spring.ai.retry.max-attemptsspring-doc.cn

Maximum number of retry attempts.spring-doc.cn

10spring-doc.cn

spring.ai.retry.backoff.initial-intervalspring-doc.cn

Initial sleep duration for the exponential backoff policy.spring-doc.cn

2 sec.spring-doc.cn

spring.ai.retry.backoff.multiplierspring-doc.cn

Backoff interval multiplier.spring-doc.cn

5spring-doc.cn

spring.ai.retry.backoff.max-intervalspring-doc.cn

Maximum backoff duration.spring-doc.cn

3 min.spring-doc.cn

spring.ai.retry.on-client-errorsspring-doc.cn

If false, throw a NonTransientAiException, and do not attempt retry for 4xx client error codesspring-doc.cn

falsespring-doc.cn

spring.ai.retry.exclude-on-http-codesspring-doc.cn

List of HTTP status codes that should not trigger a retry (e.g. to throw NonTransientAiException).spring-doc.cn

emptyspring-doc.cn

spring.ai.retry.on-http-codesspring-doc.cn

List of HTTP status codes that should trigger a retry (e.g. to throw TransientAiException).spring-doc.cn

emptyspring-doc.cn

spring.ai.openai.base-urlspring-doc.cn

The URL to connect to. Must be set to integrate.api.nvidia.comspring-doc.cn

-spring-doc.cn

spring.ai.openai.api-keyspring-doc.cn

The NVIDIA API Keyspring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.enabledspring-doc.cn

Enable OpenAI chat model.spring-doc.cn

truespring-doc.cn

spring.ai.openai.chat.base-urlspring-doc.cn

Optional overrides the spring.ai.openai.base-url to provide chat specific url. Must be set to integrate.api.nvidia.comspring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.api-keyspring-doc.cn

Optional overrides the spring.ai.openai.api-key to provide chat specific api-keyspring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.modelspring-doc.cn

The NVIDIA LLM model to usespring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.temperaturespring-doc.cn

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.spring-doc.cn

0.8spring-doc.cn

spring.ai.openai.chat.options.frequencyPenaltyspring-doc.cn

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.spring-doc.cn

0.0fspring-doc.cn

spring.ai.openai.chat.options.maxTokensspring-doc.cn

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-doc.cn

NOTE: NVIDIA LLM API requires the max-tokens parameter to be explicitly set or server error will be thrown.spring-doc.cn

spring.ai.openai.chat.options.nspring-doc.cn

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.spring-doc.cn

1spring-doc.cn

spring.ai.openai.chat.options.presencePenaltyspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.responseFormatspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.seedspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.stopspring-doc.cn

Up to 4 sequences where the API will stop generating further tokens.spring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.topPspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.toolsspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.toolChoicespring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.userspring-doc.cn

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.spring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.functionsspring-doc.cn

List of functions, identified by their names, to enable for function calling in a single prompt requests. Functions with those names must exist in the functionCallbacks registry.spring-doc.cn

-spring-doc.cn

spring.ai.openai.chat.options.stream-usagespring-doc.cn

(For streaming only) Set to add an additional chunk with token usage statistics for the entire request. The choices field for this chunk is an empty array and all other chunks will also include a usage field, but with a null value.spring-doc.cn

falsespring-doc.cn