{"id":29105273,"url":"https://github.com/torodata/healthbot","last_synced_at":"2026-07-08T13:30:59.402Z","repository":{"id":300184244,"uuid":"1005196528","full_name":"ToroData/HealthBot","owner":"ToroData","description":"HealthBot, a patient-facing prototype that uses LangGraph, LangChain, Tavily Search, and OpenAI to deliver medical education in a structured, interactive format. The system retrieves and summarizes health information in patient-friendly language, generates a comprehension question, evaluates the user’s response, and provides just-in-time feedback.","archived":false,"fork":false,"pushed_at":"2025-06-20T08:50:19.000Z","size":226,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-29T03:02:08.198Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ToroData.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-06-19T20:44:39.000Z","updated_at":"2025-06-20T09:11:31.000Z","dependencies_parsed_at":"2025-06-22T02:34:09.826Z","dependency_job_id":null,"html_url":"https://github.com/ToroData/HealthBot","commit_stats":null,"previous_names":["torodata/healthbot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ToroData/HealthBot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ToroData%2FHealthBot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ToroData%2FHealthBot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ToroData%2FHealthBot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ToroData%2FHealthBot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ToroData","download_url":"https://codeload.github.com/ToroData/HealthBot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ToroData%2FHealthBot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35266857,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-08T02:00:06.796Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2025-06-29T01:38:54.894Z","updated_at":"2026-07-08T13:30:59.393Z","avatar_url":"https://github.com/ToroData.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HealthBot: AI-Powered Patient Education System\n\nHealthBot is an interactive conversational agent designed to support patient education by providing medically accurate summaries and assessing user comprehension through automated question generation. The system is built using LangGraph and LangChain, integrates Tavily for information retrieval, and uses OpenAI models to generate human-readable summaries and feedback.\n\n## Technologies\n\n![Python](https://img.shields.io/badge/Python-3.9%2B-blue?logo=python) ![Jupyter](https://img.shields.io/badge/Jupyter-Notebook-orange?logo=jupyter) ![LangChain](https://img.shields.io/badge/LangChain-Framework-informational) ![LangGraph](https://img.shields.io/badge/LangGraph-Workflow-lightgrey) ![OpenAI](https://img.shields.io/badge/OpenAI-API-black?logo=openai) ![Tavily](https://img.shields.io/badge/Tavily-Search-blueviolet)\n\n\n## Features\n\n- Automated retrieval of medical information via the Tavily API\n- Patient-friendly summarization using the OpenAI GPT model\n- Generation of a single multiple-choice comprehension question based on the provided summary\n- Grading of the patient's response with a letter score and explanatory feedback\n- Interactive, step-by-step flow within a Jupyter Notebook\n- Optional restart of the flow with related medical topics\n\n## Jupyter Notebook Interface\n\nThe application runs entirely within a Jupyter Notebook, with Markdown-enhanced interaction, streaming responses, and structured outputs.\n\n![Interface](IMG/interface.png)\n\n## Requirements\n\n- Python 3.9 or later\n- A valid OpenAI API key\n- A valid Tavily API key\n\n## Installation\n\n1. Clone the repository:\n\n```bash\ngit clone https://github.com/your-username/healthbot.git\ncd healthbot\n```\n\n2. Set up a virtual environment and install dependencies:\n\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\npip install -r requirements.txt\n```\n\n## Configuration\n\nCreate a file named `config.env` in the same directory as the notebook. This file should contain the API keys:\n\n```\nOPENAI_API_KEY=\"sk-...\"\nTAVILY_API_KEY=\"tvly-...\"\n```\n\nLoad the configuration at runtime using:\n\n```python\nfrom dotenv import load_dotenv\nload_dotenv(\"config.env\")\n```\n\n## Usage\n\n1. Open `healthbot.ipynb` using Jupyter Notebook or JupyterLab.\n2. Execute all cells to initialize the application.\n3. Follow the interactive prompts:\n\n   * Enter a medical topic of interest\n   * Read the generated summary\n   * Confirm readiness for a comprehension check\n   * Answer the generated question\n   * Review your grade and feedback\n   * Choose whether to explore another topic or exit\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftorodata%2Fhealthbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftorodata%2Fhealthbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftorodata%2Fhealthbot/lists"}