{"id":29902988,"url":"https://github.com/jasjeev013/neuroquery-chroma-rag","last_synced_at":"2026-04-29T16:39:28.215Z","repository":{"id":306758952,"uuid":"1027125207","full_name":"jasjeev013/Neuroquery-Chroma-RAG","owner":"jasjeev013","description":"NeuroQuery is an AI-powered PDF question-answering system that lets you upload and interact with  documents using natural language. Built with LangChain, Gemini AI, and Chroma, it delivers fast, context-aware answers from your files.","archived":false,"fork":false,"pushed_at":"2025-07-27T11:50:14.000Z","size":1538,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-27T13:26:09.208Z","etag":null,"topics":["ai","chromadb","document-intelligence","gemini","langchain","multi-pdf-processing","nlp","pdf-analysis-python","pdf-question-answering","streamlit","vector-search"],"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/jasjeev013.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":"2025-07-27T11:18:04.000Z","updated_at":"2025-07-27T11:50:17.000Z","dependencies_parsed_at":"2025-07-27T13:26:11.583Z","dependency_job_id":"40c5c456-0809-4bf9-8d45-6f7d3414f21f","html_url":"https://github.com/jasjeev013/Neuroquery-Chroma-RAG","commit_stats":null,"previous_names":["jasjeev013/neuroquery-chroma-rag"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/jasjeev013/Neuroquery-Chroma-RAG","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jasjeev013%2FNeuroquery-Chroma-RAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jasjeev013%2FNeuroquery-Chroma-RAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jasjeev013%2FNeuroquery-Chroma-RAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jasjeev013%2FNeuroquery-Chroma-RAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jasjeev013","download_url":"https://codeload.github.com/jasjeev013/Neuroquery-Chroma-RAG/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jasjeev013%2FNeuroquery-Chroma-RAG/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268264363,"owners_count":24222508,"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","status":"online","status_checked_at":"2025-08-01T02:00:08.611Z","response_time":67,"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":["ai","chromadb","document-intelligence","gemini","langchain","multi-pdf-processing","nlp","pdf-analysis-python","pdf-question-answering","streamlit","vector-search"],"created_at":"2025-08-01T16:47:24.048Z","updated_at":"2026-04-29T16:39:28.159Z","avatar_url":"https://github.com/jasjeev013.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NeuroQuery: Intelligent Answers from Your Documents\n\n![NeuroQuery Banner](screenshots/banner.png) \u003c!-- Add your screenshot path here --\u003e\n\nA state-of-the-art document question answering system that extracts knowledge from your PDFs using AI.\n\n## Features\n\n| Feature | Description |\n|---------|-------------|\n| 📄 Multi-PDF Processing | Upload and analyze up to 3 PDFs simultaneously (300 pages max each) |\n| 💬 Natural Language Interface | Ask questions in plain English about your documents |\n| 🧠 Smart Context Understanding | Gemini AI provides accurate answers based on document content |\n| ⚡ Fast Retrieval | Chroma vector database enables quick information lookup |\n\n![UI Screenshot](screenshots/interface.png) \u003c!-- Add your screenshot path here --\u003e\n\n## Technical Architecture\n\n```mermaid\ngraph TD\n    A[PDF Upload] --\u003e B[Text Extraction]\n    B --\u003e C[Chunking]\n    C --\u003e D[Vector Embeddings]\n    D --\u003e E[Chroma DB Storage]\n    E --\u003e F[User Query]\n    F --\u003e G[Relevant Chunk Retrieval]\n    G --\u003e H[Gemini Answer Generation]\n    H --\u003e I[Response Display]\n```\n\n## Technology Stack\n\n ### Core Libraries \n\n| Category | Libraries |\n|----------|-----------|\n| Framework | `langchain`, `langchain_community` |\n| AI Models | `langchain_google_genai` (Gemini) |\n| Vector DB | `langchain_chroma` |\n| PDF Processing | `pypdf`, `pdfminer.six`, `unstructured` |\n| Utilities | `python-dotenv`, `nest_asyncio`, `sentence-transformers` |\n| UI | `streamlit` |\n\n## Setup Instructions\n\n### Prerequisites\n- Python 3.8+\n- Google API key with Gemini access\n\n### Installation\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/yourusername/neuroquery.git\n   cd neuroquery\n   ```\n\n2. Create and activate virtual environment:\n   ```bash\n   python -m venv venv\n   source venv/bin/activate  # Linux/Mac\n   venv\\Scripts\\activate  # Windows\n   ```\n\n3. Install dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n4. Create `.env` file:\n   ```env\n   GOOGLE_API_KEY=your_api_key_here\n   ```\n\n### Running the Application\n```bash\nstreamlit run app.py\n```\n\n## Deployment Options\n\n| Platform | Instructions |\n|----------|--------------|\n| Streamlit Cloud | [Deploy Guide](https://docs.streamlit.io/streamlit-community-cloud/deploy-your-app) |\n| Hugging Face | [Spaces Guide](https://huggingface.co/docs/hub/spaces) |\n| AWS/Azure | Use Docker with Streamlit server |\n\n## Usage Guide\n\n1. Upload PDF documents (max 3 files)\n2. Wait for processing to complete\n3. Ask questions about the document content\n4. View AI-generated answers with source references\n\n## Troubleshooting\n\n- **Processing Errors**: Ensure PDFs contain selectable text (not scanned images)\n- **API Errors**: Verify your Google API key has Gemini access\n- **Performance**: For large documents, increase chunk size in `config.py`\n\n## License\n\n[MIT License](LICENSE)\n\n---\n\nDeveloped with ❤️ by Jasjeev Singh Kohli\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjasjeev013%2Fneuroquery-chroma-rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjasjeev013%2Fneuroquery-chroma-rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjasjeev013%2Fneuroquery-chroma-rag/lists"}