{"id":30184590,"url":"https://github.com/leoantony72/multi_model_vectorsearch","last_synced_at":"2026-05-06T00:35:29.616Z","repository":{"id":309081227,"uuid":"1026984353","full_name":"leoantony72/multi_model_vectorSearch","owner":"leoantony72","description":"Multi Model vector search with Redis","archived":false,"fork":false,"pushed_at":"2025-08-09T17:06:52.000Z","size":81,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-29T08:37:31.922Z","etag":null,"topics":["database","graph","python","redis","redis-cache","vector"],"latest_commit_sha":null,"homepage":"","language":"HTML","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/leoantony72.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}},"created_at":"2025-07-27T04:03:02.000Z","updated_at":"2025-08-09T17:06:56.000Z","dependencies_parsed_at":"2025-08-09T19:06:01.083Z","dependency_job_id":"4679d3a5-192b-428f-9221-5060fa0a0764","html_url":"https://github.com/leoantony72/multi_model_vectorSearch","commit_stats":null,"previous_names":["leoantony72/multi_model_vectorsearch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/leoantony72/multi_model_vectorSearch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoantony72%2Fmulti_model_vectorSearch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoantony72%2Fmulti_model_vectorSearch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoantony72%2Fmulti_model_vectorSearch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoantony72%2Fmulti_model_vectorSearch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/leoantony72","download_url":"https://codeload.github.com/leoantony72/multi_model_vectorSearch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leoantony72%2Fmulti_model_vectorSearch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":280965074,"owners_count":26421548,"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":"2025-10-25T02:00:06.499Z","response_time":81,"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":["database","graph","python","redis","redis-cache","vector"],"created_at":"2025-08-12T12:43:07.268Z","updated_at":"2025-10-25T13:47:29.811Z","avatar_url":"https://github.com/leoantony72.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Real-Time Multi-Modal Semantic Search System\n\nThis project is a **real-time, multi-modal semantic search system** that combines **vector similarity search** with **graph-based context expansion**.  \nIt supports both **text** and **image** search using locally computed **CLIP embeddings**.\n\n---\n\n## 📜 What I Built\n- **Local CLIP embeddings** for text and images (`openai/clip-vit-base-patch16`, 512-dim)\n- **Redis 8 vector index** with cosine similarity and KNN search\n- **Result caching** in Redis for low latency and reduced recompute\n- **NetworkX semantic graph** to link and rank related items beyond the initial top-K  \n  → enables richer, more explainable retrieval\n- **Duplicate prevention** using SHA-256 content hashing\n- **Endpoints** for:\n  - `submit` (ingest)\n  - `search` (retrieve)\n\n---\n\n## 🛠 Architecture Overview\n1. **Embed**: Text and images embedded locally via CLIP  \n2. **Index**: Vectors stored in Redis 8 (cosine similarity)  \n3. **Search**: Fast KNN lookups in Redis  \n4. **Expand**: Related items discovered via semantic graph traversal in NetworkX  \n5. **Cache**: Query results cached in Redis  \n6. **Serve**: Python handles API layer, embedding and indexing\n\n---\n\n## 🚀 Getting Started\n\n### 1️⃣ Start the required services\n```bash\ndocker-compose up -d\n```\n\n```bash\npython app.py\n```\n\n```bash\nfastapi dev main.py\n```\n\n\n### Running Addr\n```bash\nlocalhost:8000\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleoantony72%2Fmulti_model_vectorsearch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fleoantony72%2Fmulti_model_vectorsearch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleoantony72%2Fmulti_model_vectorsearch/lists"}