Support to autoconfigure multiple chat models at same time #3172
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Given:
```
implementation("org.springframework.ai:spring-ai-starter-model-deepseek")
implementation("org.springframework.ai:spring-ai-starter-model-ollama")
```
Application failed to start before this commit:
```
***************************
APPLICATION FAILED TO START
***************************
Description:
Parameter 1 of method chatClientBuilder in org.springframework.ai.model.chat.client.autoconfigure.ChatClientAutoConfiguration required a single bean, but 2 were found:
- deepSeekChatModel: defined by method 'deepSeekChatModel' in class path resource [org/springframework/ai/model/deepseek/autoconfigure/DeepSeekChatAutoConfiguration.class]
- ollamaChatModel: defined by method 'ollamaChatModel' in class path resource [org/springframework/ai/model/ollama/autoconfigure/OllamaChatAutoConfiguration.class]
```
After this commit, we could construct our own instead of autoconfigured `ChatClient.Builder` by injecting qualified `ChatModel`.
Related to spring-projectsGH-2221.
Signed-off-by: Yanming Zhou <zhouyanming@gmail.com>
|
Hi. How does this PR work to achieve the goal of injecting by qualified chat model? Holding off on this until the GA release. |
Application could define their own @Bean
@Scope("prototype")
ChatClient.Builder deepSeekChatClientBuilder(ChatClientBuilderConfigurer chatClientBuilderConfigurer, @Qualifier("deepSeekChatModel") ChatModel deepSeekChatModel,
ObjectProvider<ObservationRegistry> observationRegistry,
ObjectProvider<ChatClientObservationConvention> observationConvention) {
ChatClient.Builder builder = ChatClient.builder(deepSeekChatModel,
observationRegistry.getIfUnique(() -> ObservationRegistry.NOOP),
observationConvention.getIfUnique(() -> null));
return chatClientBuilderConfigurer.configure(builder);
}
@Bean
@Scope("prototype")
ChatClient.Builder ollamaChatClientBuilder(ChatClientBuilderConfigurer chatClientBuilderConfigurer, @Qualifier("ollamaChatModel") ChatModel ollamaChatModel,
ObjectProvider<ObservationRegistry> observationRegistry,
ObjectProvider<ChatClientObservationConvention> observationConvention) {
ChatClient.Builder builder = ChatClient.builder(ollamaChatModel,
observationRegistry.getIfUnique(() -> ObservationRegistry.NOOP),
observationConvention.getIfUnique(() -> null));
return chatClientBuilderConfigurer.configure(builder);
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Given:
Application failed to start before this commit:
After this commit, we could construct our own instead of autoconfigured
ChatClient.Builderby injecting qualifiedChatModel.Related to GH-2221.