Large Language Model

Process text and generate human-like responses with advanced AI models.

What is the Large Language Model?

The Large Language Model (LLM) node is a powerful component that leverages state-of-the-art language models from providers like AWS Bedrock, OpenAI, and Google AI. This tool processes text inputs, generates human-like responses, and performs various language tasks based on the selected model and configuration.

How to use it?

1. Select a Model:

   • Choose from various models provided by AWS Bedrock, OpenAI, or Google AI.
   • Each model has its own strengths and capabilities. Refer to the provider's documentation:
     • AWS Bedrock Models
     • OpenAI Models
     • Google AI Language Models

2. Configure Model Parameters:

   • Set the temperature (default: 0.7) to control output randomness.
   • Adjust the topP value (default: 1.0) to influence output diversity.
   • For AWS Bedrock models, specify the region (default: us-east-1).

3. Provide Input:

   • Connect a string input to the "Prompt Text" anchor.
   • For supported models, you can provide an image input for multimodal tasks.

4. Set Up Output:

   • Choose between "Text" (complete response) or "Streaming" (real-time chunks) output types.

5. Execute the Component:

   • Run your workflow to process the input through the selected language model.

Example Task: Text Summarization Workflow

Objective: Create a workflow that accepts user-provided text and produces a concise summary.

Step-by-Step Setup

1. Add Text Input:

   • Add a Text Input node to your canvas.
   • Add an input variable.
   • Edit the template text to be: Summarize the following text:
   • Add an input variable and click the created variable to make use of it in the text. For more details on this step see the text input documentation.

2. Add Input node

   • Add an input node.
   • Change its name to ArticleText
   • Change the type to text.

3. Add Large Language Model:

   • Locate the Large Language Model node in your node selection.
   • Add it to the canvas.
   • Configure it with your API key and select an appropriate model.

4. Add Output:

   • Add a String Output component to display the result.
   • Connect the output of the OpenAI component to the input of the String Output.

5. Connect Components:

   • Link the output of the "ArticleText" Input node to the created variable in the text input node.
   • Link the text input node output to the Prompt Text of the Large Language Model node.
   • Link the Large Language Model output to the Output node.

This leaves us with the result:

Article summary graph

🔗 Related Nodes: Input, Text, Large Language Model, Output

Execution

To execute the workflow described in the step by step guide, add your article to the input nodes value field.

Additional Information

• Authentication: Set up necessary API keys and permissions:

  • AWS Bedrock Authentication
  • OpenAI API Keys
  • Google AI Authentication

• Multimodal Inputs: Some models support image inputs. Check the model's documentation for supported formats.

• Parameter Tuning: Experiment with temperature and topP values to balance creativity and coherence.

• Ethical Considerations: Be aware of potential biases in AI-generated content. Review outputs before use in sensitive applications.

• Stay Updated: Providers frequently release new models with improved capabilities.

For advanced usage, explore:

• Prompt engineering techniques

Troubleshooting

• If you encounter rate limits, check your API usage and consider upgrading your plan.
• For unexpected outputs, review your prompt and try adjusting the temperature or topP values.
• Ensure your AWS region is compatible with the chosen Bedrock model.