{"id":24634497,"url":"https://github.com/namikazi25/ecobot","last_synced_at":"2026-05-17T22:36:48.914Z","repository":{"id":273397642,"uuid":"919199223","full_name":"namikazi25/Ecobot","owner":"namikazi25","description":"EcoBot is a chatbot built to empower ecological exploration and species identification. It leverages GPT-4o Mini for intelligent responses, supports chat history persistence, and can analyze images and PDFs to provide insights into biodiversity, species traits, and ecological questions.","archived":false,"fork":false,"pushed_at":"2025-02-23T23:14:41.000Z","size":937,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-23T23:26:39.421Z","etag":null,"topics":["chatbot","ecology","langchain","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/namikazi25.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}},"created_at":"2025-01-19T23:55:16.000Z","updated_at":"2025-01-24T16:30:12.000Z","dependencies_parsed_at":"2025-02-14T22:20:35.950Z","dependency_job_id":"67b8453b-9cdd-44f6-afdd-5b33401b1d5f","html_url":"https://github.com/namikazi25/Ecobot","commit_stats":null,"previous_names":["namikazi25/ecohack","namikazi25/ecobot"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namikazi25%2FEcobot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namikazi25%2FEcobot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namikazi25%2FEcobot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namikazi25%2FEcobot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/namikazi25","download_url":"https://codeload.github.com/namikazi25/Ecobot/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244574798,"owners_count":20474818,"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":["chatbot","ecology","langchain","python"],"created_at":"2025-01-25T09:12:53.330Z","updated_at":"2026-05-17T22:36:48.872Z","avatar_url":"https://github.com/namikazi25.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![EcoBot Logo](screenshot-ecobot.jpeg)\n\n\n# 🌿 EcoBot: AI-Powered Ecological Assistant with Agentic Workflow\n\nEcoBot is an intelligent ecological assistant that combines **multi-agent architecture** with **domain-specific tools** to provide scientifically accurate responses. Leveraging GPT-4o Mini and a sophisticated agentic workflow, it offers robust species identification, ecological analysis, and research paper processing capabilities.\n\n\n---\n\n## 🚀 Key Features\n\n- **Agentic Workflow Architecture** (Planner → Evaluator → Executor)\n- **Multi-Modal Analysis**: Images, PDFs, and text queries\n- **Scientific Validation**: Wikipedia integration for taxonomic verification\n- **Context-Aware Processing**: Maintains conversation context across sessions\n- **BioTrove-CLIP Integration**: Specialized biological image classification\n\n---\n\n## 🧠 Architecture: Agentic Workflow\n\nEcoBot implements a three-stage agentic pipeline to ensure accurate and reliable responses:\n\n```mermaid\ngraph TD\n    A[User Input] --\u003e B(Planning Agent)\n    B --\u003e C{Requires Wikipedia?}\n    C --\u003e|Yes| D[Wikipedia Tools]\n    C --\u003e|No| E{File Type?}\n    E --\u003e|Image| F[GPT4o-mini]\n    F --\u003e H[Evaluating Agent]\n    E --\u003e|PDF| G[PDF Processor]\n    G --\u003e H[Evaluating Agent]\n    H --\u003e B(Planning Agent)\n    E --\u003e|Text| H[Evaluating Agent]\n    H --\u003e I[Executing Agent]\n    I --\u003e J[Response Generation]\n```\n\n### Core Components\n\n1. **Planning Agent** (`planner.py`)\n   - Analyzes user intent using GPT-4o Mini\n   - Selects appropriate tools (Wikipedia/Image/PDF/GPT)\n   - Generates initial execution plan\n\n2. **Evaluating Agent** (`evaluator.py`)\n   - Validates tool selection against domain rules\n   - Checks for recent duplicate queries\n   - Approves or revises execution plans\n\n3. **Executing Agent** (`executor.py`)\n   - Orchestrates tool-specific operations:\n     - `wiki_tool.py`: Wikipedia API integration\n     - `image_tools.py`: BioTrove-CLIP + GPT-4o vision\n     - `pdf_tools.py`: Research paper analysis\n   - Maintains conversation context\n   - Formats final response with sources\n\n---\n\n## 📂 Directory Structure\n\n```\nnamikazi25-ecobot/\n├── app.py                 # Streamlit frontend\n├── backend/\n│   ├── agents/            # Core decision-making components\n│   │   ├── evaluator.py   # Plan validation\n│   │   ├── executor.py    # Tool execution\n│   │   └── planner.py     # Initial strategy\n│   ├── tools/             # Domain-specific capabilities\n│   │   ├── image_tools.py # Vision processing\n│   │   ├── pdf_tools.py   # Document analysis\n│   │   └── wiki_tool.py   # Fact verification\n│   └── utils/             # Shared functionality\n└── tests/                 # Comprehensive test suite\n```\n\n---\n\n## 🛠️ Installation \u0026 Usage\n\n### Prerequisites\n- Python 3.9+\n- OpenAI API key\n\n### Quick Start\n\n1. **Clone repository**\n   ```bash\n   git clone https://github.com/namikazi25/ecobot.git\n   cd ecobot\n   ```\n\n2. **Install dependencies**\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. **Configure environment**\n   ```bash\n   echo \"OPENAI_API_KEY=your_key_here\" \u003e .env\n   ```\n\n4. **Launch system**\n   ```bash\n   # Start backend\n   cd backend \u0026\u0026 uvicorn main:app --reload\n   \n   # In new terminal\n   streamlit run app.py\n   ```\n\n\n\n## 📚 Knowledge Base\n\nEcoBot prioritizes scientific accuracy through:\n- **GPT4o-mini Model**: Biological image classification\n- **Wikipedia Verification**: Taxonomic data validation\n- **Research Paper Analysis**: PDF text extraction + GPT synthesis\n\n---\n🤝 How to Contribute\nWe welcome contributions from developers, ecologists, and AI enthusiasts! Here's how you can help:\n- Report Issues: Found a bug? Open an issue\n- Suggest Enhancements: Have an idea? Start a discussion\n- Submit PRs:\n- Improve vision processing in image_tools.py\n- Enhance PDF analysis in pdf_tools.py\n- Expand ecological knowledge base\n- First-time contributors are especially welcome!\n---\n\n\u003cp align=\"center\"\u003e\n  \"Empowering ecological exploration through intelligent agentic workflows\" 🌍\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnamikazi25%2Fecobot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnamikazi25%2Fecobot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnamikazi25%2Fecobot/lists"}