LlmService

All Implemented Interfaces:

com.embabel.common.ai.model.LlmMetadata , com.embabel.common.ai.model.ModelMetadata , com.embabel.common.ai.prompt.PromptContributorConsumer
```
public interface LlmService<THIS extends LlmService<THIS>>
 implements LlmMetadata, PromptContributorConsumer
                    
```
Framework-agnostic LLM service abstraction, parallel to com.embabel.common.ai.model.EmbeddingService.
Implementations wrap specific LLM backends (Spring AI, direct API clients, etc.) and provide a consistent interface for creating message senders.
The type parameter THIS enables fluent builder-style methods that preserve the concrete type through method chaining.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`abstract LlmMessageSender`	`createMessageSender(LlmOptions options)`	Create a message sender for this LLM configured with the given options.
`abstract THIS`	`withKnowledgeCutoffDate(LocalDate date)`	Returns a copy of this LLM service with the specified knowledge cutoff date.
`abstract THIS`	`withPromptContributor(PromptContributor promptContributor)`	Returns a copy of this LLM service with an additional prompt contributor.

Methods inherited from class com.embabel.common.ai.model.LlmMetadata
getKnowledgeCutoffDate, getPricingModel, getType
Methods inherited from class com.embabel.common.ai.model.ModelMetadata
getName, getProvider
Methods inherited from class com.embabel.common.ai.prompt.PromptContributorConsumer
getPromptContributors
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - createMessageSender
```
 abstract LlmMessageSender createMessageSender(LlmOptions options)
```
    Create a message sender for this LLM configured with the given options.
    The message sender handles the actual LLM API calls but does NOT execute tools - it returns the LLM's response including any tool call requests.
    
    Parameters:
    
    options - Configuration options for the LLM call (temperature, max tokens, etc.
    
    Returns:
    
    A message sender configured for this LLM
  - withKnowledgeCutoffDate
```
 abstract THIS withKnowledgeCutoffDate(LocalDate date)
```
    Returns a copy of this LLM service with the specified knowledge cutoff date.
    
    Parameters:
    
    date - The knowledge cutoff date for the model
    
    Returns:
    
    A new instance with the updated cutoff date
  - withPromptContributor
```
 abstract THIS withPromptContributor(PromptContributor promptContributor)
```
    Returns a copy of this LLM service with an additional prompt contributor.
    
    Parameters:
    
    promptContributor - The prompt contributor to add
    
    Returns:
    
    A new instance with the added contributor