{"id":14064895,"url":"https://github.com/tonykipkemboi/trip_planner_agent","last_synced_at":"2025-06-24T02:03:31.907Z","repository":{"id":217454709,"uuid":"743917871","full_name":"tonykipkemboi/trip_planner_agent","owner":"tonykipkemboi","description":"CrewAI agents that can plan your vacation.","archived":false,"fork":false,"pushed_at":"2024-06-19T15:04:05.000Z","size":10897,"stargazers_count":129,"open_issues_count":0,"forks_count":59,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-20T05:45:06.855Z","etag":null,"topics":["crewai","llm","llms","open-source","openai","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tonykipkemboi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-16T09:09:17.000Z","updated_at":"2025-06-19T04:33:38.000Z","dependencies_parsed_at":null,"dependency_job_id":"f7df2c18-71fe-4a7d-bcdf-9e7449c6fcd4","html_url":"https://github.com/tonykipkemboi/trip_planner_agent","commit_stats":null,"previous_names":["tonykipkemboi/trip_planner_agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tonykipkemboi/trip_planner_agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonykipkemboi%2Ftrip_planner_agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonykipkemboi%2Ftrip_planner_agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonykipkemboi%2Ftrip_planner_agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonykipkemboi%2Ftrip_planner_agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tonykipkemboi","download_url":"https://codeload.github.com/tonykipkemboi/trip_planner_agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tonykipkemboi%2Ftrip_planner_agent/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261589902,"owners_count":23181434,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["crewai","llm","llms","open-source","openai","python"],"created_at":"2024-08-13T07:04:09.882Z","updated_at":"2025-06-24T02:03:31.866Z","avatar_url":"https://github.com/tonykipkemboi.png","language":"Python","funding_links":[],"categories":["Learning","Agent Categories","Python"],"sub_categories":["Repositories","\u003ca name=\"CrewAI\"\u003e\u003c/a\u003eCrewAI"],"readme":"# 🏖️ VacAIgent: Streamlit-Integrated AI Crew for Trip Planning\n\n_Forked and enhanced from the_ [_crewAI examples repository_](https://github.com/joaomdmoura/crewAI-examples/tree/main/trip_planner)\n\n![Beach Vacation Scene ~ generated by GPT-4V](images/beach.png)\n\n## Introduction\n\nVacAIgent 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.\n\n**Check out the video below for code walkthrough** 👇\n\n\u003ca href=\"https://youtu.be/nKG_kbQUDDE\"\u003e\n  \u003cimg src=\"https://img.youtube.com/vi/nKG_kbQUDDE/hqdefault.jpg\" alt=\"Watch the video\" width=\"100%\"\u003e\n\u003c/a\u003e\n\n(_Trip example originally developed by [@joaomdmoura](https://x.com/joaomdmoura)_)\n\n## CrewAI Framework\n\nCrewAI 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.\n\n## Streamlit Interface\n\nThe introduction of [Streamlit](https://streamlit.io/) transforms this application into an interactive web app, allowing users to easily input their preferences and receive tailored travel plans.\n\n## Running the Application\n\nTo experience the VacAIgent app:\n\n- **Configure Environment**: Set up the environment variables for [Browseless](https://www.browserless.io/), [Serper](https://serper.dev/), and [OpenAI](https://openai.com/). Use the `secrets.example` as a guide to add your keys then move that file (`secrets.toml`) to `.streamlit/secrets.toml`.\n\n- **Install Dependencies**: Execute `pip install -r requirements.txt` in your terminal.\n- **Launch the App**: Run `streamlit run streamlit_app.py` to start the Streamlit interface.\n\n★ **Disclaimer**: The application uses GPT-4 by default. Ensure you have access to OpenAI's API and be aware of the associated costs.\n\n## Details \u0026 Explanation\n\n- **Streamlit UI**: The Streamlit interface is implemented in `streamlit_app.py`, where users can input their trip details.\n- **Components**:\n  - `./trip_tasks.py`: Contains task prompts for the agents.\n  - `./trip_agents.py`: Manages the creation of agents.\n  - `./tools directory`: Houses tool classes used by agents.\n  - `./streamlit_app.py`: The heart of the Streamlit app.\n\n## Using GPT 3.5\n\nTo switch from GPT-4 to GPT-3.5, pass the llm argument in the agent constructor:\n\n```python\nfrom langchain.chat_models import ChatOpenAI\n\nllm = 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)\n\nclass TripAgents:\n    # ... existing methods\n\n    def local_expert(self):\n        return Agent(\n            role='Local Expert',\n            goal='Provide insights about the selected city',\n            tools=[SearchTools.search_internet, BrowserTools.scrape_and_summarize_website],\n            llm=llm,\n            verbose=True\n        )\n\n```\n\n## Using Local Models with Ollama\n\nFor enhanced privacy and customization, you can integrate local models like Ollama:\n\n### Setting Up Ollama\n\n- **Installation**: Follow Ollama's guide for installation.\n- **Configuration**: Customize the model as per your requirements.\n\n### Integrating Ollama with CrewAI\n\nPass the Ollama model to agents in the CrewAI framework:\n\n```python\nfrom langchain.llms import Ollama\n\nollama_model = Ollama(model=\"agent\")\n\nclass TripAgents:\n    # ... existing methods\n\n    def local_expert(self):\n        return Agent(\n            role='Local Expert',\n            tools=[SearchTools.search_internet, BrowserTools.scrape_and_summarize_website],\n            llm=ollama_model,\n            verbose=True\n        )\n\n```\n\n## Benefits of Local Models\n\n- **Privacy**: Process sensitive data in-house.\n- **Customization**: Tailor models to fit specific needs.\n- **Performance**: Potentially faster responses with on-premises models.\n\n## License\n\nVacAIgent is open-sourced under the MIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftonykipkemboi%2Ftrip_planner_agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftonykipkemboi%2Ftrip_planner_agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftonykipkemboi%2Ftrip_planner_agent/lists"}