README.md

metadata

title: VacAIgent
emoji: 🐨
colorFrom: yellow
colorTo: purple
sdk: streamlit
sdk_version: 1.44.1
app_file: app.py
pinned: false
license: apache-2.0
short_description: Let AI agents plan your next vacation!

🏖️ VacAIgent: Streamlit-Integrated AI Crew for Trip Planning

Forked and enhanced from the crewAI examples repository

Introduction

VacAIgent leverages the CrewAI framework to automate and enhance the trip planning experience, integrating a user-friendly Streamlit interface. This project demonstrates how autonomous AI agents can collaborate and execute complex tasks efficiently, now with an added layer of interactivity and accessibility through Streamlit.

Check out the video below for code walkthrough 👇

(Trip example originally developed by @joaomdmoura)

CrewAI Framework

CrewAI simplifies the orchestration of role-playing AI agents. In VacAIgent, these agents collaboratively decide on cities and craft a complete itinerary for your trip based on specified preferences, all accessible via a streamlined Streamlit user interface.

Streamlit Interface

The introduction of Streamlit transforms this application into an interactive web app, allowing users to easily input their preferences and receive tailored travel plans.

Running the Application

To experience the VacAIgent app:

Pre-Requisites

1. Install and Configure git on your machine
2. Get the API key from scrapinagent.com from scrapinagent Click Here to Signup
3. Get the API from SERPER API from serper Click here to Signup

Deploy Trip Planner

Step 1

git clone https://github.com/intel-sandbox/trip_planner_agent

• Please make sure git is installed

Step 2

Insall Dependencies

pip install -r requirements.txt

Step 3

cd trip_planner_agent

create .streamlit/secrets.toml file and Update Credentials you can use secrtes.example file for reference

SERPER_API_KEY=""
SCRAPINGANT_API_KEY=""
OPENAI_API_KEY=""
MODEL_ID=""
MODEL_BASE_URL=""

Step 4

Run the application

streamlit run streamlit_app.py

Your application should be up and running

★ Disclaimer: The application uses GPT-4 by default. Ensure you have access to OpenAI's API and be aware of the associated costs.

Details & Explanation

• Streamlit UI: The Streamlit interface is implemented in streamlit_app.py, where users can input their trip details.
• Components:
  • ./trip_tasks.py: Contains task prompts for the agents.
  • ./trip_agents.py: Manages the creation of agents.
  • ./tools directory: Houses tool classes used by agents.
  • ./streamlit_app.py: The heart of the Streamlit app.

Using GPT 3.5

To switch from GPT-4 to GPT-3.5, pass the llm argument in the agent constructor:

from langchain.chat_models import ChatOpenAI

llm = ChatOpenAI(model='gpt-3.5-turbo') # Loading gpt-3.5-turbo (see more OpenAI models at https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)

class TripAgents:
    # ... existing methods

    def local_expert(self):
        return Agent(
            role='Local Expert',
            goal='Provide insights about the selected city',
            tools=[SearchTools.search_internet, BrowserTools.scrape_and_summarize_website],
            llm=llm,
            verbose=True
        )

Using Local Models with Ollama

For enhanced privacy and customization, you can integrate local models like Ollama:

Setting Up Ollama

• Installation: Follow Ollama's guide for installation.
• Configuration: Customize the model as per your requirements.

Integrating Ollama with CrewAI

Pass the Ollama model to agents in the CrewAI framework:

from langchain.llms import Ollama

ollama_model = Ollama(model="agent")

class TripAgents:
    # ... existing methods

    def local_expert(self):
        return Agent(
            role='Local Expert',
            tools=[SearchTools.search_internet, BrowserTools.scrape_and_summarize_website],
            llm=ollama_model,
            verbose=True
        )

Benefits of Local Models

• Privacy: Process sensitive data in-house.
• Customization: Tailor models to fit specific needs.
• Performance: Potentially faster responses with on-premises models.

License

VacAIgent is open-sourced under the MIT License.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference