{"id":26090538,"url":"https://github.com/manjushree08/langflow_rag","last_synced_at":"2026-05-02T20:35:42.265Z","repository":{"id":280531040,"uuid":"941991932","full_name":"manjushree08/Langflow_RAG","owner":"manjushree08","description":"This project integrates LangFlow as a backend API with a Streamlit frontend for a chatbot interface. It also includes RAGAS evaluation for measuring the performance of RAG (Retrieval-Augmented Generation) pipelines.","archived":false,"fork":false,"pushed_at":"2025-03-03T23:07:45.000Z","size":3144,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-04T00:20:12.599Z","etag":null,"topics":["agentic","fastapi","langflow","project-management","ragas-evaluation","streamlit","uvicorn"],"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/manjushree08.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":"2025-03-03T11:52:18.000Z","updated_at":"2025-03-03T23:11:08.000Z","dependencies_parsed_at":"2025-03-04T00:31:34.469Z","dependency_job_id":null,"html_url":"https://github.com/manjushree08/Langflow_RAG","commit_stats":null,"previous_names":["manjushree08/langflow_rag"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/manjushree08/Langflow_RAG","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manjushree08%2FLangflow_RAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manjushree08%2FLangflow_RAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manjushree08%2FLangflow_RAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manjushree08%2FLangflow_RAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/manjushree08","download_url":"https://codeload.github.com/manjushree08/Langflow_RAG/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manjushree08%2FLangflow_RAG/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262538595,"owners_count":23325812,"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":["agentic","fastapi","langflow","project-management","ragas-evaluation","streamlit","uvicorn"],"created_at":"2025-03-09T09:34:30.961Z","updated_at":"2026-05-02T20:35:37.238Z","avatar_url":"https://github.com/manjushree08.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LangFlow Streamlit Integration with RAGAS Evaluation\n\nThis project integrates LangFlow as a backend API with a Streamlit frontend for a chatbot interface. It also includes RAGAS evaluation for measuring the performance of RAG (Retrieval-Augmented Generation) pipelines.\n\u003cimg src=\"data\\Animation.gif\" alt=\"this slowpoke moves\"  width=\"500\" height=\"400\"/\u003e\n\n## Project Structure\n\n```\nproject/\n├── api/                  # FastAPI server that connects to LangFlow\n├── chatbot/              # Streamlit application\n├── evaluation/           # RAGAS evaluation tools\n├── data/                 # Data storage for evaluation\n├── .env                  # Environment variables\n├── requirements.txt      # Project dependencies\n├── docker-compose.yml    # Docker configuration\n```\n\n## Getting Started\n\n### Langflow Graph\n\u003cimg src=\"data\\Langflow.png\" alt=\"Langflow\" width=\"500\" height=\"400\"\u003e\n\n### Prerequisites\n\n- Docker and Docker Compose\n- Python 3.10+\n\n### Installation\n\n1. Clone this repository\n2. Create a virtual environment and install dependencies:\n\n   ```bash\n   python -m venv venv\n   source venv/bin/activate  # On Windows: venv\\Scripts\\activate\n   pip install -r requirements.txt\n   ```\n\n3. Create a `.env` file with the following content:\n   ```\n   LANGFLOW_API_URL=http://localhost:7860\n   API_PORT=8000\n   DEBUG=True\n   ```\n\n### Running the Application\n\n#### Using Docker\n\nThe easiest way to run the entire stack is with Docker Compose:\n\n```bash\ndocker-compose up -d\n```\n\nThis will start:\n\n- LangFlow on port 7860\n- The API server on port 8000\n- The Streamlit UI on port 8501\n\n#### Running Locally\n\n1. Start LangFlow:\n\n   ```bash\n   docker run -p 7860:7860 logspace/langflow:latest\n   ```\n\n2. Start the API server:\n\n   ```bash\n   uvicorn api.app:app --reload\n   ```\n\n   ```\n\n   ```\n\n3. Start the Streamlit application:\n\n   ```bash\n   streamlit run chatbot/app.py\n   ```\n\n4. Start the evaluation dashboard:\n   ```bash\n   streamlit run evaluation/metrics.py\n   ```\n\n## Using the Application\n\n### Setting Up LangFlow\n\n1. Access LangFlow at http://localhost:7860\n2. Create a new flow using the drag-and-drop interface\n3. Set up your RAG pipeline with appropriate components:\n   - Document loaders\n   - Vector stores\n   - LLM models\n   - Chain components\n4. Deploy your flow\n\n### Using the Chatbot\n\n1. Access the Streamlit UI at http://localhost:8501\n2. Select your flow from the dropdown in the sidebar\n3. Start chatting with your LangFlow-powered application\n\n### Running Evaluations\n\n1. Access the evaluation dashboard at http://localhost:8501/evaluation\n2. Select the flow you want to evaluate\n3. Click \"Run Evaluation\" to test your flow with RAGAS metrics\n4. Review the results and optimize your flow accordingly\n\n## RAGAS Evaluation\n\nThis project uses RAGAS to evaluate the performance of your RAG pipelines with the following metrics:\n\n1. **Faithfulness**: Measures how factually consistent the generated answer is with the retrieved context\n2. **Answer Relevancy**: Evaluates whether the answer addresses the question\n3. **Context Relevancy**: Assesses the quality of retrieval - how relevant the retrieved context is to the question\n4. **Context Recall**: Measures how well the retrieved context covers the information needed to answer the question\n5. **Harmfulness**: Evaluates the safety of the generated response\n\n## Customizing the Application\n\n### Adding Custom Evaluation Questions\n\nEdit or replace the `data/questions.json` file with your domain-specific questions and ground truth answers.\n\n### Extending the API\n\nThe API is built with FastAPI, making it easy to add new endpoints:\n\n1. Open `api/app.py`\n2. Add new route functions using the FastAPI decorator syntax\n3. Implement your endpoint logic\n\n### Customizing the UI\n\nThe Streamlit UI can be customized:\n\n1. Edit `chatbot/app.py` to adjust the main application flow\n2. Modify components in the `chatbot/components/` directory\n3. Add new utility functions as needed\n\n## Evaluation Insights\n\nThe evaluation dashboard provides valuable insights into your RAG pipeline performance:\n\n- Metric comparison across different flows\n- Historical performance tracking\n- Detailed view of evaluation results\n- Areas for improvement identification\n\nUse these insights to iteratively improve your LangFlow pipelines:\n\n1. Identify metrics with lower scores\n2. Adjust relevant components in your flow\n3. Re-run evaluations to measure improvement\n4. Repeat until satisfactory performance is achieved\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanjushree08%2Flangflow_rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanjushree08%2Flangflow_rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanjushree08%2Flangflow_rag/lists"}