{"id":20904194,"url":"https://github.com/shivamarora1/youtube-gpt","last_synced_at":"2026-04-06T21:30:58.471Z","repository":{"id":238121737,"uuid":"789731042","full_name":"shivamarora1/youtube-gpt","owner":"shivamarora1","description":"Youtube GPT","archived":false,"fork":false,"pushed_at":"2024-05-18T09:49:12.000Z","size":231,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-28T09:56:48.822Z","etag":null,"topics":["llm","mistral-7b","nltk","qdrant","rag","retrieval-augmented-generation","streamlit","summarization","youtube"],"latest_commit_sha":null,"homepage":"https://youtube-ai-gpt.streamlit.app/","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/shivamarora1.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}},"created_at":"2024-04-21T12:02:27.000Z","updated_at":"2024-12-19T14:11:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"1741745f-2757-4158-924b-fa8c0051e9da","html_url":"https://github.com/shivamarora1/youtube-gpt","commit_stats":null,"previous_names":["shivamarora1/youtube-gpt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/shivamarora1/youtube-gpt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamarora1%2Fyoutube-gpt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamarora1%2Fyoutube-gpt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamarora1%2Fyoutube-gpt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamarora1%2Fyoutube-gpt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shivamarora1","download_url":"https://codeload.github.com/shivamarora1/youtube-gpt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivamarora1%2Fyoutube-gpt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31491094,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-06T17:22:55.647Z","status":"ssl_error","status_checked_at":"2026-04-06T17:22:54.741Z","response_time":112,"last_error":"SSL_read: 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":["llm","mistral-7b","nltk","qdrant","rag","retrieval-augmented-generation","streamlit","summarization","youtube"],"created_at":"2024-11-18T13:16:17.436Z","updated_at":"2026-04-06T21:30:58.306Z","avatar_url":"https://github.com/shivamarora1.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Youtube GPT: Converse with Youtube video\n![resized_speed_up](https://github.com/shivamarora1/youtube-gpt/assets/28146775/0d5fb99d-b3f6-4e2e-a8bb-d12e515ec71f)\n\nThis [Streamlit](https://streamlit.io/) application helps you in summarizing YouTube videos, making it easier to digest content efficiently. Additionally, it allows users to pose follow-up questions related to the video, and the application generates pertinent responses, enhancing engagement and understanding.\n\n### Steps to run on local:\n---\n1. Create and activate virtual environment\n```\npython3 -m venv .venv\nsource .venv\n```\n2. Download all dependencies\n```\npip install -r requirements.txt\n```\n3. Run application\n```\nstreamlit run main.py \n```\n\n### App overview\n---\n1. Enter Youtube video link in left side bar.\n2. Using Youtube Transcription api application will fetch transcriptions of Youtube video.\n3. Fetched transcriptions are sent to `Mistral-7B-instruction` model for summarization.\n4. Embeddings of transcriptions are generated using `all-MiniLM-L6-v2` model\n5. Generated embeddings are stored in `Qdrant` in memory vector database.\n6. When you follow question relevant similar Youtube video context is fetched from vector database and that context is sent to `Mistral-7B-instruction` model along with question.\n7. `Mistral-7B-instruction` uses fetched background context and gives answer of asked question. \n\u003cbr\u003e\u003cbr\u003e\n\n    #### Limitations\n    1. Youtube videos larger that 30 minutes length are not supported.\n    2. Youtube video only in english language are only supported.\n\n### Architecture diagram\n![arch](https://github.com/shivamarora1/youtube-gpt/assets/28146775/5bfd6cf4-34b9-4558-8a75-f4360ba5e16d)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivamarora1%2Fyoutube-gpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshivamarora1%2Fyoutube-gpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivamarora1%2Fyoutube-gpt/lists"}