Package dev.langchain4j.model.openai
Class OpenAiChatModel
java.lang.Object
dev.langchain4j.model.openai.OpenAiChatModel
- All Implemented Interfaces:
ChatLanguageModel
,TokenCountEstimator
Represents an OpenAI language model with a chat completion interface, such as gpt-3.5-turbo and gpt-4.
You can find description of parameters here.
-
Nested Class Summary
-
Constructor Summary
ConstructorDescriptionOpenAiChatModel
(String baseUrl, String apiKey, String organizationId, String modelName, Double temperature, Double topP, List<String> stop, Integer maxTokens, Integer maxCompletionTokens, Double presencePenalty, Double frequencyPenalty, Map<String, Integer> logitBias, String responseFormat, Boolean strictJsonSchema, Integer seed, String user, Boolean strictTools, Boolean parallelToolCalls, Duration timeout, Integer maxRetries, Proxy proxy, Boolean logRequests, Boolean logResponses, Tokenizer tokenizer, Map<String, String> customHeaders, List<ChatModelListener> listeners) -
Method Summary
Modifier and TypeMethodDescriptionbuilder()
chat
(ChatRequest request) int
estimateTokenCount
(List<ChatMessage> messages) Estimates the count of tokens in the specified list of messages.generate
(List<ChatMessage> messages) Generates a response from the model based on a sequence of messages.generate
(List<ChatMessage> messages, ToolSpecification toolSpecification) Generates a response from the model based on a list of messages and a single tool specification.generate
(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications) Generates a response from the model based on a list of messages and a list of tool specifications.static OpenAiChatModel
withApiKey
(String apiKey) Deprecated, for removal: This API element is subject to removal in a future version.Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
Methods inherited from interface dev.langchain4j.model.chat.ChatLanguageModel
generate, generate
Methods inherited from interface dev.langchain4j.model.chat.TokenCountEstimator
estimateTokenCount, estimateTokenCount, estimateTokenCount, estimateTokenCount
-
Constructor Details
-
OpenAiChatModel
public OpenAiChatModel(String baseUrl, String apiKey, String organizationId, String modelName, Double temperature, Double topP, List<String> stop, Integer maxTokens, Integer maxCompletionTokens, Double presencePenalty, Double frequencyPenalty, Map<String, Integer> logitBias, String responseFormat, Boolean strictJsonSchema, Integer seed, String user, Boolean strictTools, Boolean parallelToolCalls, Duration timeout, Integer maxRetries, Proxy proxy, Boolean logRequests, Boolean logResponses, Tokenizer tokenizer, Map<String, String> customHeaders, List<ChatModelListener> listeners)
-
-
Method Details
-
modelName
-
supportedCapabilities
- Specified by:
supportedCapabilities
in interfaceChatLanguageModel
-
generate
Description copied from interface:ChatLanguageModel
Generates a response from the model based on a sequence of messages. Typically, the sequence contains messages in the following order: System (optional) - User - AI - User - AI - User ...- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- A list of messages.- Returns:
- The response generated by the model.
-
generate
public Response<AiMessage> generate(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications) Description copied from interface:ChatLanguageModel
Generates a response from the model based on a list of messages and a list of tool specifications. The response may either be a text message or a request to execute one of the specified tools. Typically, the list contains messages in the following order: System (optional) - User - AI - User - AI - User ...- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- A list of messages.toolSpecifications
- A list of tools that the model is allowed to execute. The model autonomously decides whether to use any of these tools.- Returns:
- The response generated by the model.
AiMessage
can contain either a textual response or a request to execute one of the tools.
-
generate
public Response<AiMessage> generate(List<ChatMessage> messages, ToolSpecification toolSpecification) Description copied from interface:ChatLanguageModel
Generates a response from the model based on a list of messages and a single tool specification. The model is forced to execute the specified tool. Typically, the list contains messages in the following order: System (optional) - User - AI - User - AI - User ...- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- A list of messages.toolSpecification
- The specification of a tool that must be executed. The model is forced to execute this tool.- Returns:
- The response generated by the model.
AiMessage
contains a request to execute the specified tool.
-
chat
- Specified by:
chat
in interfaceChatLanguageModel
-
estimateTokenCount
Description copied from interface:TokenCountEstimator
Estimates the count of tokens in the specified list of messages.- Specified by:
estimateTokenCount
in interfaceTokenCountEstimator
- Parameters:
messages
- the list of messages- Returns:
- the estimated count of tokens
-
withApiKey
Deprecated, for removal: This API element is subject to removal in a future version.Please usebuilder()
instead, and explicitly set the model name and, if necessary, other parameters. The default values for the model name and temperature will be removed in future releases! -
builder
-
builder()
instead, and explicitly set the model name and, if necessary, other parameters.