{"id":49264459,"url":"https://github.com/rajivpant/ragbot","last_synced_at":"2026-04-25T09:10:22.012Z","repository":{"id":163115587,"uuid":"637475364","full_name":"rajivpant/ragbot","owner":"rajivpant","description":"Ragbot.AI is an augmented brain assistant developed by Rajiv Pant","archived":false,"fork":false,"pushed_at":"2026-04-11T18:19:22.000Z","size":3471,"stargazers_count":30,"open_issues_count":1,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-04-11T20:11:56.530Z","etag":null,"topics":["ai","ai-assistant","artificial-intelligence","chatbot","generative-ai","machine-learning","natural-language-generation","natural-language-processing","natural-language-understanding","nlp"],"latest_commit_sha":null,"homepage":"https://rajiv.com/blog/2023/05/08/introducing-rbot-a-personalized-ai-assistant-written-by-rbot/","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/rajivpant.png","metadata":{"files":{"readme":"README-DOCKER.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","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":"2023-05-07T17:06:02.000Z","updated_at":"2026-04-11T18:19:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"a12b5eb4-223e-413e-94e2-206c271dbfff","html_url":"https://github.com/rajivpant/ragbot","commit_stats":null,"previous_names":["rajivpant/ragbot"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/rajivpant/ragbot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajivpant%2Fragbot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajivpant%2Fragbot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajivpant%2Fragbot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajivpant%2Fragbot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rajivpant","download_url":"https://codeload.github.com/rajivpant/ragbot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajivpant%2Fragbot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32256300,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T04:23:17.126Z","status":"ssl_error","status_checked_at":"2026-04-25T04:21:53.360Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["ai","ai-assistant","artificial-intelligence","chatbot","generative-ai","machine-learning","natural-language-generation","natural-language-processing","natural-language-understanding","nlp"],"created_at":"2026-04-25T09:10:21.366Z","updated_at":"2026-04-25T09:10:21.996Z","avatar_url":"https://github.com/rajivpant.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ragbot.AI - Docker Deployment Guide\n\nThis guide explains how to run Ragbot.AI using Docker and Docker Compose for easy deployment and portability.\n\n## Prerequisites\n\n- [Docker](https://docs.docker.com/get-docker/) (version 20.10 or later)\n- [Docker Compose](https://docs.docker.com/compose/install/) (version 2.0 or later)\n- At least one AI provider API key (OpenAI, Anthropic, or Google Gemini)\n\n## Quick Start\n\n### 1. Set Up API Keys\n\nCreate the keys configuration file:\n\n```bash\nmkdir -p ~/.synthesis\ncat \u003e ~/.synthesis/keys.yaml \u003c\u003c 'EOF'\n# Synthesis API Keys (shared across synthesis-engineering products: ragbot, ragenie, etc.)\ndefault:\n  anthropic: \"sk-ant-your-key-here\"\n  openai: \"sk-your-key-here\"\n  google: \"your-gemini-key-here\"\nEOF\nchmod 600 ~/.synthesis/keys.yaml\n```\n\nEdit with your actual API keys.\n\n### 2. Configure the Database (pgvector)\n\nRagbot's default vector backend is PostgreSQL with the `pgvector` extension. Copy the env template and change the password before any non-local use:\n\n```bash\ncp .env.example .env\n# Edit .env and set POSTGRES_PASSWORD to a strong value.\n# RAGBOT_DATABASE_URL is auto-derived from POSTGRES_USER/POSTGRES_PASSWORD.\n```\n\nDocker Compose will start a Postgres 16 container (image `pgvector/pgvector:pg16`) alongside ragbot-api. The schema is applied automatically on first connection. Verify with:\n\n```bash\ndocker compose up -d postgres\ndocker compose exec postgres psql -U ragbot -d ragbot -c \"SELECT extversion FROM pg_extension WHERE extname='vector';\"\n```\n\nTo opt into the legacy embedded Qdrant backend instead, set `RAGBOT_VECTOR_BACKEND=qdrant` in `.env`.\n\n### 3. Build and Start the Web Interface\n\n```bash\n# Build the Docker image\ndocker-compose build\n\n# Start the web interface\ndocker-compose up -d\n\n# View logs\ndocker-compose logs -f ragbot-web\n```\n\n### 3. Access the Application\n\nOpen your browser and navigate to:\n```\nhttp://localhost:8501\n```\n\nThe Streamlit web interface should now be running!\n\n## Usage Examples\n\n### Web Interface (Streamlit)\n\n**Start the web interface:**\n```bash\ndocker-compose up -d ragbot-web\n```\n\n**Stop the web interface:**\n```bash\ndocker-compose down\n```\n\n**View real-time logs:**\n```bash\ndocker-compose logs -f ragbot-web\n```\n\n**Restart after config changes:**\n```bash\ndocker-compose restart ragbot-web\n```\n\n### CLI Interface\n\nThe CLI can be run as a one-off command using `docker-compose run`:\n\n**Get help:**\n```bash\ndocker-compose run --rm ragbot-cli --help\n```\n\n**Run with a prompt:**\n```bash\ndocker-compose run --rm ragbot-cli -p \"Your prompt here\"\n```\n\n**Interactive mode:**\n```bash\ndocker-compose run --rm ragbot-cli -i\n```\n\n**With custom dataset:**\n```bash\ndocker-compose run --rm ragbot-cli -p \"Analyze this data\" -d /app/datasets\n```\n\n**Note:** To enable the CLI service, uncomment the `ragbot-cli` section in `docker-compose.yml`.\n\n## Configuration\n\n### API Keys\n\nAPI keys are stored in `~/.synthesis/keys.yaml` (shared across synthesis-engineering products):\n\n```yaml\n# Ragbot API Keys\ndefault:\n  anthropic: \"sk-ant-...\"\n  openai: \"sk-...\"\n  google: \"...\"\n\n# Optional: workspace-specific key overrides\nworkspaces:\n  example-client:\n    anthropic: \"sk-ant-client-specific-key...\"\n```\n\nThis file should have restrictive permissions (`chmod 600`).\n\n### AI Knowledge Repositories\n\nRagbot automatically discovers workspaces from `ai-knowledge-*` repositories. For Docker:\n\n**Mount your ai-knowledge directory:**\n\nCreate `docker-compose.override.yml`:\n```yaml\nversion: '3.8'\n\nservices:\n  ragbot-web:\n    volumes:\n      # Mount ai-knowledge repos\n      - /path/to/ai-knowledge:/app/ai-knowledge:ro\n      # Mount keys configuration\n      - ~/.synthesis:/root/.synthesis:ro\n```\n\nThe workspaces are discovered automatically based on the `ai-knowledge-*` naming convention.\n\n### Engines Configuration\n\nThe `engines.yaml` file is included in the Docker image. To customize it:\n\n1. Edit `engines.yaml` locally\n2. Rebuild the image: `docker-compose build`\n3. Restart: `docker-compose up -d`\n\n## Data Persistence\n\nSession data is persisted using Docker volumes:\n\n```bash\n# List volumes\ndocker volume ls | grep ragbot\n\n# Inspect session data\ndocker volume inspect ragbot_ragbot-sessions\n\n# Backup sessions\ndocker run --rm -v ragbot_ragbot-sessions:/data -v $(pwd):/backup alpine tar czf /backup/sessions-backup.tar.gz -C /data .\n\n# Restore sessions\ndocker run --rm -v ragbot_ragbot-sessions:/data -v $(pwd):/backup alpine tar xzf /backup/sessions-backup.tar.gz -C /data\n```\n\n## Development Mode\n\nFor local development with hot-reload:\n\n```bash\n# The docker-compose.override.yml is automatically loaded\ndocker-compose up\n\n# Your code changes in ./src will automatically reload the Streamlit app\n```\n\n### Run Tests\n\n```bash\n# Run the test suite\ndocker-compose run --rm ragbot-test\n\n# Run specific test file\ndocker-compose run --rm ragbot-test tests/test_ragbot.py\n\n# Run with verbose output\ndocker-compose run --rm ragbot-test -v -s\n```\n\n## Production Deployment\n\n### Security Best Practices\n\n1. **Use Docker secrets** instead of environment variables:\n```yaml\nsecrets:\n  openai_api_key:\n    external: true\n```\n\n2. **Run as non-root user** (uncomment in Dockerfile):\n```dockerfile\nUSER ragbot\n```\n\n3. **Mount sensitive files as read-only:**\n```yaml\nvolumes:\n  - ~/.config/ragbot:/root/.config/ragbot:ro\n```\n\n### Resource Limits\n\nAdd resource constraints in `docker-compose.yml`:\n\n```yaml\nservices:\n  ragbot-web:\n    deploy:\n      resources:\n        limits:\n          cpus: '2.0'\n          memory: 2G\n        reservations:\n          memory: 512M\n```\n\n### Reverse Proxy (Nginx/Traefik)\n\nExample Nginx configuration:\n\n```nginx\nserver {\n    listen 80;\n    server_name ragbot.yourdomain.com;\n\n    location / {\n        proxy_pass http://localhost:8501;\n        proxy_http_version 1.1;\n        proxy_set_header Upgrade $http_upgrade;\n        proxy_set_header Connection \"upgrade\";\n        proxy_set_header Host $host;\n        proxy_set_header X-Real-IP $remote_addr;\n    }\n}\n```\n\n### Docker Compose Production Override\n\nCreate `docker-compose.prod.yml`:\n\n```yaml\nversion: '3.8'\n\nservices:\n  ragbot-web:\n    restart: always\n    deploy:\n      resources:\n        limits:\n          memory: 2G\n    logging:\n      driver: \"json-file\"\n      options:\n        max-size: \"10m\"\n        max-file: \"3\"\n```\n\nRun with:\n```bash\ndocker-compose -f docker-compose.yml -f docker-compose.prod.yml up -d\n```\n\n## Troubleshooting\n\n### Container won't start\n\n**Check logs:**\n```bash\ndocker-compose logs ragbot-web\n```\n\n**Verify environment variables:**\n```bash\ndocker-compose config\n```\n\n### Port already in use\n\nChange the port mapping in `docker-compose.yml`:\n```yaml\nports:\n  - \"8502:8501\"  # Use port 8502 instead\n```\n\n### API key not recognized\n\n**Verify environment variables are loaded:**\n```bash\ndocker-compose exec ragbot-web env | grep API_KEY\n```\n\n**Rebuild if needed:**\n```bash\ndocker-compose down\ndocker-compose up --build\n```\n\n### Session data not persisting\n\n**Check volume is created:**\n```bash\ndocker volume ls | grep ragbot\n```\n\n**Inspect volume mount:**\n```bash\ndocker-compose exec ragbot-web ls -la /root/.local/share/ragbot/sessions/\n```\n\n### Permission issues with mounted volumes\n\n**On Linux, you may need to set permissions:**\n```bash\nsudo chown -R 1000:1000 datasets instructions\n```\n\nOr uncomment the non-root user section in the Dockerfile.\n\n## Publishing to Docker Hub\n\n```bash\n# Tag the image\ndocker tag ragbot:latest yourusername/ragbot:latest\ndocker tag ragbot:latest yourusername/ragbot:v1.0.0\n\n# Push to Docker Hub\ndocker push yourusername/ragbot:latest\ndocker push yourusername/ragbot:v1.0.0\n```\n\nThen others can use:\n```bash\ndocker pull yourusername/ragbot:latest\ndocker run -p 8501:8501 -e OPENAI_API_KEY=your-key yourusername/ragbot:latest\n```\n\n## Advanced Usage\n\n### Custom Streamlit Configuration\n\nCreate `.streamlit/config.toml`:\n\n```toml\n[server]\nport = 8501\naddress = \"0.0.0.0\"\nheadless = true\n\n[theme]\nprimaryColor = \"#F63366\"\nbackgroundColor = \"#FFFFFF\"\nsecondaryBackgroundColor = \"#F0F2F6\"\n```\n\nMount it:\n```yaml\nvolumes:\n  - ./.streamlit:/app/.streamlit:ro\n```\n\n### Multi-stage Deployment\n\nBuild once, deploy everywhere:\n\n```bash\n# Build\ndocker-compose build\n\n# Save image\ndocker save ragbot:latest | gzip \u003e ragbot-docker-image.tar.gz\n\n# On another server\ngunzip -c ragbot-docker-image.tar.gz | docker load\ndocker-compose up -d\n```\n\n## Updating\n\n```bash\n# Pull latest code\ngit pull\n\n# Rebuild and restart\ndocker-compose down\ndocker-compose build --no-cache\ndocker-compose up -d\n```\n\n## Cleanup\n\n```bash\n# Stop and remove containers\ndocker-compose down\n\n# Remove volumes (WARNING: deletes session data)\ndocker-compose down -v\n\n# Remove images\ndocker rmi ragbot:latest\n\n# Complete cleanup\ndocker system prune -a\n```\n\n## Support\n\nFor issues and questions:\n- GitHub Issues: https://github.com/rajivpant/ragbot/issues\n- Documentation: See main README.md\n\n## License\n\nSame as Ragbot.AI - see LICENSE file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajivpant%2Fragbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frajivpant%2Fragbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajivpant%2Fragbot/lists"}