This project is an LLM-powered travel agent that assists users with various travel-related queries, such as checking flight availability, retrieving weather updates, and fetching YouTube video transcripts. This implementation uses prompting to guide the LLM's structured responses and interactions with tools.
The system consists of two main components:
prompt_agent.py: Handles user queries, constructs structured LLM prompts, and manages tool execution based on the LLM's output.
tools.py: Implements various helper functions for retrieving external data (weather, flights, transcripts, web search, etc.).
1. The user submits a travel-related query (e.g., "Find me flights to NYC on April 10").
2. prompt_agent.pystructures a prompt instructing the LLM to determine if additional tools are needed.
3. If external data is required, the LLM returns a JSON object specifying which tools to use and their required inputs.
4. The script executes the relevant tools from tools.py and retrieves the necessary data.
5. The retrieved data is inserted into the context, and the LLM is called again to generate the final response.
6. The structured response is presented to the user.
Full code and files can be found on the Github Repo
There are no models linked
There are no models linked
There are no datasets linked
There are no datasets linked