{"componentChunkName":"component---src-templates-project-page-js","path":"/project/archi/","result":{"data":{"site":{"siteMetadata":{"title":"M.Hassan Ahmed","author":"Hassan11196"}},"markdownRemark":{"id":"d466fc08-2534-5d01-aecd-ffc1ed655b54","excerpt":"Archi · LLM Copilot for CMS Ops Archi is a collaboration between MIT and CMS to help operators access the vast amount of documentation and logs behind CERN’s…","html":"<h1>Archi · LLM Copilot for CMS Ops</h1>\n<p>Archi is a collaboration between MIT and CMS to help operators access the vast amount of documentation and logs behind CERN’s systems. I lead the development for CMS computing operations, handling the data pipelines, backend, and frontend.</p>\n<p><strong>Source:</strong> <a href=\"https://github.com/archi-physics/archi\">github.com/archi-physics/archi</a></p>\n<h2>What I Did</h2>\n<ul>\n<li><strong>Data Ingestion:</strong> Built a crawler that authenticates through CERN SSO to index internal portals, JIRA tickets, and logbooks.</li>\n<li><strong>Processing Pipeline:</strong> Created a pipeline to clean and normalize data (Markdown, HTML, ticket metadata) for the retrieval system.</li>\n</ul>\n<h2>Why It’s Useful</h2>\n<ul>\n<li><strong>Faster Debugging:</strong> Helps operators find recurring issues quickly without searching through multiple tools.</li>\n<li><strong>Shared Knowledge:</strong> Makes it easier for shifters and coordinators to access the same information.</li>\n<li><strong>Future Proofing:</strong> Lays the groundwork for automated fixes based on the indexed knowledge base.</li>\n</ul>","frontmatter":{"title":"Archi · LLM Copilot for CMS Ops","pics":[{"childImageSharp":{"fluid":{"base64":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABQAAAAKCAYAAAC0VX7mAAAACXBIWXMAABYlAAAWJQFJUiTwAAABJ0lEQVQoz21Sy2rDMBDM/39I6TWn9tLk0jSBQqCHUkJbiu3YpvJDtnBw/ZCmrGIJy4pgvauVNDue3VXXdZgvpZT24zgijmMEQWB9GIaIoghSSufuPF4ZQLo0DINzoaoq5HmufcYYiqLQtgQye/IWUIgaaZp6lW8tc04EiH2SJDA4FrDiHFmWOdVM3OYF/kp+zUvpnNEfMMasDBaQwKia1Wfy4hzjuNnhbfOCyy/zdBZCoK5rHXsamqRmMAFmHyfstq/YPx3Av3+cYuYNmcdwKbLVUSkNmp8+zVZ/ljp7XSaB+753NLyyUJBqhIL0zmiVZYm2bf0uk4Y0Y7eacv94wN3D3ss3TaN1p+kgMg5DSswrkcnp4fb4hfXzu2VsADnnOEeRHniD8w8wOgqBHJbOXAAAAABJRU5ErkJggg==","aspectRatio":1.92090395480226,"src":"/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/40a76/archi.png","srcSet":"/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/c972b/archi.png 340w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/27625/archi.png 680w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/40a76/archi.png 1360w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/ca459/archi.png 1766w","sizes":"(max-width: 1360px) 100vw, 1360px"}}}],"date":"2024-05-15T00:00:00.000Z","description":"Partnering with MIT to build an LLM-powered RAG copilot for CMS computing operations.","thumbnail":{"childImageSharp":{"fluid":{"base64":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABQAAAAKCAYAAAC0VX7mAAAACXBIWXMAABYlAAAWJQFJUiTwAAABJ0lEQVQoz21Sy2rDMBDM/39I6TWn9tLk0jSBQqCHUkJbiu3YpvJDtnBw/ZCmrGIJy4pgvauVNDue3VXXdZgvpZT24zgijmMEQWB9GIaIoghSSufuPF4ZQLo0DINzoaoq5HmufcYYiqLQtgQye/IWUIgaaZp6lW8tc04EiH2SJDA4FrDiHFmWOdVM3OYF/kp+zUvpnNEfMMasDBaQwKia1Wfy4hzjuNnhbfOCyy/zdBZCoK5rHXsamqRmMAFmHyfstq/YPx3Av3+cYuYNmcdwKbLVUSkNmp8+zVZ/ljp7XSaB+753NLyyUJBqhIL0zmiVZYm2bf0uk4Y0Y7eacv94wN3D3ss3TaN1p+kgMg5DSswrkcnp4fb4hfXzu2VsADnnOEeRHniD8w8wOgqBHJbOXAAAAABJRU5ErkJggg==","aspectRatio":1.92090395480226,"src":"/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/40a76/archi.png","srcSet":"/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/c972b/archi.png 340w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/27625/archi.png 680w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/40a76/archi.png 1360w,\n/static/39c8dd0ef4dc6fe15f1d83c15a89c1bb/ca459/archi.png 1766w","sizes":"(max-width: 1360px) 100vw, 1360px"}}}}}},"pageContext":{"slug":"/archi/","previous":"projectundefined","next":"projectundefined"}},"staticQueryHashes":["32046230"]}