{"id":13454020,"url":"https://github.com/mukulpatnaik/researchgpt","last_synced_at":"2025-09-27T10:31:23.903Z","repository":{"id":65903576,"uuid":"595940434","full_name":"mukulpatnaik/researchgpt","owner":"mukulpatnaik","description":"A LLM based research assistant that allows you to have a conversation with a research paper","archived":true,"fork":false,"pushed_at":"2023-11-21T01:54:29.000Z","size":593,"stargazers_count":3556,"open_issues_count":0,"forks_count":335,"subscribers_count":41,"default_branch":"main","last_synced_at":"2025-01-17T20:38:05.797Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://www.dara.chat","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/mukulpatnaik.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}},"created_at":"2023-02-01T05:46:57.000Z","updated_at":"2025-01-17T17:13:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"ce73171c-cb52-4c66-a569-b2aa457e4666","html_url":"https://github.com/mukulpatnaik/researchgpt","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mukulpatnaik/researchgpt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukulpatnaik%2Fresearchgpt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukulpatnaik%2Fresearchgpt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukulpatnaik%2Fresearchgpt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukulpatnaik%2Fresearchgpt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mukulpatnaik","download_url":"https://codeload.github.com/mukulpatnaik/researchgpt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukulpatnaik%2Fresearchgpt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":277218847,"owners_count":25781446,"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":"2025-09-27T02:00:08.978Z","response_time":73,"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":"2024-07-31T08:00:50.350Z","updated_at":"2025-09-27T10:31:23.655Z","avatar_url":"https://github.com/mukulpatnaik.png","language":"Python","funding_links":[],"categories":["Python","Documentations, Tutorials \u0026 Other Resources","Web Apps","Chatbots","web应用","精选开源项目合集","Uncategorized","Specialized Agent Applications","ChatGPT 工具","排行榜 [2025-03-18]","SDK, Libraries, Frameworks"],"sub_categories":["Prompts","Special-purpose","Emacs","特殊用途","GPT工具","Uncategorized","LangManus","[科研助手：researchgpt](https://github.com/mukulpatnaik/researchgpt)","Python library, sdk or frameworks"],"readme":"## **This repository is no longer actively maintained. A more advanced version of this project is available at [chat.portal.so](https://chat.portal.so) for free and will be open sourced soon.**\n\n# ResearchGPT\n\nThis is a simple fastapi app that provides a clean interface to enable a conversation with any pdf. You can enter a link to a pdf hosted online or upload your own pdf. The app will then extract the text from the pdf, create embeddings from the text and use them with the openai api to generate a response to a question you ask. It will also return a source for the part of the text it used to generate the response and the page number. \n\nTry the demo at: https://www.dara.chat\n\n## Example \n(this video shows some features available on the [live demo](https://www.dara.chat) only )\n\nhttps://user-images.githubusercontent.com/36257370/230793133-ecb579d3-47d9-4200-916a-9c5978a40b09.mp4\n\n## Installation\n\n```bash\ngit clone https://github.com/mukulpatnaik/researchgpt.git\ncd researchgpt\npip install -r requirements.txt\n```\n\nYou also need redis for storing the embeddings locally on your machine. You can find installation instructions here: https://redis.io/docs/getting-started/installation/. To start the db, run the following command in your terminal.\n\nOn MacOS:\n\n```bash\nredis-server\n```\n\nOn Windows:\n\n```bash\nsudo service redis-server start\n```\n\n## Usage\n\nYou need to have an openai api key and set it as the environment variable 'OPENAI_API_KEY'.\n\nYou can get the OpenAI API key here - https://platform.openai.com/account/api-keys\n\nTo set your environment variable open your .bashrc or .zshrc and add the line `export OPENAI_API_KEY=\"your-key`, make sure to put your actual key instead of \"your-key\".\n\n```bash\nuvicorn main:app --reload\n```\n\n## Contributing\n\nPull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.\n\n## License\n\n[MIT](https://choosealicense.com/licenses/mit/)\n\nIf you would like to collaborate on this project, please reach out to me at mukulpatnaik@gmail.com or find me on [twitter](https://twitter.com/mukul0x)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmukulpatnaik%2Fresearchgpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmukulpatnaik%2Fresearchgpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmukulpatnaik%2Fresearchgpt/lists"}