LLM tools

Tool that uses artificial intelligence and deep learning techniques to process and generate human-like text. It understands context, grammar, and semantics to perform a wide range of natural language processing tasks, including translation, chatbots, and content generation.

Here's how you can create your LLM tool:

Start by clicking the button from the Tools section. The next step is to choose the the type of tool. Here we will discuss about LLM tools. Once you select the LLM option, follow the below steps:

1. Add Tool Information: Input essential details like the Tool's name and briefly describe what it does in the 'About' section (this is for user's understanding)

2. Configure your Model : Select the model that the tool will leverage to complete it’s tasks. For example GPT 4, Claude etc.

3. Adjust settings and hyperparameters of the model: Tweak settings like temperature, context length etc. for the model.

4. Templatise your Prompt: Establish the description that the Tool's LLM will leverage to process queries. Importantly, you can define variables within the prompt that can be dynamically populated during the tool's execution. These variables are passed on to the Tool for processing, providing a flexible way to execute tasks. Essentially, while the "Routing description" outlines what the Tool can do, the "Prompt" details how it accomplishes that task, including variable inputs.

5. Configure for Routing: Compose a descriptive text for the Tool. A Tool can be used individually or within an App. The Router description is crucial as the App's LLM/Router utilises this description to determine if this Tool should be invoked within complex workflows.