Frequently Asked Questions (FAQ) about Trip Planner

Q: What is Trip Planner?

A: Trip Planner is an AI-powered application that uses the CrewAI framework and Model Context Protocol (MCP) to automate and enhance the travel planning process. It integrates with Streamlit, FastAPI, and CLI to create detailed, personalized itineraries.

Q: How does Trip Planner use AI?

A: Trip Planner uses AI agents that collaborate to decide on destinations and craft itineraries based on user preferences. These agents leverage Large Language Models (LLMs) to access and process information about travel options, attractions, and logistics.

Q: What is CrewAI?

A: CrewAI is a framework that simplifies the orchestration of role-playing AI agents. It allows developers to define agents, assign them tasks, and coordinate their interactions to achieve a common goal.

Q: What is MCP (Model Context Protocol)?

A: MCP is a protocol that standardizes how applications provide context to LLMs. It allows AI models to access external data sources and tools, enabling more informed and context-aware decision-making.

Q: What interfaces does Trip Planner support?

A: Trip Planner supports multiple interfaces, including a command-line interface (CLI), a FASTAPI server, and a Streamlit interface.

Q: What are the system requirements to run Trip Planner?

A: To run Trip Planner, you need Python 3.6 or higher, along with the necessary dependencies specified in the requirements.txt file. You also need access to API keys for Browseless, Serper, and OpenAI (or another supported LLM provider).

Q: How do I install the dependencies for Trip Planner?

A: You can install the dependencies by running the command pip install -r requirements.txt in your terminal.

Q: How do I configure the environment variables?

A: You need to set up environment variables for Browseless, Serper, and OpenAI. Use the secrets.example file as a guide and move the configured file to .streamlit/secrets.toml.

Q: How do I launch the Streamlit app?

A: You can launch the Streamlit app by running the command streamlit run streamlit_app.py in your terminal.

Q: Can I use other LLM models besides GEMINI?

A: Yes, Trip Planner supports integration with various LLMs, including Ollama and others. You can configure the LLM model in the TripAgents class.

Q: How do I integrate Ollama with Trip Planner?

A: To integrate Ollama, pass the Ollama model to agents in the CrewAI framework, specifying the model name and base URL in the Agent constructor.

Q: Is Trip Planner open-source?

A: Yes, Trip Planner is open-sourced under the MIT License, allowing for free use, modification, and distribution.

Q: Can I contribute to the Trip Planner project?

A: Yes, contributions are welcome! You can contribute by submitting bug reports, feature requests, or pull requests on the project’s GitHub repository.

Q: How can Trip Planner be integrated with the UBOS platform?

A: Integrating Trip Planner with UBOS allows for centralized agent management, enhanced data integration, customizable LLM models, scalability, and improved security and compliance.

Q: What are the potential use cases for Trip Planner?

A: Trip Planner can be used by individual travelers, travel agencies, corporate travel departments, AI enthusiasts, and for educational purposes.

Q: Where can I find more information about UBOS?

A: You can find more information about UBOS on the official UBOS website: https://ubos.tech.

Q: Does the Trip Planner consider real-time data such as flight prices and hotel availability?

A: The Trip Planner, through its MCP server integration, can be configured to consider real-time data. This would involve setting up the appropriate tools and integrations to access real-time APIs for flight prices, hotel availability, and other relevant data. The base Trip Planner provides a framework, but integration with these real-time data sources requires further development and configuration. Ensure you have access to and configure the appropriate APIs within the tools directory.