{"id":31919665,"url":"https://github.com/martingaida/embedding_atlas","last_synced_at":"2025-10-13T21:46:05.809Z","repository":{"id":309438141,"uuid":"1036235745","full_name":"martingaida/embedding_atlas","owner":"martingaida","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-22T13:38:16.000Z","size":2880,"stargazers_count":8,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-22T15:39:52.348Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/martingaida.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,"zenodo":null}},"created_at":"2025-08-11T19:05:19.000Z","updated_at":"2025-08-22T13:38:20.000Z","dependencies_parsed_at":"2025-08-11T23:41:18.310Z","dependency_job_id":null,"html_url":"https://github.com/martingaida/embedding_atlas","commit_stats":null,"previous_names":["martingaida/embedding_atlas"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/martingaida/embedding_atlas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martingaida%2Fembedding_atlas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martingaida%2Fembedding_atlas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martingaida%2Fembedding_atlas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martingaida%2Fembedding_atlas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/martingaida","download_url":"https://codeload.github.com/martingaida/embedding_atlas/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/martingaida%2Fembedding_atlas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279017050,"owners_count":26085951,"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":"2025-10-13T02:00:06.723Z","response_time":61,"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":[],"created_at":"2025-10-13T21:45:53.343Z","updated_at":"2025-10-13T21:46:05.800Z","avatar_url":"https://github.com/martingaida.png","language":"Jupyter Notebook","funding_links":[],"categories":["Tools"],"sub_categories":["Administration"],"readme":"# Pinecone Embedding Atlas: Interactive Vector Visualization\n\nThis notebook demonstrates how to:\n- Set up and connect to Pinecone vector database with flexible namespace support\n- Fetch and process vectors from default, specific, or all namespaces\n- Create interactive visualizations using the [**Embedding Atlas**](https://apple.github.io/embedding-atlas/)\n- Compute text projections and display embedding relationships\n- Handle large-scale vector operations with batch processing\n\n## Prerequisites\n- Pinecone API key and index setup\n- Environment variables configured in `.env` file (see `.env.example`)\n- Required Python packages installed\n- Vectors already stored in your Pinecone index\n\n# Namespace configuration (optional)\n```bash\nPINECONE_NAMESPACE=\"\"        # Default: empty string (default namespace)\n#PINECONE_NAMESPACE=\"all\"     # Fetch from all namespaces\n#PINECONE_NAMESPACE=\"prod\"    # Fetch from specific namespace\n\n# Limit number of vectors to fetch\nMAX_COUNT=1000               # Set to integer or leave unset/set to None for all vectors\n```\n\n## Notebook Structure\n1. **Package Installation** - Install required dependencies\n2. **Environment Setup** - Load configuration and validate settings\n3. **Pinecone Connection** - Initialize client and verify index access\n4. **Namespace Configuration** - Set up flexible namespace handling\n5. **Vector Retrieval** - Retrieve vectors from configured namespaces\n6. **Data Processing** - Convert vectors to DataFrame for analysis\n7. **Basic Visualization** - Create EmbeddingAtlasWidget without projections\n8. **Text Projection** - Compute and visualize embedding projections\n9. **Advanced Visualization** - Interactive widget with full functionality\n\n## Key Features\n\n### Flexible Namespace Support\n- **Default**: Fetch from default namespace (empty string)\n- **All**: Fetch from all available namespaces\n- **Specific**: Fetch from a named namespace\n- Automatic fallback to default if specified namespace doesn't exist\n\n### Batch Processing\n- Efficient fetching of large vector collections\n- Configurable batch sizes for optimal performance\n- Progress tracking with detailed logging\n\n### Interactive Visualizations\n- Table view of vector metadata\n- Charts and statistics\n- 2D embedding projections\n- Text-based similarity exploration\n\n## Important Notes\n\n**Widget Loading**: If you see \"Widgets require us to download supporting files from a 3rd party website\", click `OK` to enable the interactive visualizations.\n\n**Performance**: For large datasets, consider setting `MAX_COUNT` to limit the number of vectors processed initially.\n\n**Namespace Strategy**: \n- Use `\"\"` (default) for development and testing\n- Use specific namespaces for production data separation\n- Use `\"all\"` for comprehensive analysis across all data\n\n## Troubleshooting\n\n- **No vectors found**: Verify your index contains data and namespace configuration is correct\n- **Connection errors**: Check your API key and network connectivity\n- **Widget not loading**: Ensure you have the latest version of `embedding-atlas` installed\n- **Memory issues**: Reduce `MAX_COUNT` or process data in smaller batches\n\nReady to explore your vector database? Let's get started! 🚀","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmartingaida%2Fembedding_atlas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmartingaida%2Fembedding_atlas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmartingaida%2Fembedding_atlas/lists"}