{"id":24719133,"url":"https://github.com/ernestaroozoo/deepknowledge.net","last_synced_at":"2026-04-09T21:05:09.919Z","repository":{"id":274356660,"uuid":"920121189","full_name":"ErnestAroozoo/DeepKnowledge.net","owner":"ErnestAroozoo","description":"DeepKnowledge.net is an advanced Q\u0026A chatbot leveraging Retrieval-Augmented Generation (RAG) to deliver precise, source-grounded responses. It integrates DeepSeek-V3 for chat interactions and OpenAI's text-embedding-ada-002 for embeddings, utilizing Streamlit for a seamless web interface.","archived":false,"fork":false,"pushed_at":"2025-01-27T15:52:43.000Z","size":1088,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-22T11:47:57.200Z","etag":null,"topics":["chatbot","deepseek","deepseek-v3","llamaindex","openai","python","rag","retrieval-augmented-generation","streamlit","text-embedding-ada-002"],"latest_commit_sha":null,"homepage":"https://DeepKnowledge.net","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/ErnestAroozoo.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":"2025-01-21T15:48:15.000Z","updated_at":"2025-01-28T06:30:43.000Z","dependencies_parsed_at":"2025-01-26T20:36:16.846Z","dependency_job_id":null,"html_url":"https://github.com/ErnestAroozoo/DeepKnowledge.net","commit_stats":null,"previous_names":["ernestaroozoo/deepknowledge.net"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ErnestAroozoo/DeepKnowledge.net","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErnestAroozoo%2FDeepKnowledge.net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErnestAroozoo%2FDeepKnowledge.net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErnestAroozoo%2FDeepKnowledge.net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErnestAroozoo%2FDeepKnowledge.net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ErnestAroozoo","download_url":"https://codeload.github.com/ErnestAroozoo/DeepKnowledge.net/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErnestAroozoo%2FDeepKnowledge.net/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264926332,"owners_count":23684320,"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","deepseek","deepseek-v3","llamaindex","openai","python","rag","retrieval-augmented-generation","streamlit","text-embedding-ada-002"],"created_at":"2025-01-27T11:16:50.670Z","updated_at":"2026-04-09T21:05:09.908Z","avatar_url":"https://github.com/ErnestAroozoo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeepKnowledge.net\n\n[![Python](https://img.shields.io/badge/Python-3.12%2B-blue)](https://python.org)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow)](https://opensource.org/licenses/MIT)\n\nAn intelligent Q\u0026A system powered by Retrieval-Augmented Generation (RAG).\n\n![Demo Screenshot](https://github.com/ErnestAroozoo/DeepKnowledge.net/blob/main/demo.png)\n\n## Project Overview\n\nDeepKnowledge.net is an advanced chatbot that integrates large language models with your private data sources using Retrieval-Augmented Generation (RAG). This approach provides precise, source-grounded answers while ensuring data privacy.\n\n## Key Features\n\n- **Multi-source Integration**: Seamlessly process content from websites and documents (PDF/DOCX).\n- **Source Citation**: Offers transparent references to original data sources for every response.\n- **Relevance Scoring**: Efficiently ranks information based on query relevance.\n- **Conversational Memory**: Supports context-aware follow-up questions to maintain dialogue continuity.\n\n## Technical Specifications\n\n- **Language Models**: Uses OpenRouter as the single API provider while keeping DeepSeek for chat interactions and OpenAI's text-embedding-ada-002 for embeddings.\n- **RAG Framework**: Powered by LlamaIndex.\n- **Vector Store**: Employs LlamaIndex In-Memory Vector Store for efficient data retrieval.\n- **User Interface**: Built with Streamlit for a seamless web experience.\n\n## Installation Instructions\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/ErnestAroozoo/DeepKnowledge.net.git\n   cd DeepKnowledge.net\n   ```\n\n2. Install necessary dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. Set up environment variables:\n   ```bash\n   cp .env.example .env\n   # then edit .env and paste your OpenRouter API key\n   ```\n\n## Configuration\n\nUpdate the `.env` file with your OpenRouter credentials:\n\n```ini\n# OpenRouter Configuration\nOPENROUTER_API_KEY=your-openrouter-key\nOPENROUTER_API_HOST=https://openrouter.ai/api/v1\nOPENROUTER_CHAT_MODEL=deepseek/deepseek-chat\nOPENROUTER_EMBED_MODEL=text-embedding-ada-002\n\n# OpenRouter Headers\nOPENROUTER_SITE_URL=https://DeepKnowledge.net\nOPENROUTER_APP_NAME=DeepKnowledge.net\n```\n\n\u003e **Note**: You only need an OpenRouter API key now.\n\n## Usage Guide\n\n1. Launch the application:\n   ```bash\n   streamlit run app.py\n   ```\n\n2. Add data sources:\n   - **Websites**: Input valid URLs for content parsing.\n   - **Documents**: Upload PDF/DOCX files for text extraction.\n\n3. Engage with the chatbot by:\n   - Asking natural language queries.\n   - Following up with questions using chat history.\n   - Requesting source verification for responses.\n\n## Supported Data Sources\n\n| Type        | Formats               | Processing Method       |\n|-------------|-----------------------|-------------------------|\n| Web Content | URLs                  | Web page parsing        |\n| Documents   | PDF, DOCX             | Text extraction         |","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fernestaroozoo%2Fdeepknowledge.net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fernestaroozoo%2Fdeepknowledge.net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fernestaroozoo%2Fdeepknowledge.net/lists"}