LLM Engine#
The LLM Engine Processor is a processor that generates text using a language model. It is an essential component in the OpenPlugin system for tasks that require natural language generation.
Supported Input Port:
text: The LLM Engine Processor accepts input through the “text” port. The input should be a string that serves as a prompt for the language model.
Supported Output Port:
text: The processor produces output through the “text” port. The output is a string generated by the language model based on the provided prompt.
List of Implementations:#
OpenAI Implementation#
The BeautifulSoup implementation of the HTML to Text Processor uses the BeautifulSoup library to parse the HTML and extract the text content.
Metadata
Field |
Type |
Required |
User Provided |
Description |
---|---|---|---|---|
model_name |
string |
no |
no |
The name of the language model to be used. The default value is “gpt-3.5-turbo”. |
pre_prompt |
string |
no |
no |
An optional string that is prepended to the input text before it is fed to the language model. The default value is null. |
openai_api_key |
string |
yes |
yes |
The API key for accessing OpenAI’s language models. This key is user-provided. |
Sample processor configuration:#
NOTE: Processor is always added to a module(Input or Output). The module is then added to the pipeline.
{
"processor_type": "llm_engine",
"processor_implementation_type": "llm_engine_with_openai",
"input_port": "text",
"output_port": "text",
"metadata": {},
}