StandardOpenAILLMService
Description
A Controller Service that provides integration with OpenAI's Chat Completion API. Supports configurable parameters including model selection, temperature, top_p, max tokens, and retry behavior. Handles API authentication, request retries with exponential backoff, and error handling.
Tags
AI, Chat Completion, ChatGPT, LLM, Large Language Model, OpenAI
Properties
In the list below required Properties are shown with an asterisk (*). Other properties are considered optional. The table also indicates any default values, and whether a property supports the NiFi Expression Language.
| Display Name | API Name | Default Value | Allowable Values | Description |
|---|---|---|---|---|
| Web Client Service * | Web Client Service | Controller Service: WebClientServiceProvider Implementations: StandardWebClientServiceProvider | The Web Client Service to use for communicating with the LLM provider. | |
| OpenAI API Key * | OpenAI API Key | The API Key for authenticating to OpenAI. | ||
| Model Name * | Model Name | gpt-4o-mini | The name of the OpenAI model. Supports Expression Language, using FlowFile attributes and Environment variables. | |
| Temperature | Temperature | The temperature to use for generating the response. Supports Expression Language, using FlowFile attributes and Environment variables. | ||
| Top P | Top P | The top_p value for nucleus sampling. It controls the diversity of the generated responses. Supports Expression Language, using FlowFile attributes and Environment variables. | ||
| Seed | Seed | The seed to use for generating the response Supports Expression Language, using FlowFile attributes and Environment variables. | ||
| User | User | Your end user, sent to OpenAI for monitoring and detection of abuse Supports Expression Language, using FlowFile attributes and Environment variables. | ||
| Max Response Tokens | Max Response Tokens | The maximum number of tokens to generate in the response. Supports Expression Language, using FlowFile attributes and Environment variables. | ||
| Max Retries * | Max Retries | 3 | The maximum number of retry attempts for API calls | |
| Backoff Base Delay (ms) * | Backoff Base Delay (ms) | 1000 | The base delay in milliseconds for exponential backoff between retries |
State Management
This component does not store state.
Restricted
This component is not restricted.
System Resource Considerations
This component does not specify system resource considerations.