{"id":28255548,"url":"https://github.com/swagath18/personalized-recommender","last_synced_at":"2026-04-11T18:05:10.869Z","repository":{"id":293559381,"uuid":"984410451","full_name":"Swagath18/Personalized-Recommender","owner":"Swagath18","description":null,"archived":false,"fork":false,"pushed_at":"2025-05-15T23:30:27.000Z","size":43,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-25T03:47:34.379Z","etag":null,"topics":["faiss-vector-database","gpt-4","gradio","numpy","openai","python","rag","recommendation","sentiment-classification","transformer"],"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/Swagath18.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":"2025-05-15T22:18:23.000Z","updated_at":"2025-05-15T23:32:45.000Z","dependencies_parsed_at":"2025-05-16T00:36:10.438Z","dependency_job_id":null,"html_url":"https://github.com/Swagath18/Personalized-Recommender","commit_stats":null,"previous_names":["swagath18/personalized-recommender"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Swagath18/Personalized-Recommender","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swagath18%2FPersonalized-Recommender","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swagath18%2FPersonalized-Recommender/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swagath18%2FPersonalized-Recommender/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swagath18%2FPersonalized-Recommender/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Swagath18","download_url":"https://codeload.github.com/Swagath18/Personalized-Recommender/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Swagath18%2FPersonalized-Recommender/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269982061,"owners_count":24507301,"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":"2025-08-11T02:00:10.019Z","response_time":75,"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":["faiss-vector-database","gpt-4","gradio","numpy","openai","python","rag","recommendation","sentiment-classification","transformer"],"created_at":"2025-05-19T22:13:56.832Z","updated_at":"2026-04-11T18:05:10.829Z","avatar_url":"https://github.com/Swagath18.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM-Powered Personalized Product Recommender\n\nA context-aware recommendation system powered by **Retrieval-Augmented Generation (RAG)** and **GPT-4**, enhanced with **hybrid reranking** and a **feedback sentiment analysis system** using VADER.\n\n## Workflow\n\n![Workflow](./workflow.png)\n\n##  Features\n\n- Semantic product search with FAISS + Sentence Transformers\n- GPT-4 for natural language product recommendations\n- Personalized reranking using user context + cosine similarity\n- Multi-tab UI with Gradio (Recommendations + Feedback)\n- Feedback logging with real-time sentiment analysis (VADER)\n- Logged query, prompt, and model responses for auditability\n\n## Stack\n\n- Python \n- SentenceTransformers (MiniLM-L6-v2)\n- FAISS (vector search)\n- OpenAI (GPT-4 API)\n- VADER Sentiment Analysis\n- Gradio (for UI)\n- Pandas, Numpy, Scikit-learn\n\n## Folder Structure\n\n```\n.\n├── llmpoweredrag.py                 # Main app script\n├── amazon_electronics_products.csv # Sample dataset\n├── .env                             # API keys\n├── recommendation_log.txt          # GPT prompt/response logs\n├── feedback_log.txt                # Feedback + sentiment logs\n└── README.md\n```\n\n## Setup Instructions\n\n```bash\ngit clone https://github.com/yourusername/llm-personalized-recommender.git\ncd llm-personalized-recommender\npip install -r requirements.txt\npython llmragsenti.py\n```\n\nMake sure your `.env` file contains:\n\n```\nOPENAI_API_KEY=your-api-key-here\n```\n\n## Try These Test Cases\n\n**Query:**  \n`best noise-cancelling headphones for Zoom calls`\n\n**Context:**  \n```\nprefers Bose or Sony\nneeds comfort for extended meetings\nwants good microphone quality\n```\n\nClick \"Recommend\" and observe the GPT-4 output with ranked FAISS items.\n\nThen test feedback like:\n```\nThe suggestions made no sense. I didn’t find them helpful.\n```\n\n## Output Example\n\n```text\nRetrieved Products:\nSony WH-1000XM4 (Context Score: 0.874)\nBose QC35 II (Context Score: 0.832)\n\nGPT-4 Recommendations:\n1. Sony WH-1000XM4 - Superior noise cancellation...\n2. Bose QC35 II - Excellent comfort and clarity...\n```\n\n## Sentiment Feedback Log\n\nEach entry is saved with timestamp and label:\n```\n[2025-04-24 15:06:36] User Feedback: Loved it! | Sentiment: positive (0.89)\n```\n\n## License\n\nMIT\n\n##  Future Improvements\n\n- Add image-based product cards\n- Deploy on Hugging Face Spaces or Streamlit Cloud\n- Build dashboard with feedback insights\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswagath18%2Fpersonalized-recommender","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fswagath18%2Fpersonalized-recommender","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswagath18%2Fpersonalized-recommender/lists"}