Skip to main content

Agent Plugins: Included Models

Google (Gemini)

Google Gemini models offer a combination of capabilities that may be appealing over other models.

Their large context window allows them to process and understand and recall extensive amounts of information at once.

They are also designed to be flexible, performing well across a wide range of tasks like text generation, translation, and code generation.

Gemini models also are optimized for different scales, making them suitable for both large-scale deployments and smaller, resource-constrained environments.

(You can also load the smaller open-source variants of Gemini (Gemma) locally using our Ollama agent plugin.)

Setting up your agent

  • After setting up your system, navigate to the "Add Panel" section and select your Gemini plugin.
  • Choose your desired model from the list of available options.
  • Set a System Message, this will help guide your model if you'd like it to behave a certain way or do something specific.
  • Enter your OpenAI API key, which you can find here: https://aistudio.google.com/app/apikey

Once you've added your API key, your agent will be ready to use!

Models Available

Each model offers unique capabilities and costs. Consider your needs when selecting a model:

  • Gemini Pro 1.5:
    • Compatible up to 1,000,000 tokens.
    • The latest version of the Pro model, offering the best performance and capabilities across various tasks. It is designed for high accuracy and versatility.
  • Gemini Flash 1.5:
    • Compatible up to 1,000,000 tokens.
    • This model is optimized for speed and lower latency, making it ideal for real-time applications where quick responses are important.
  • Gemini Pro 1.0
    • The previous version of the Pro model, which might still be suitable for certain applications where backward compatibility is necessary or where the latest features are not required.

Document upload ( and /append command)

This plugin allows you to upload text-based documents (e.g., .txt, .doc, .md) to enhance your chat experience.

The plugin will:

  • Convert your uploaded files into plain text.
  • Store these text versions for your AI model to access.

When you want to use your document when chatting:

  • Use the /append command in your chat
  • Followed by your document(s) filename(s) /file filename.pdf
  • And then any additional questions you have to add the documents to your context when chatting.

An example prompt with the command would look like:

/append /file filename.pdf What are the core themes I should be aware of in this document?

Note on longer context

If your document is too large to fit within your chosen model's context window it will be excluded from your message context and you will receive a warning.

For larger documents, consider using our Document Lookup (RAG) agent plugin.

Vision support

This plugin offers "vision" capabilities, meaning it can process uploaded images (e.g., .png, .jpg) alongside your text input.

Example vision usage

After uploading a receipt image, you could ask:

"What are the amounts listed in this invoice? Could you also categorize the purchase for me?"

Review the code

Want to review how this model is made, or use it as the base to creating a new agent plugin?

You can find the code that powers this plugin available here:
https://github.com/promptpanel/promptpanel/tree/main/plugins/gemini