Connect a tool to your Advanced-Agent application

SWE provides you with the means to construct tools that connect to various data sources, enhancing your model's intelligence.

📘

Before you begin

Before you begin crafting your tool, ensure you have an active application. If you have not yet set up an application, please refer to the quickstart guide for instructions on how to create one swiftly and successfully.

Once your application is established, you can proceed with the following:

• Create a DB Tool: Develop a tool that connects your application to your structured SQL database, facilitating efficient query execution.
• Create a Vector DB Tool: Formulate a tool that links your application to your stored embeddings, empowering your application with deeper, context-aware data insights.
• 
  

Building Smarter LLMs: ReAct Framework Integration

SWE integration of the ReAct framework provides a robust method for enhancing LLMs by equipping them with a rich context and an array of tools for advanced reasoning. This flexible approach allows models to be configured with specific external resources and data, vastly improving their decision-making capabilities and interaction with complex environments, thus enabling more human-like operations and problem-solving.

What is ReAct?

Short for Reasoning + Acting. ReAct empowers LLMs to reason like humans and interact with simulated environments. This facilitates richer interactions, improves decision-making, and enables them to utilize external tools.

How Does React Work?

ReAct structures complex tasks into smaller, actionable components, enabling LLMs to strategically utilize a suite of designated tools that align with the user's input. The LLM assesses each tool's relevance to the task at hand, and following those actionable insights, it refines its reasoning process and decision-making. This is complemented by ReAct's integration with external tools and services, which the LLM leverages for effective task execution and information acquisition

Optimizing tool usage

To effectively apply React, provide the LLM with detailed tool descriptions. These descriptions should outline the tool’s purpose, functionality, and any relevant information that helps the LLM determine when to utilize it. For example: "This tools is used for querying internal VectorDB with all the medical documents from years 2016 to 2023, it can be useful when getting question about internal medical case"