{"id":26398099,"url":"https://github.com/bessouat40/rag-scientific-papers","last_synced_at":"2025-03-17T12:20:01.981Z","repository":{"id":277052726,"uuid":"929750454","full_name":"Bessouat40/rag-scientific-papers","owner":"Bessouat40","description":"Automated pipeline that daily fetches, stores, and indexes arXiv research papers in MinIO.","archived":false,"fork":false,"pushed_at":"2025-03-05T09:49:12.000Z","size":13659,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-05T10:39:20.661Z","etag":null,"topics":["arxiv","arxiv-api","arxiv-daily","arxiv-papers","automation","database","minio","minio-client","prefect","python"],"latest_commit_sha":null,"homepage":"","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/Bessouat40.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":"2025-02-09T10:03:23.000Z","updated_at":"2025-03-05T09:49:15.000Z","dependencies_parsed_at":"2025-03-05T10:39:23.406Z","dependency_job_id":null,"html_url":"https://github.com/Bessouat40/rag-scientific-papers","commit_stats":null,"previous_names":["bessouat40/arxivflow","bessouat40/rag-scientific-papers"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Frag-scientific-papers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Frag-scientific-papers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Frag-scientific-papers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Frag-scientific-papers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Bessouat40","download_url":"https://codeload.github.com/Bessouat40/rag-scientific-papers/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244031030,"owners_count":20386534,"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","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":["arxiv","arxiv-api","arxiv-daily","arxiv-papers","automation","database","minio","minio-client","prefect","python"],"created_at":"2025-03-17T12:20:01.450Z","updated_at":"2025-03-17T12:20:01.975Z","avatar_url":"https://github.com/Bessouat40.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG Scientific Papers\n\nRAG Scientific Papers is a project that enables you to automatically fetch, process, and ingest the latest ArXiv research papers on any given topic on a daily basis. This daily retrieval supports continuous technological monitoring, ensuring that you stay up-to-date with emerging research and trends. The pipeline is orchestrated using [Prefect](https://www.prefect.io/) for scheduling and seamless automation, and it stores the retrieved PDFs in a [MinIO](https://min.io/) object storage system for efficient management and retrieval.\n\nThank you to arXiv for use of its open access interoperability.\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"RAGLight\" height=\"500px\" src=\"./media/schema.png\"\u003e\n\u003c/div\u003e\n\n## Features\n\n- Fetch ArXiv Papers: Automatically query the ArXiv API for research papers based on a topic and publication date.\n- PDF Ingestion: Download the PDF files and store them in a MinIO bucket.\n- Embeddings extraction : Extract embeddings and store them inside Chroma vector store.\n- Pipeline Orchestration: Use Prefect flows and tasks to schedule and manage the pipelines.\n- UI to display pdf, read them and filter them.\n\n## Installation\n\n1. Clone the repository\n\n```bash\ngit clone https://github.com/Bessouat40/rag-scientific-papers.git\ncd rag-scientific-papers\n```\n\n2. Configure .env File\n\nYou'll need to rename **.env.example** file and fill it with your own values :\n\n```bash\nmv .env.example .env\n```\n\n3. Install the required packages\n\n```bash\npython -m pip install -r backend/requirements.txt\ncd frontend\nnpm i\n```\n\n## Usage\n\n### Start the Pipeline with Prefect locally\n\nYou can run the pipeline as a scheduled flow using Prefect. For example, to run the pipeline daily at midnight, use the Prefect deployment approach or serve the flow directly (for testing purposes).\n\n```bash\npython -m backend.main\n```\n\n### Running Pipelines and UI with Docker\n\nYou can now run Prefect flow and UI inside a Docker container :\n\n```bash\ndocker-compose up -d --build\n```\n\nNow you can access Prefect UI at [localhost:4200](http://localhost:4200/dashboard).\nYour flow will run every day at midnight.\n\nYou can access UI at [localhost:3000](http://localhost:3000).\n\n## Configuration\n\n### Topic\n\nThe pipeline fetches articles based on a given topic.\n\nYou can modify this parameter in the **.env** file.\n\n## TODO\n\n- [x] **Containerization with Docker:** Create a Dockerfile to containerize the application and manage its dependencies.\n\n- [x] **Embedding Extraction:** Use a model to extract and store embeddings from the PDFs for later semantic search.\n\n- [x] **Semantic Search:** Implement a semantic search feature that leverages the stored embeddings to enable more accurate article search.\n\n- [x] **Add UI**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbessouat40%2Frag-scientific-papers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbessouat40%2Frag-scientific-papers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbessouat40%2Frag-scientific-papers/lists"}