OpenAi Chat/Embedding options handling optimizations
- Also restructure and clean the openai chat/embedding docs. Address review comments
This commit is contained in:
Christian Tzolov
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
* Copyright 2023-2023 the original author or authors.
|
||||
* Copyright 2023-2024 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.
|
||||
|
||||
@@ -26,6 +26,7 @@ import org.springframework.ai.document.Document;
|
||||
import org.springframework.ai.document.MetadataMode;
|
||||
import org.springframework.ai.embedding.AbstractEmbeddingClient;
|
||||
import org.springframework.ai.embedding.Embedding;
|
||||
import org.springframework.ai.embedding.EmbeddingOptions;
|
||||
import org.springframework.ai.embedding.EmbeddingRequest;
|
||||
import org.springframework.ai.embedding.EmbeddingResponse;
|
||||
import org.springframework.ai.embedding.EmbeddingResponseMetadata;
|
||||
@@ -51,9 +52,7 @@ public class OpenAiEmbeddingClient extends AbstractEmbeddingClient {
|
||||
|
||||
public static final String DEFAULT_OPENAI_EMBEDDING_MODEL = "text-embedding-ada-002";
|
||||
|
||||
private OpenAiEmbeddingOptions defaultOptions = OpenAiEmbeddingOptions.builder()
|
||||
.withModel(DEFAULT_OPENAI_EMBEDDING_MODEL)
|
||||
.build();
|
||||
private final OpenAiEmbeddingOptions defaultOptions;
|
||||
|
||||
private final RetryTemplate retryTemplate = RetryTemplate.builder()
|
||||
.maxAttempts(10)
|
||||
@@ -76,15 +75,18 @@ public class OpenAiEmbeddingClient extends AbstractEmbeddingClient {
|
||||
}
|
||||
|
||||
public OpenAiEmbeddingClient(OpenAiApi openAiApi, MetadataMode metadataMode) {
|
||||
Assert.notNull(openAiApi, "OpenAiService must not be null");
|
||||
Assert.notNull(metadataMode, "metadataMode must not be null");
|
||||
this.openAiApi = openAiApi;
|
||||
this.metadataMode = metadataMode;
|
||||
this(openAiApi, metadataMode,
|
||||
OpenAiEmbeddingOptions.builder().withModel(DEFAULT_OPENAI_EMBEDDING_MODEL).build());
|
||||
}
|
||||
|
||||
public OpenAiEmbeddingClient withDefaultOptions(OpenAiEmbeddingOptions options) {
|
||||
public OpenAiEmbeddingClient(OpenAiApi openAiApi, MetadataMode metadataMode, OpenAiEmbeddingOptions options) {
|
||||
Assert.notNull(openAiApi, "OpenAiService must not be null");
|
||||
Assert.notNull(metadataMode, "metadataMode must not be null");
|
||||
Assert.notNull(options, "options must not be null");
|
||||
|
||||
this.openAiApi = openAiApi;
|
||||
this.metadataMode = metadataMode;
|
||||
this.defaultOptions = options;
|
||||
return this;
|
||||
}
|
||||
|
||||
@Override
|
||||
@@ -93,19 +95,20 @@ public class OpenAiEmbeddingClient extends AbstractEmbeddingClient {
|
||||
return this.embed(document.getFormattedContent(this.metadataMode));
|
||||
}
|
||||
|
||||
@SuppressWarnings("unchecked")
|
||||
@Override
|
||||
public EmbeddingResponse call(EmbeddingRequest request) {
|
||||
|
||||
return this.retryTemplate.execute(ctx -> {
|
||||
org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest<List<String>> apiRequest = new org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest<>(
|
||||
request.getInstructions(), DEFAULT_OPENAI_EMBEDDING_MODEL);
|
||||
|
||||
if (this.defaultOptions != null) {
|
||||
apiRequest = ModelOptionsUtils.merge(apiRequest, this.defaultOptions,
|
||||
org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest.class);
|
||||
}
|
||||
org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest<List<String>> apiRequest = (this.defaultOptions != null)
|
||||
? new org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest<>(request.getInstructions(),
|
||||
this.defaultOptions.getModel(), this.defaultOptions.getEncodingFormat(),
|
||||
this.defaultOptions.getUser())
|
||||
: new org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest<>(request.getInstructions(),
|
||||
DEFAULT_OPENAI_EMBEDDING_MODEL);
|
||||
|
||||
if (request.getOptions() != null) {
|
||||
if (request.getOptions() != null && !EmbeddingOptions.EMPTY.equals(request.getOptions())) {
|
||||
apiRequest = ModelOptionsUtils.merge(request.getOptions(), apiRequest,
|
||||
org.springframework.ai.openai.api.OpenAiApi.EmbeddingRequest.class);
|
||||
}
|
||||
|
||||
@@ -2,14 +2,11 @@
|
||||
|
||||
Spring AI supports ChatGPT, the AI language model by OpenAI. ChatGPT has been instrumental in sparking interest in AI-driven text generation, thanks to its creation of industry-leading text generation models and embeddings.
|
||||
|
||||
== Getting Started
|
||||
== Pre-requisites
|
||||
|
||||
You will need to create an API with OpenAI to access ChatGPT models.
|
||||
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
@@ -17,9 +14,114 @@ Exporting an environment variable is one way to set that configuration property:
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
----
|
||||
|
||||
=== Configure the OpenAI Chat Client Manually
|
||||
== Auto-configuration
|
||||
|
||||
Add the `spring-ai-openai` dependency to your project's Maven `pom.xml` file:
|
||||
Spring AI provides Spring Boot auto-configuration for the OpenAI Chat Client.
|
||||
To enable it add the following dependency to your project's Maven `pom.xml` file:
|
||||
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
<groupId>org.springframework.ai</groupId>
|
||||
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
|
||||
<version>0.8.0-SNAPSHOT</version>
|
||||
</dependency>
|
||||
----
|
||||
|
||||
or to your Gradle `build.gradle` build file.
|
||||
|
||||
[source,groovy]
|
||||
----
|
||||
dependencies {
|
||||
implementation 'org.springframework.ai:spring-ai-openai-spring-boot-starter:0.8.0-SNAPSHOT'
|
||||
}
|
||||
----
|
||||
|
||||
NOTE: Refer to the xref:getting-started.adoc#_dependency_management[Dependency Management] section to add Milestone and/or Snapshot Repositories to your build file.
|
||||
|
||||
=== Chat Properties
|
||||
|
||||
The prefix `spring.ai.openai` is used as the property prefix that lets you connect to OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.base-url | The URL to connect to | https://api.openai.com
|
||||
| spring.ai.openai.api-key | The API Key | -
|
||||
|====
|
||||
|
||||
The prefix `spring.ai.openai.chat` is the property prefix that lets you configure the `ChatClient` implementation for OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.chat.base-url | Optional overrides the spring.ai.openai.base-url to provide chat specific url | -
|
||||
| spring.ai.openai.chat.api-key | Optional overrides the spring.ai.openai.api-key to provide chat specific api-key | -
|
||||
| spring.ai.openai.chat.options.model | This is the OpenAI Chat model to use | `gpt-35-turbo` (the `gpt-3.5-turbo`, `gpt-4`, and `gpt-4-32k` point to the latest model versions)
|
||||
| spring.ai.openai.chat.options.temperature | The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. | 0.8
|
||||
| spring.ai.openai.chat.options.frequencyPenalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. | 0.0f
|
||||
| spring.ai.openai.chat.options.logitBias | Modify the likelihood of specified tokens appearing in the completion. | -
|
||||
| spring.ai.openai.chat.options.maxTokens | The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. | -
|
||||
| spring.ai.openai.chat.options.n | How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs. | 1
|
||||
| spring.ai.openai.chat.options.presencePenalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. | -
|
||||
| spring.ai.openai.chat.options.responseFormat | An object specifying the format that the model must output. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON.| -
|
||||
| spring.ai.openai.chat.options.seed | This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. | -
|
||||
| spring.ai.openai.chat.options.stop | Up to 4 sequences where the API will stop generating further tokens. | -
|
||||
| spring.ai.openai.chat.options.topP | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. | -
|
||||
| spring.ai.openai.chat.options.tools | A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. | -
|
||||
| spring.ai.openai.chat.options.toolChoice | Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present. | -
|
||||
| spring.ai.openai.chat.options.user | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. | -
|
||||
|====
|
||||
|
||||
NOTE: You can override the common `spring.ai.openai.base-url` and `spring.ai.openai.api-key` for the `ChatClient` and `EmbeddingClient` implementations.
|
||||
The `spring.ai.openai.chat.base-url` and `spring.ai.openai.chat.api-key` properties if set take precedence over the common properties.
|
||||
This is useful if you want to use different OpenAI accounts for different models and different model endpoints.
|
||||
|
||||
=== Sample Code
|
||||
|
||||
This will create a `ChatClient` implementation that you can inject into your class.
|
||||
Here is an example of a simple `@Controller` class that uses the `ChatClient` implementation.
|
||||
|
||||
[source,application.properties]
|
||||
----
|
||||
spring.ai.openai.api-key=YOUR_API_KEY
|
||||
spring.ai.openai.chat.options.model=gpt-35-turbo
|
||||
spring.ai.openai.chat.options.temperature=0.7
|
||||
----
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@RestController
|
||||
public class ChatController {
|
||||
|
||||
private final ChatClient chatClient;
|
||||
private final StreamingChatClient streamingChatClient;
|
||||
|
||||
@Autowired
|
||||
public ChatController(ChatClient chatClient, StreamingChatClient streamingChatClient) {
|
||||
this.chatClient = chatClient;
|
||||
this.streamingChatClient = streamingChatClient;
|
||||
}
|
||||
|
||||
@GetMapping("/open-ai/generate")
|
||||
public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
return Map.of("generation", chatClient.call(message));
|
||||
}
|
||||
|
||||
@GetMapping("/open-ai/generateStream")
|
||||
public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
Prompt prompt = new Prompt(new UserMessage(message));
|
||||
return streamingChatClient.stream(prompt);
|
||||
}
|
||||
}
|
||||
----
|
||||
|
||||
== Manual Configuration
|
||||
|
||||
If you are not using Spring Boot, you can manually configure the `OpenAiChatClient` by creating the beans in your configuration class.
|
||||
For this add the `spring-ai-openai` dependency to your project's Maven `pom.xml` file:
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
@@ -64,12 +166,11 @@ Flux<ChatResponse> response = chatClient.stream(
|
||||
The `OpenAiChatOptions` provides the configuration information for the chat requests.
|
||||
The `OpenAiChatOptions.Builder` is fluent options builder.
|
||||
|
||||
==== ChatOptions and OpenAiChatOptions
|
||||
=== Chat Options
|
||||
|
||||
The https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiChatOptions.java[OpenAiChatOptions.java] provides provides the configuration information for the chat requests, such as the model to use, the temperature, the frequency penalty, etc.
|
||||
|
||||
The default options can be configured using the `spring.ai.openai.chat.options` properties as well.
|
||||
|
||||
On start-time use the `OpenAiChatClient#withDefaultOptions()` to set the default options applicable for all chat completion requests.
|
||||
At run-time you can override the default options with `OpenAiChatOptions` instance in the request `Prompt`.
|
||||
|
||||
@@ -90,116 +191,3 @@ ChatResponse response = chatClient.call(
|
||||
You can use as prompt options any instance that implements the portable `ChatOptions` interface.
|
||||
For example you can use the `ChatOptionsBuilder` to create a portable prompt options.
|
||||
|
||||
=== OpenAiChatClient Auto-configuration
|
||||
|
||||
Spring AI provides Spring Boot auto-configuration for the OpenAI Chat Client.
|
||||
To enable it add the following dependency to your project's Maven `pom.xml` file:
|
||||
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
<groupId>org.springframework.ai</groupId>
|
||||
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
|
||||
<version>0.8.0-SNAPSHOT</version>
|
||||
</dependency>
|
||||
----
|
||||
|
||||
or to your Gradle `build.gradle` build file.
|
||||
|
||||
[source,groovy]
|
||||
----
|
||||
dependencies {
|
||||
implementation 'org.springframework.ai:spring-ai-openai-spring-boot-starter:0.8.0-SNAPSHOT'
|
||||
}
|
||||
----
|
||||
|
||||
NOTE: Refer to the xref:getting-started.adoc#_dependency_management[Dependency Management] section to add Milestone and/or Snapshot Repositories to your build file.
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
----
|
||||
|
||||
==== Sample Code
|
||||
|
||||
This will create a `ChatClient` implementation that you can inject into your class.
|
||||
Here is an example of a simple `@Controller` class that uses the `ChatClient` implementation.
|
||||
|
||||
[source,application.properties]
|
||||
----
|
||||
spring.ai.openai.api-key=YOUR_API_KEY
|
||||
spring.ai.openai.chat.options.model=gpt-35-turbo
|
||||
spring.ai.openai.chat.options.temperature=0.7
|
||||
----
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@RestController
|
||||
public class ChatController {
|
||||
|
||||
private final ChatClient chatClient;
|
||||
private final StreamingChatClient streamingChatClient;
|
||||
|
||||
@Autowired
|
||||
public ChatController(ChatClient chatClient, StreamingChatClient streamingChatClient) {
|
||||
this.chatClient = chatClient;
|
||||
this.streamingChatClient = streamingChatClient;
|
||||
}
|
||||
|
||||
@GetMapping("/open-ai/generate")
|
||||
public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
return Map.of("generation", chatClient.call(message));
|
||||
}
|
||||
|
||||
@GetMapping("/open-ai/generateStream")
|
||||
public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
Prompt prompt = new Prompt(new UserMessage(message));
|
||||
return streamingChatClient.stream(prompt);
|
||||
}
|
||||
}
|
||||
----
|
||||
|
||||
== OpenAI Chat Properties
|
||||
|
||||
The prefix `spring.ai.openai` is used as the property prefix that lets you connect to OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.base-url | The URL to connect to | https://api.openai.com
|
||||
| spring.ai.openai.api-key | The API Key | -
|
||||
|====
|
||||
|
||||
The prefix `spring.ai.openai.chat` is the property prefix that lets you configure the `ChatClient` implementation for OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.chat.base-url | Optional overrides the spring.ai.openai.base-url to provide chat specific url | -
|
||||
| spring.ai.openai.chat.api-key | Optional overrides the spring.ai.openai.api-key to provide chat specific api-key | -
|
||||
| spring.ai.openai.chat.options.model | This is the OpenAI Chat model to use | `gpt-35-turbo` (the `gpt-3.5-turbo`, `gpt-4`, and `gpt-4-32k` point to the latest model versions)
|
||||
| spring.ai.openai.chat.options.temperature | The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. | 0.8
|
||||
| spring.ai.openai.chat.options.frequencyPenalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. | 0.0f
|
||||
| spring.ai.openai.chat.options.logitBias | Modify the likelihood of specified tokens appearing in the completion. | -
|
||||
| spring.ai.openai.chat.options.maxTokens | The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. | -
|
||||
| spring.ai.openai.chat.options.n | How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs. | 1
|
||||
| spring.ai.openai.chat.options.presencePenalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. | -
|
||||
| spring.ai.openai.chat.options.responseFormat | An object specifying the format that the model must output. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON.| -
|
||||
| spring.ai.openai.chat.options.seed | This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. | -
|
||||
| spring.ai.openai.chat.options.stop | Up to 4 sequences where the API will stop generating further tokens. | -
|
||||
| spring.ai.openai.chat.options.topP | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. | -
|
||||
| spring.ai.openai.chat.options.tools | A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. | -
|
||||
| spring.ai.openai.chat.options.toolChoice | Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present. | -
|
||||
| spring.ai.openai.chat.options.user | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. | -
|
||||
|====
|
||||
|
||||
|
||||
NOTE: You can override the common `spring.ai.openai.base-url` and `spring.ai.openai.api-key` for the `ChatClient` and `EmbeddingClient` implementations.
|
||||
The `spring.ai.openai.chat.base-url` and `spring.ai.openai.chat.api-key` properties if set take precedence over the common properties.
|
||||
This is useful if you want to use different OpenAI accounts for different models and different model endpoints.
|
||||
|
||||
@@ -4,14 +4,12 @@ Spring AI supports the OpenAI's text embeddings models.
|
||||
OpenAI’s text embeddings measure the relatedness of text strings.
|
||||
An embedding is a vector (list) of floating point numbers. The distance between two vectors measures their relatedness. Small distances suggest high relatedness and large distances suggest low relatedness.
|
||||
|
||||
== Getting Started
|
||||
== Pre-requisites
|
||||
|
||||
You will need to create an API with OpenAI to access OpenAI embeddings models.
|
||||
|
||||
Create an account at https://platform.openai.com/signup[OpenAI signup page] and generate the token on the https://platform.openai.com/account/api-keys[API Keys page].
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
@@ -19,9 +17,96 @@ Exporting an environment variable is one way to set that configuration property:
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
----
|
||||
|
||||
=== Configure the OpenAI Embedding Client Manually
|
||||
== Auto-configuration
|
||||
|
||||
Add the `spring-ai-openai` dependency to your project's Maven `pom.xml` file:
|
||||
Spring AI provides Spring Boot auto-configuration for the Azure OpenAI Embedding Client.
|
||||
To enable it add the following dependency to your project's Maven `pom.xml` file:
|
||||
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
<groupId>org.springframework.ai</groupId>
|
||||
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
|
||||
<version>0.8.0-SNAPSHOT</version>
|
||||
</dependency>
|
||||
----
|
||||
|
||||
or to your Gradle `build.gradle` build file.
|
||||
|
||||
[source,groovy]
|
||||
----
|
||||
dependencies {
|
||||
implementation 'org.springframework.ai:spring-ai-openai-spring-boot-starter:0.8.0-SNAPSHOT'
|
||||
}
|
||||
----
|
||||
|
||||
NOTE: Refer to the xref:getting-started.adoc#_dependency_management[Dependency Management] section to add Milestone and/or Snapshot Repositories to your build file.
|
||||
|
||||
=== Embedding Properties
|
||||
|
||||
The prefix `spring.ai.openai` is used as the property prefix that lets you connect to OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.base-url | The URL to connect to | https://api.openai.com
|
||||
| spring.ai.openai.api-key | The API Key | -
|
||||
|====
|
||||
|
||||
The prefix `spring.ai.openai.embedding` is property prefix that configures the `EmbeddingClient` implementation for OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
| spring.ai.openai.embedding.base-url | Optional overrides the spring.ai.openai.base-url to provide embedding specific url | -
|
||||
| spring.ai.openai.embedding.api-key | Optional overrides the spring.ai.openai.api-key to provide embedding specific api-key | -
|
||||
| spring.ai.openai.embedding.metadata-mode | Document content extraction mode | EMBED
|
||||
| spring.ai.openai.embedding.options.model | The model to use | text-embedding-ada-002
|
||||
| spring.ai.openai.embedding.options.encodingFormat | The format to return the embeddings in. Can be either float or base64. | -
|
||||
| spring.ai.openai.embedding.options.user | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. | -
|
||||
|====
|
||||
|
||||
NOTE: You can override the common `spring.ai.openai.base-url` and `spring.ai.openai.api-key` for the `ChatClient` and `EmbeddingClient` implementations.
|
||||
The `spring.ai.openai.embedding.base-url` and `spring.ai.openai.embedding.api-key` properties if set take precedence over the common properties.
|
||||
Similarly, the `spring.ai.openai.embedding.base-url` and `spring.ai.openai.embedding.api-key` properties if set take precedence over the common properties.
|
||||
This is useful if you want to use different OpenAI accounts for different models and different model endpoints.
|
||||
|
||||
=== Sample Controller
|
||||
|
||||
This will create a `EmbeddingClient` implementation that you can inject into your class.
|
||||
Here is an example of a simple `@Controller` class that uses the `EmbeddingClient` implementation.
|
||||
|
||||
[source,application.properties]
|
||||
----
|
||||
spring.ai.openai.api-key=YOUR_API_KEY
|
||||
spring.ai.openai.embedding.options.model=text-embedding-ada-002
|
||||
----
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@RestController
|
||||
public class EmbeddingController {
|
||||
|
||||
private final EmbeddingClient embeddingClient;
|
||||
|
||||
@Autowired
|
||||
public EmbeddingController(EmbeddingClient embeddingClient) {
|
||||
this.embeddingClient = embeddingClient;
|
||||
}
|
||||
|
||||
@GetMapping("/ai/embedding")
|
||||
public Map embed(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
EmbeddingResponse embeddingResponse = this.embeddingClient.embedForResponse(List.of(message));
|
||||
return Map.of("embedding", embeddingResponse);
|
||||
}
|
||||
}
|
||||
----
|
||||
|
||||
== Manual Configuration
|
||||
|
||||
If you are not using Spring Boot, you can manually configure the OpenAI Embedding Client.
|
||||
For this add the `spring-ai-openai` dependency to your project's Maven `pom.xml` file:
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
@@ -62,7 +147,7 @@ EmbeddingResponse embeddingResponse = embeddingClient
|
||||
The `OpenAiEmbeddingOptions` provides the configuration information for the embedding requests.
|
||||
The options class offers a `builder()` for easy options creation.
|
||||
|
||||
==== OpenAiEmbeddingOptions
|
||||
=== Embedding Options
|
||||
|
||||
The https://github.com/spring-projects/spring-ai/blob/main/models/spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiEmbeddingOptions.java[OpenAiEmbeddingOptions.java] provides the OpenAI configurations, such as the model to use and etc.
|
||||
|
||||
@@ -82,99 +167,3 @@ EmbeddingResponse embeddingResponse = embeddingClient.call(
|
||||
.build()));
|
||||
----
|
||||
|
||||
=== OpenAiEmbeddingClient Auto-configuration
|
||||
|
||||
Spring AI provides Spring Boot auto-configuration for the Azure OpenAI Embedding Client.
|
||||
To enable it add the following dependency to your project's Maven `pom.xml` file:
|
||||
|
||||
[source, xml]
|
||||
----
|
||||
<dependency>
|
||||
<groupId>org.springframework.ai</groupId>
|
||||
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
|
||||
<version>0.8.0-SNAPSHOT</version>
|
||||
</dependency>
|
||||
----
|
||||
|
||||
or to your Gradle `build.gradle` build file.
|
||||
|
||||
[source,groovy]
|
||||
----
|
||||
dependencies {
|
||||
implementation 'org.springframework.ai:spring-ai-openai-spring-boot-starter:0.8.0-SNAPSHOT'
|
||||
}
|
||||
----
|
||||
|
||||
NOTE: Refer to the xref:getting-started.adoc#_dependency_management[Dependency Management] section to add Milestone and/or Snapshot Repositories to your build file.
|
||||
|
||||
The Spring AI project defines a configuration property named `spring.ai.openai.api-key` that you should set to the value of the `API Key` obtained from openai.com.
|
||||
|
||||
Exporting an environment variable is one way to set that configuration property:
|
||||
|
||||
[source,shell]
|
||||
----
|
||||
export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>
|
||||
----
|
||||
|
||||
The `spring.ai.openai.embedding.options.*` properties are used to configure the default options used for all embedding requests.
|
||||
|
||||
==== Sample Embedding Controller
|
||||
|
||||
This will create a `EmbeddingClient` implementation that you can inject into your class.
|
||||
Here is an example of a simple `@Controller` class that uses the `EmbeddingClient` implementation.
|
||||
|
||||
[source,application.properties]
|
||||
----
|
||||
spring.ai.openai.api-key=YOUR_API_KEY
|
||||
spring.ai.openai.embedding.options.model=text-embedding-ada-002
|
||||
----
|
||||
|
||||
[source,java]
|
||||
----
|
||||
@RestController
|
||||
public class EmbeddingController {
|
||||
|
||||
private final EmbeddingClient embeddingClient;
|
||||
|
||||
@Autowired
|
||||
public EmbeddingController(EmbeddingClient embeddingClient) {
|
||||
this.embeddingClient = embeddingClient;
|
||||
}
|
||||
|
||||
@GetMapping("/ai/embedding")
|
||||
public Map embed(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
|
||||
EmbeddingResponse embeddingResponse = this.embeddingClient.embedForResponse(List.of(message));
|
||||
return Map.of("embedding", embeddingResponse);
|
||||
}
|
||||
}
|
||||
----
|
||||
|
||||
== OpenAI Embedding Properties
|
||||
|
||||
The prefix `spring.ai.openai` is used as the property prefix that lets you connect to OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
|
||||
| spring.ai.openai.base-url | The URL to connect to | https://api.openai.com
|
||||
| spring.ai.openai.api-key | The API Key | -
|
||||
|====
|
||||
|
||||
|
||||
The prefix `spring.ai.openai.embedding` is property prefix that configures the `EmbeddingClient` implementation for OpenAI.
|
||||
|
||||
[cols="3,5,1"]
|
||||
|====
|
||||
| Property | Description | Default
|
||||
| spring.ai.openai.embedding.base-url | Optional overrides the spring.ai.openai.base-url to provide embedding specific url | -
|
||||
| spring.ai.openai.embedding.api-key | Optional overrides the spring.ai.openai.api-key to provide embedding specific api-key | -
|
||||
| spring.ai.openai.embedding.options.model | The model to use | text-embedding-ada-002
|
||||
| spring.ai.openai.embedding.options.encodingFormat | The format to return the embeddings in. Can be either float or base64. | -
|
||||
| spring.ai.openai.embedding.options.user | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. | -
|
||||
|====
|
||||
|
||||
NOTE: You can override the common `spring.ai.openai.base-url` and `spring.ai.openai.api-key` for the `ChatClient` and `EmbeddingClient` implementations.
|
||||
The `spring.ai.openai.embedding.base-url` and `spring.ai.openai.embedding.api-key` properties if set take precedence over the common properties.
|
||||
Similarly, the `spring.ai.openai.embedding.base-url` and `spring.ai.openai.embedding.api-key` properties if set take precedence over the common properties.
|
||||
This is useful if you want to use different OpenAI accounts for different models and different model endpoints.
|
||||
|
||||
@@ -81,7 +81,8 @@ public class OpenAiAutoConfiguration {
|
||||
|
||||
var openAiApi = new OpenAiApi(baseUrl, apiKey, restClientBuilder);
|
||||
|
||||
return new OpenAiEmbeddingClient(openAiApi).withDefaultOptions(embeddingProperties.getOptions());
|
||||
return new OpenAiEmbeddingClient(openAiApi, embeddingProperties.getMetadataMode(),
|
||||
embeddingProperties.getOptions());
|
||||
}
|
||||
|
||||
@Bean
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
package org.springframework.ai.autoconfigure.openai;
|
||||
|
||||
import org.springframework.ai.document.MetadataMode;
|
||||
import org.springframework.ai.openai.OpenAiEmbeddingOptions;
|
||||
import org.springframework.boot.context.properties.ConfigurationProperties;
|
||||
import org.springframework.boot.context.properties.NestedConfigurationProperty;
|
||||
@@ -27,6 +28,8 @@ public class OpenAiEmbeddingProperties extends OpenAiParentProperties {
|
||||
|
||||
public static final String DEFAULT_EMBEDDING_MODEL = "text-embedding-ada-002";
|
||||
|
||||
private MetadataMode metadataMode = MetadataMode.EMBED;
|
||||
|
||||
@NestedConfigurationProperty
|
||||
private OpenAiEmbeddingOptions options = OpenAiEmbeddingOptions.builder()
|
||||
.withModel(DEFAULT_EMBEDDING_MODEL)
|
||||
@@ -40,4 +43,12 @@ public class OpenAiEmbeddingProperties extends OpenAiParentProperties {
|
||||
this.options = options;
|
||||
}
|
||||
|
||||
public MetadataMode getMetadataMode() {
|
||||
return metadataMode;
|
||||
}
|
||||
|
||||
public void setMetadataMode(MetadataMode metadataMode) {
|
||||
this.metadataMode = metadataMode;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user