{"id":26362565,"url":"https://github.com/shaikh-raj/talk2data","last_synced_at":"2026-05-03T20:31:43.680Z","repository":{"id":282610371,"uuid":"949127306","full_name":"shaikh-raj/talk2data","owner":"shaikh-raj","description":"POC project integrating LLM, RAG, and KG to generate context-aware responses from text and database inputs.","archived":false,"fork":false,"pushed_at":"2025-03-15T19:22:16.000Z","size":90,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-11T01:11:30.065Z","etag":null,"topics":["faiss","knowledge-graph","langchain","langsmith","neo4j","python","serpapi"],"latest_commit_sha":null,"homepage":"https://talk2data.mathnai.com/","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/shaikh-raj.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-15T18:32:40.000Z","updated_at":"2025-04-21T16:41:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"dc1b0006-5320-48f8-b1d1-ceab03aa2096","html_url":"https://github.com/shaikh-raj/talk2data","commit_stats":null,"previous_names":["shaikh-raj/llm-rag-kg-poc"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/shaikh-raj/talk2data","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shaikh-raj%2Ftalk2data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shaikh-raj%2Ftalk2data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shaikh-raj%2Ftalk2data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shaikh-raj%2Ftalk2data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shaikh-raj","download_url":"https://codeload.github.com/shaikh-raj/talk2data/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shaikh-raj%2Ftalk2data/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32583905,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T06:36:36.687Z","status":"ssl_error","status_checked_at":"2026-05-03T06:36:09.306Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["faiss","knowledge-graph","langchain","langsmith","neo4j","python","serpapi"],"created_at":"2025-03-16T18:18:21.944Z","updated_at":"2026-05-03T20:31:43.674Z","avatar_url":"https://github.com/shaikh-raj.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM POC Project\n\nThis project demonstrates integration of various AI capabilities using LangChain, including:\n\n- Text-based RAG (Retrieval-Augmented Generation)\n- Knowledge Graph integration with Neo4j\n- SQL database querying\n- Web search capabilities\n- Multi-tool orchestration\n\n## Features\n\n- Text input processing with vector embeddings\n- Knowledge graph creation and querying\n- Database integration for structured data\n- Web search capability via SerpAPI\n- Streamlit-based user interface\n\n## Setup Instructions\n\n1. Install dependencies:\n   ```\n   pip install -r requirements.txt\n   ```\n\n2. Set up API keys:\n   - Create a `secrets.toml` file in the `.streamlit` directory with:\n     ```\n     GOOGLE_API_KEY = \"your-google-api-key\"\n     LANGSMITH_API_KEY = \"your-langsmith-api-key\" # Optional\n     NEO4J_URI = \"your-neo4j-uri\"\n     NEO4J_USERNAME = \"your-neo4j-username\"\n     NEO4J_PASSWORD = \"your-neo4j-password\"\n     SERPAPI_API_KEY = \"your-serpapi-key\"\n     ```\n\n3. Run the application:\n   ```\n   streamlit run app.py\n   ```\n\n## Usage\n\n1. **Text Data**: Enter text or use the sample text. Click \"Process Text Data\" to create embeddings and knowledge graph.\n\n2. **Database**: Upload an Excel file or use the sample database. Click \"Process Database\" to load data into SQLite.\n\n3. **Web Search**: Enable web search for external information retrieval.\n\n4. **Query Selection**: Select which data sources to use for answering queries.\n\n5. **Ask Questions**: Type your query in the text box and get answers from the selected data sources.\n\n## Architecture\n\nThe application uses a modular architecture:\n\n- **Streamlit Frontend**: User interface and interaction\n- **LangChain**: Orchestration of various components\n- **FAISS**: Vector storage for text embeddings\n- **Neo4j**: Knowledge graph storage and querying\n- **SQLite**: Relational database for structured data\n- **SerpAPI**: Web search capabilities\n\n## Project Structure\n\n```\n├── app.py                 # Main Streamlit application\n├── utils.py               # Helper Library\n├── requirements.txt       # Project dependencies\n├── flow_diagram.png       # System architecture diagram\n└── README.md              # Project documentation\n```\n\n## Project Flow\n![Project Flow](https://raw.githubusercontent.com/shaikh-raj/llm-rag-kg-poc/refs/heads/main/mermaid-diagram.png)\n\n## Future Improvements\n\n- Support for PDF and document processing\n- Integration with more external tools\n- Enhanced visualization capabilities\n- User authentication and permissions\n- Improved performance and caching","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshaikh-raj%2Ftalk2data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshaikh-raj%2Ftalk2data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshaikh-raj%2Ftalk2data/lists"}