Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add transformers-embedding boot auto-configuraiton and starter

Browse Source
This commit is contained in:
Christian Tzolov
2023-11-15 12:29:22 +01:00
parent 952ff6c319
commit 1746bf6b46
12 changed files with 491 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
embedding-clients/transformers-embedding/README.md
View File

@@ -34,9 +34,9 @@ Add the `transformers-embedding` project to your maven dependencies:
```xml
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>transformers-embedding</artifactId>
<version>0.7.1-SNAPSHOT</version>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>transformers-embedding</artifactId>
<version>0.7.1-SNAPSHOT</version>
</dependency>
```
@@ -51,8 +51,7 @@ If the model is not explicitly set, `TransformersEmbeddingClient` defaults to [s
| Speed | 14200 sentences/sec |
| Size | 80MB |
Following snippet illustrates how to use the `TransformersEmbeddingClient`:
Following snippet illustrates how to use the `TransformersEmbeddingClient` manually:
```java
TransformersEmbeddingClient embeddingClient = new TransformersEmbeddingClient();
@@ -73,14 +72,53 @@ List<List<Double>> embeddings = embeddingClient.embed(List.of("Hello world", "Wo
```
Note that when created manually you have to call the `afterPropertiesSet()` after setting the properties and before using the client.
The first `embed()` call downloads the the large ONNX model and caches it on the local file system.
Therefore the first call might take longer than usual.
Use the `#setResourceCacheDirectory(<path>)` to set the local folder where the ONNX models as stored.
The default cache folder is `${java.io.tmpdir}/spring-ai-onnx-model`.
It is more convenient (and preferred) to create the TransformersEmbeddingClient as a `Bean`.
Then you don't have to call the `afterPropertiesSet()` manually.
```java
@Bean
public EmbeddingClient embeddingClient() {
return new TransformersEmbeddingClient();
}
```
## Transformers Embedding Spring Boot Starter.
You can bootstrap and auto-wire the `TransformersEmbeddingClient` with following boot starer:
```xml
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>spring-ai-transformers-embedding-spring-boot-starter</artifactId>
<version>0.7.1-SNAPSHOT</version>
</dependency>
```
and use the `spring.ai.embedding.transformer.*` properties to configure it.
For example add this to your application.properties to configure with the [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) text embedding model:
```
spring.ai.embedding.transformer.onnx.modelUri=https://huggingface.co/intfloat/e5-small-v2/resolve/main/model.onnx
spring.ai.embedding.transformer.tokenizer.uri=https://huggingface.co/intfloat/e5-small-v2/raw/main/tokenizer.json
```
The complete list of supported properties are:
| Property | Description | Default |
| -------- | ------- | ------- |
| spring.ai.embedding.transformer.tokenizer.uri | URI of a pre-trained HuggingFaceTokenizer created by the ONNX engine (e.g. tokenizer.json). | onnx/all-MiniLM-L6-v2/tokenizer.json |
| spring.ai.embedding.transformer.tokenizer.options | HuggingFaceTokenizer options such as '`addSpecialTokens`', '`modelMaxLength`', '`truncation`', '`padding`', '`maxLength`', '`stride`' and '`padToMultipleOf`'. Leave empty to fallback to the defaults. | empty |
| spring.ai.embedding.transformer.cache.enabled | Enable remote Resource caching. | true |
| spring.ai.embedding.transformer.cache.directory | Directory path to cache remote resources, such as the ONNX models | ${java.io.tmpdir}/spring-ai-onnx-model |
| spring.ai.embedding.transformer.onnx.modelUri | Existing, pre-trained ONNX model. | onnx/all-MiniLM-L6-v2/model.onnx |
| spring.ai.embedding.transformer.onnx.gpuDeviceId | The GPU device ID to execute on. Only applicable if >= 0. Ignored otherwise. | -1 |
| spring.ai.embedding.transformer.metadataMode | Specifies what parts of the Documents content and metadata will be used for computing the embeddings. | NONE |

8
embedding-clients/transformers-embedding/pom.xml
View File

@@ -10,8 +10,8 @@
</parent>
<artifactId>transformers-embedding</artifactId>
<packaging>jar</packaging>
<name>Spring AI Embedding Client - Sentence Transormers Embeddings </name>
<description>Spring AI Sentence Transformers Embedding Client</description>
<name>Spring AI Transormers Embedding Client</name>
<description>Spring AI Transformers Embedding Client</description>
<url>https://github.com/spring-projects-experimental/spring-ai</url>
<scm>
@@ -21,8 +21,8 @@
</scm>
<properties>
<djl.version>0.24.0</djl.version>
<onnxruntime.version>1.16.1</onnxruntime.version>
<djl.version>0.25.0</djl.version>
<onnxruntime.version>1.16.2</onnxruntime.version>
</properties>
<dependencies>
<dependency>

54
embedding-clients/transformers-embedding/src/main/java/org/springframework/ai/embedding/TransformersEmbeddingClient.java
View File

@@ -5,6 +5,7 @@ import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Collectors;
import ai.djl.huggingface.tokenizers.Encoding;
import ai.djl.huggingface.tokenizers.HuggingFaceTokenizer;
@@ -17,6 +18,8 @@ import ai.onnxruntime.OnnxValue;
import ai.onnxruntime.OrtEnvironment;
import ai.onnxruntime.OrtException;
import ai.onnxruntime.OrtSession;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.springframework.ai.document.Document;
import org.springframework.ai.document.MetadataMode;
@@ -33,12 +36,14 @@ import org.springframework.util.StringUtils;
*/
public class TransformersEmbeddingClient implements EmbeddingClient, InitializingBean {
private static final Log logger = LogFactory.getLog(TransformersEmbeddingClient.class);
// ONNX tokenizer for the all-MiniLM-L6-v2 model
private final static String DEFAULT_ONNX_TOKENIZER_URI = "https://raw.githubusercontent.com/spring-projects-experimental/spring-ai/main/embedding-clients/transformers-embedding/src/main/resources/onnx/all-MiniLM-L6-v2/tokenizer.json";
public final static String DEFAULT_ONNX_TOKENIZER_URI = "https://raw.githubusercontent.com/spring-projects-experimental/spring-ai/main/embedding-clients/transformers-embedding/src/main/resources/onnx/all-MiniLM-L6-v2/tokenizer.json";
// ONNX model for all-MiniLM-L6-v2 pre-trained transformer:
// https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2
private final static String DEFAULT_ONNX_MODEL_URI = "https://github.com/spring-projects-experimental/spring-ai/raw/main/embedding-clients/transformers-embedding/src/main/resources/onnx/all-MiniLM-L6-v2/model.onnx";
public final static String DEFAULT_ONNX_MODEL_URI = "https://github.com/spring-projects-experimental/spring-ai/raw/main/embedding-clients/transformers-embedding/src/main/resources/onnx/all-MiniLM-L6-v2/model.onnx";
private final static int EMBEDDING_AXIS = 1;
@@ -59,10 +64,19 @@ public class TransformersEmbeddingClient implements EmbeddingClient, Initializin
*/
private OrtEnvironment environment;
/**
* Runtime session that wraps the ONNX model and enables inference calls.
*/
private OrtSession session;
private final AtomicInteger embeddingDimensions = new AtomicInteger(-1);
/**
* Specifies what parts of the {@link Document}'s content and metadata will be used
* for computing the embeddings. Applicable for the {@link #embed(Document)} method
* only. Has no effect on the {@link #embed(String)} or {@link #embed(List)}. Defaults
* to {@link MetadataMode#NONE}.
*/
private final MetadataMode metadataMode;
/**
@@ -76,7 +90,15 @@ public class TransformersEmbeddingClient implements EmbeddingClient, Initializin
*/
private boolean disableCaching = false;
private ResourceCacheService cache;
/**
* Cache service for caching large {@link Resource} contents, such as the
* tokenizerResource and modelResource, on the local file system. Can be
* enabled/disabled with the {@link #disableCaching} property and uses the
* {@link #resourceCacheDirectory} for local storage.
*/
private ResourceCacheService cacheService;
public Map<String, String> tokenizerOptions = Map.of();
public TransformersEmbeddingClient() {
this(MetadataMode.NONE);
@@ -87,6 +109,10 @@ public class TransformersEmbeddingClient implements EmbeddingClient, Initializin
this.metadataMode = metadataMode;
}
public void setTokenizerOptions(Map<String, String> tokenizerOptions) {
this.tokenizerOptions = tokenizerOptions;
}
public void setDisableCaching(boolean disableCaching) {
this.disableCaching = disableCaching;
}
@@ -121,23 +147,32 @@ public class TransformersEmbeddingClient implements EmbeddingClient, Initializin
@Override
public void afterPropertiesSet() throws Exception {
this.cache = StringUtils.hasText(this.resourceCacheDirectory)
this.cacheService = StringUtils.hasText(this.resourceCacheDirectory)
? new ResourceCacheService(this.resourceCacheDirectory) : new ResourceCacheService();
// Create a pre-trained HuggingFaceTokenizer instance from tokenizerResource
// InputStream.
this.tokenizer = HuggingFaceTokenizer.newInstance(getCachedResource(this.tokenizerResource).getInputStream(),
Map.of());
this.tokenizerOptions);
// onnxruntime
this.environment = OrtEnvironment.getEnvironment();
var sessionOptions = new OrtSession.SessionOptions();
if (this.gpuDeviceId >= 0) {
// Run on a GPU or with another provider
sessionOptions.addCUDA(this.gpuDeviceId);
sessionOptions.addCUDA(this.gpuDeviceId); // Run on a GPU or with another
// provider
}
this.session = this.environment.createSession(getCachedResource(this.modelResource).getContentAsByteArray(),
sessionOptions);
logger.info("Model input names: " + this.session.getInputNames().stream().collect(Collectors.joining(", ")));
logger.info("Model output names: " + this.session.getOutputNames().stream().collect(Collectors.joining(", ")));
}
private Resource getCachedResource(Resource resource) {
return this.disableCaching ? resource : this.cache.getCachedResource(resource);
return this.disableCaching ? resource : this.cacheService.getCachedResource(resource);
}
@Override
@@ -186,6 +221,9 @@ public class TransformersEmbeddingClient implements EmbeddingClient, Initializin
Map<String, OnnxTensor> modelInputs = Map.of("input_ids", inputIds, "attention_mask", attentionMask,
"token_type_ids", tokenTypeIds);
// The Run result object is AutoCloseable to prevent references from leaking
// out. Once the Result object is
// closed, all it’s child OnnxValues are closed too.
try (OrtSession.Result results = this.session.run(modelInputs)) {
// OnnxValue lastHiddenState = results.get(0);

2
embedding-clients/transformers-embedding/src/test/java/org/springframework/ai/embedding/TransformersEmbeddingClientTests.java
View File

@@ -16,11 +16,9 @@
package org.springframework.ai.embedding;
import java.io.File;
import java.util.List;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.io.TempDir;
import org.springframework.ai.document.Document;

2
spring-ai-huggingface/README.md
View File

@@ -10,7 +10,7 @@ Add the `spring-ai-huggingface` dependency:
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>spring-ai-huggingface</artifactId>
<version>0.7.0-SNAPSHOT</version>
<version>0.7.1-SNAPSHOT</version>
</dependency>
```

16
spring-ai-spring-boot-autoconfigure/pom.xml
View File

@@ -49,6 +49,14 @@
<optional>true</optional>
</dependency>
<!-- Transformers Embedding Client -->
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>transformers-embedding</artifactId>
<version>${project.parent.version}</version>
<optional>true</optional>
</dependency>
<!-- Pinecone Vector Store-->
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
@@ -87,7 +95,6 @@
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-configuration-processor</artifactId>
@@ -125,13 +132,6 @@
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>transformers-embedding</artifactId>
<version>${parent.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testcontainers</groupId>
<artifactId>testcontainers</artifactId>

57
spring-ai-spring-boot-autoconfigure/src/main/java/org/springframework/ai/autoconfigure/embedding/transformer/TransformersEmbeddingClientAutoConfiguration.java Normal file
View File

@@ -0,0 +1,57 @@
/*
* Copyright 2023-2023 the original author or authors.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.springframework.ai.autoconfigure.embedding.transformer;
import ai.djl.huggingface.tokenizers.HuggingFaceTokenizer;
import ai.onnxruntime.OrtSession;
import org.springframework.ai.embedding.EmbeddingClient;
import org.springframework.ai.embedding.TransformersEmbeddingClient;
import org.springframework.boot.autoconfigure.AutoConfiguration;
import org.springframework.boot.autoconfigure.condition.ConditionalOnClass;
import org.springframework.boot.autoconfigure.condition.ConditionalOnMissingBean;
import org.springframework.boot.context.properties.EnableConfigurationProperties;
import org.springframework.context.annotation.Bean;
/**
* @author Christian Tzolov
*/
@AutoConfiguration
@EnableConfigurationProperties({ TransformersEmbeddingClientProperties.class })
@ConditionalOnClass({ OrtSession.class, HuggingFaceTokenizer.class })
public class TransformersEmbeddingClientAutoConfiguration {
@Bean
@ConditionalOnMissingBean
public EmbeddingClient embeddingClient(TransformersEmbeddingClientProperties properties) {
TransformersEmbeddingClient embeddingClient = new TransformersEmbeddingClient(properties.getMetadataMode());
embeddingClient.setDisableCaching(!properties.getCache().isEnabled());
embeddingClient.setResourceCacheDirectory(properties.getCache().getDirectory());
embeddingClient.setTokenizerResource(properties.getTokenizer().getUri());
embeddingClient.setTokenizerOptions(properties.getTokenizer().getOptions());
embeddingClient.setModelResource(properties.getOnnx().getModelUri());
embeddingClient.setGpuDeviceId(properties.getOnnx().getGpuDeviceId());
return embeddingClient;
}
}

188
spring-ai-spring-boot-autoconfigure/src/main/java/org/springframework/ai/autoconfigure/embedding/transformer/TransformersEmbeddingClientProperties.java Normal file
View File

@@ -0,0 +1,188 @@
/*
* Copyright 2023-2023 the original author or authors.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.springframework.ai.autoconfigure.embedding.transformer;
import java.io.File;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import ai.djl.huggingface.tokenizers.HuggingFaceTokenizer;
import org.springframework.ai.document.Document;
import org.springframework.ai.document.MetadataMode;
import org.springframework.ai.embedding.TransformersEmbeddingClient;
import org.springframework.boot.context.properties.ConfigurationProperties;
import static org.springframework.ai.autoconfigure.embedding.transformer.TransformersEmbeddingClientProperties.CONFIG_PREFIX;
/**
* @author Christian Tzolov
*/
@ConfigurationProperties(CONFIG_PREFIX)
public class TransformersEmbeddingClientProperties {
public static final String CONFIG_PREFIX = "spring.ai.embedding.transformer";
public static final String DEFAULT_CACHE_DIRECTORY = new File(System.getProperty("java.io.tmpdir"),
"spring-ai-onnx-model")
.getAbsolutePath();
/**
* Configurations for the {@link HuggingFaceTokenizer} used to convert sentences into
* tokens.
*/
public static class Tokenizer {
/**
* URI of a pre-trained HuggingFaceTokenizer created by the ONNX engine (e.g.
* tokenizer.json).
*/
private String uri = TransformersEmbeddingClient.DEFAULT_ONNX_TOKENIZER_URI;
/**
* HuggingFaceTokenizer options such as 'addSpecialTokens', 'modelMaxLength',
* 'truncation', 'padding', 'maxLength', 'stride' and 'padToMultipleOf'. Leave
* empty to fallback to the defaults.
*/
private Map<String, String> options = new HashMap<>();
public String getUri() {
return uri;
}
public void setUri(String uri) {
this.uri = uri;
}
public Map<String, String> getOptions() {
return options;
}
public void setOptions(Map<String, String> options) {
this.options = options;
}
}
private final Tokenizer tokenizer = new Tokenizer();
public static class Cache {
/**
* Enable the {@link Resource} caching.
*/
private boolean enabled = true;
/**
* Resource cache directory. Used to cache remote resources, such as the ONNX
* models, to the local file system. Applicable only for cache.enabled == true.
* Defaults to {java.io.tmpdir}/spring-ai-onnx-model.
*/
private String directory = DEFAULT_CACHE_DIRECTORY;
public boolean isEnabled() {
return enabled;
}
public void setEnabled(boolean enabled) {
this.enabled = enabled;
}
public String getDirectory() {
return directory;
}
public void setDirectory(String directory) {
this.directory = directory;
}
}
/**
* Controls caching of remote, large resources to local file system.
*/
private final Cache cache = new Cache();
public Cache getCache() {
return cache;
}
public static class Onnx {
/**
* Existing, pre-trained ONNX model. Commonly exported from
* https://sbert.net/docs/pretrained_models.html. Defaults to
* sentence-transformers/all-MiniLM-L6-v2.
*/
private String modelUri = TransformersEmbeddingClient.DEFAULT_ONNX_MODEL_URI;
/**
* Run on a GPU or with another provider (optional).
* https://onnxruntime.ai/docs/get-started/with-java.html#run-on-a-gpu-or-with-another-provider-optional
*
* The GPU device ID to execute on. Only applicable if >= 0. Ignored otherwise.
*/
private int gpuDeviceId = -1;
public String getModelUri() {
return modelUri;
}
public void setModelUri(String modelUri) {
this.modelUri = modelUri;
}
public int getGpuDeviceId() {
return gpuDeviceId;
}
public void setGpuDeviceId(int gpuDeviceId) {
this.gpuDeviceId = gpuDeviceId;
}
}
private final Onnx onnx = new Onnx();
public Onnx getOnnx() {
return onnx;
}
/**
* Specifies what parts of the {@link Document}'s content and metadata will be used
* for computing the embeddings. Applicable for the
* {@link TransformersEmbeddingClient#embed(Document)} method only. Has no effect on
* the {@link TransformersEmbeddingClient#embed(String)} or
* {@link TransformersEmbeddingClient#embed(List)}. Defaults to
* {@link MetadataMode#NONE}.
*/
private MetadataMode metadataMode = MetadataMode.NONE;
public Tokenizer getTokenizer() {
return tokenizer;
}
public MetadataMode getMetadataMode() {
return metadataMode;
}
public void setMetadataMode(MetadataMode metadataMode) {
this.metadataMode = metadataMode;
}
}

92
spring-ai-spring-boot-autoconfigure/src/test/java/org/springframework/ai/autoconfigure/embedding/transformer/TransformersEmbeddingClientAutoConfigurationIT.java Normal file
View File

@@ -0,0 +1,92 @@
/*
* Copyright 2023-2023 the original author or authors.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.springframework.ai.autoconfigure.embedding.transformer;
import java.io.File;
import java.util.List;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.io.TempDir;
import org.springframework.ai.embedding.EmbeddingClient;
import org.springframework.ai.embedding.TransformersEmbeddingClient;
import org.springframework.boot.autoconfigure.AutoConfigurations;
import org.springframework.boot.test.context.runner.ApplicationContextRunner;
import static org.assertj.core.api.Assertions.assertThat;
/**
* @author Christian Tzolov
*/
public class TransformersEmbeddingClientAutoConfigurationIT {
@TempDir
File tempDir;
private final ApplicationContextRunner contextRunner = new ApplicationContextRunner()
.withConfiguration(AutoConfigurations.of(TransformersEmbeddingClientAutoConfiguration.class));
@Test
public void embedding() {
contextRunner.run(context -> {
var properties = context.getBean(TransformersEmbeddingClientProperties.class);
assertThat(properties.getCache().isEnabled()).isTrue();
assertThat(properties.getCache().getDirectory())
.isEqualTo(new File(System.getProperty("java.io.tmpdir"), "spring-ai-onnx-model").getAbsolutePath());
EmbeddingClient embeddingClient = context.getBean(EmbeddingClient.class);
assertThat(embeddingClient).isInstanceOf(TransformersEmbeddingClient.class);
List<List<Double>> embeddings = embeddingClient.embed(List.of("Spring Framework", "Spring AI"));
assertThat(embeddings.size()).isEqualTo(2); // batch size
assertThat(embeddings.get(0).size()).isEqualTo(embeddingClient.dimensions()); // dimensions
// size
});
}
@Test
public void remoteOnnxModel() {
// https://huggingface.co/intfloat/e5-small-v2
contextRunner.withPropertyValues("spring.ai.embedding.transformer.cache.directory=" + tempDir.getAbsolutePath(),
"spring.ai.embedding.transformer.onnx.modelUri=https://huggingface.co/intfloat/e5-small-v2/resolve/main/model.onnx",
"spring.ai.embedding.transformer.tokenizer.uri=https://huggingface.co/intfloat/e5-small-v2/raw/main/tokenizer.json")
.run(context -> {
var properties = context.getBean(TransformersEmbeddingClientProperties.class);
assertThat(properties.getOnnx().getModelUri())
.isEqualTo("https://huggingface.co/intfloat/e5-small-v2/resolve/main/model.onnx");
assertThat(properties.getTokenizer().getUri())
.isEqualTo("https://huggingface.co/intfloat/e5-small-v2/raw/main/tokenizer.json");
assertThat(properties.getCache().isEnabled()).isTrue();
assertThat(properties.getCache().getDirectory()).isEqualTo(tempDir.getAbsolutePath());
assertThat(tempDir.listFiles()).hasSize(2);
EmbeddingClient embeddingClient = context.getBean(EmbeddingClient.class);
assertThat(embeddingClient).isInstanceOf(TransformersEmbeddingClient.class);
assertThat(embeddingClient.dimensions()).isEqualTo(384);
List<List<Double>> embeddings = embeddingClient.embed(List.of("Spring Framework", "Spring AI"));
assertThat(embeddings.size()).isEqualTo(2); // batch size
assertThat(embeddings.get(0).size()).isEqualTo(embeddingClient.dimensions()); // dimensions
// size
});
}
}

3
spring-ai-spring-boot-autoconfigure/src/test/java/org/springframework/ai/autoconfigure/vectorstore/milvus/MilvusVectorStoreAutoConfigurationIT.java
View File

@@ -27,12 +27,10 @@ import java.util.UUID;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.springframework.core.io.DefaultResourceLoader;
import org.testcontainers.containers.DockerComposeContainer;
import org.testcontainers.containers.wait.strategy.Wait;
import org.testcontainers.junit.jupiter.Testcontainers;
import org.springframework.ai.ResourceUtils;
import org.springframework.ai.document.Document;
import org.springframework.ai.embedding.EmbeddingClient;
import org.springframework.ai.embedding.TransformersEmbeddingClient;
@@ -42,6 +40,7 @@ import org.springframework.boot.autoconfigure.AutoConfigurations;
import org.springframework.boot.test.context.runner.ApplicationContextRunner;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.core.io.DefaultResourceLoader;
import org.springframework.util.FileSystemUtils;
import static org.assertj.core.api.Assertions.assertThat;

51
spring-ai-spring-boot-starters/spring-ai-starter-transformers-embedding/pom.xml Normal file
View File

@@ -0,0 +1,51 @@
<?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/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>spring-ai</artifactId>
<version>0.7.1-SNAPSHOT</version>
<relativePath>../../pom.xml</relativePath>
</parent>
<artifactId>spring-ai-transformers-embedding-spring-boot-starter</artifactId>
<packaging>jar</packaging>
<name>Spring AI Starter - Transformers Embedding</name>
<description>Spring Transformers Embedding Auto Configuration</description>
<url>https://github.com/spring-projects-experimental/spring-ai</url>
<scm>
<url>https://github.com/spring-projects-experimental/spring-ai</url>
<connection>git://github.com/spring-projects-experimental/spring-ai.git</connection>
<developerConnection>git@github.com:spring-projects-experimental/spring-ai.git</developerConnection>
</scm>
<dependencies>
<!-- production dependencies -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>spring-ai-spring-boot-autoconfigure</artifactId>
<version>${project.parent.version}</version>
</dependency>
<dependency>
<groupId>org.springframework.experimental.ai</groupId>
<artifactId>transformers-embedding</artifactId>
<version>${project.parent.version}</version>
</dependency>
<!-- test dependencies -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-test</artifactId>
<scope>test</scope>
</dependency>
</dependencies>
</project>

5
vector-stores/spring-ai-milvus-store/src/test/java/org/springframework/ai/vectorstore/MilvusVectorStoreIT.java
View File

@@ -310,11 +310,6 @@ public class MilvusVectorStoreIT {
return new OpenAiEmbeddingClient(new OpenAiService(api), "text-embedding-ada-002");
}
// @Bean
// public EmbeddingClient embeddingClient() {
// return new TransformersEmbeddingClient();
// }
}
}