Package dev.langchain4j.model.mistralai
Class MistralAiChatModel
java.lang.Object
dev.langchain4j.model.mistralai.MistralAiChatModel
- All Implemented Interfaces:
ChatLanguageModel
Represents a Mistral AI Chat Model with a chat completion interface, such as open-mistral-7b and open-mixtral-8x7b
This model allows generating chat completion of a sync way based on a list of chat messages.
You can find description of parameters here.
-
Nested Class Summary
-
Constructor Summary
ConstructorDescriptionMistralAiChatModel
(String baseUrl, String apiKey, String modelName, Double temperature, Double topP, Integer maxTokens, Boolean safePrompt, Integer randomSeed, String responseFormat, Duration timeout, Boolean logRequests, Boolean logResponses, Integer maxRetries) Constructs a MistralAiChatModel with the specified parameters. -
Method Summary
Modifier and TypeMethodDescriptionbuilder()
generate
(List<ChatMessage> messages) Generates chat response based on the given list of messages.generate
(List<ChatMessage> messages, ToolSpecification toolSpecification) Generates an AI message response based on the given list of chat messages and a tool specification.generate
(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications) Generates an AI message response based on the given list of chat messages and tool specifications.static MistralAiChatModel
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
chat, generate, generate, supportedCapabilities
-
Constructor Details
-
MistralAiChatModel
public MistralAiChatModel(String baseUrl, String apiKey, String modelName, Double temperature, Double topP, Integer maxTokens, Boolean safePrompt, Integer randomSeed, String responseFormat, Duration timeout, Boolean logRequests, Boolean logResponses, Integer maxRetries) Constructs a MistralAiChatModel with the specified parameters.- Parameters:
baseUrl
- the base URL of the Mistral AI API. It uses the default value if not specifiedapiKey
- the API key for authenticationmodelName
- the name of the Mistral AI model to usetemperature
- the temperature parameter for generating chat responsestopP
- the top-p parameter for generating chat responsesmaxTokens
- the maximum number of new tokens to generate in a chat responsesafePrompt
- a flag indicating whether to use a safe prompt for generating chat responsesrandomSeed
- the random seed for generating chat responsesresponseFormat
- the response format for generating chat responses.Current values supported are "text" and "json_object".
timeout
- the timeout duration for API requestsThe default value is 60 seconds
logRequests
- a flag indicating whether to log API requestslogResponses
- a flag indicating whether to log API responsesmaxRetries
- the maximum number of retries for API requests. It uses the default value 3 if not specified
-
-
Method Details
-
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 value for the model name will be removed in future releases! -
generate
Generates chat response based on the given list of messages.- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- the list of chat messages- Returns:
- The response generated by the model.
-
generate
public Response<AiMessage> generate(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications) Generates an AI message response based on the given list of chat messages and tool specifications.- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- the list of chat messagestoolSpecifications
- the list of tool specifications. tool_choice is set to AUTO.- Returns:
- a Response containing the generated AI message
-
generate
public Response<AiMessage> generate(List<ChatMessage> messages, ToolSpecification toolSpecification) Generates an AI message response based on the given list of chat messages and a tool specification.- Specified by:
generate
in interfaceChatLanguageModel
- Parameters:
messages
- the list of chat messagestoolSpecification
- the tool specification that must be executed. tool_choice is set to ANY.- Returns:
- a Response containing the generated AI message
-
builder
-
builder()
instead, and explicitly set the model name and, if necessary, other parameters.