    private Map<String, SpacePropertyParam> properties;
+    private List<ModelParam> models;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/CreateSpaceResponse.java

@@ -0,0 +1,14 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class CreateSpaceResponse {
+
+    private Integer id;
+    private String name;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/ListDatabaseResponse.java

@@ -0,0 +1,14 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class ListDatabaseResponse {
+
+    private Integer id;
+    private String name;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/ListSpaceResponse.java

@@ -0,0 +1,14 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+public class ListSpaceResponse {
+
+    private Integer id;
+    private String name;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/MetricType.java

@@ -0,0 +1,17 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import com.google.gson.annotations.SerializedName;
+
+/**
+ * if metric type is not set when searching, it will use the parameter specified when building the space
+ *
+ * <p>LangChain4j currently only support {@link MetricType#INNER_PRODUCT}</p>
+ */
+public enum MetricType {
+
+    /**
+     * Inner Product
+     */
+    @SerializedName("InnerProduct")
+    INNER_PRODUCT
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/ModelParam.java

@@ -0,0 +1,17 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+import java.util.List;
+
+@Getter
+@Setter
+@Builder
+public class ModelParam {
+
+    private String modelId;
+    private List<String> fields;
+    private String out;
+}

langchain4j-vearch/src/main/java/dev/langchain4j/store/embedding/vearch/ResponseWrapper.java

@@ -0,0 +1,15 @@
+package dev.langchain4j.store.embedding.vearch;
+
+import lombok.Builder;
+import lombok.Getter;
+import lombok.Setter;
+
+@Getter
+@Setter
+@Builder
+class ResponseWrapper<T> {
+
+    private Integer code;
+    private String msg;
+    private T data;
+}