{"id":25616692,"url":"https://github.com/jcaperella29/ai_llm_set_up","last_synced_at":"2026-05-02T08:34:42.234Z","repository":{"id":278415854,"uuid":"935550825","full_name":"jcaperella29/Ai_LLM_set_up","owner":"jcaperella29","description":"AI-powered research paper summarization using local LLMs (Ollama). Extracts, processes, and summarizes PDFs with structured insights. Ideal for scientific papers \u0026 bioinformatics","archived":false,"fork":false,"pushed_at":"2025-02-19T16:25:08.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-19T17:27:25.484Z","etag":null,"topics":["ai","llm","machine-learning","nlp","ollama","pdf-processing","python","research"],"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/jcaperella29.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}},"created_at":"2025-02-19T16:20:25.000Z","updated_at":"2025-02-19T17:09:55.000Z","dependencies_parsed_at":"2025-02-19T17:39:02.383Z","dependency_job_id":null,"html_url":"https://github.com/jcaperella29/Ai_LLM_set_up","commit_stats":null,"previous_names":["jcaperella29/ai_llm_set_up"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FAi_LLM_set_up","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FAi_LLM_set_up/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FAi_LLM_set_up/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jcaperella29%2FAi_LLM_set_up/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jcaperella29","download_url":"https://codeload.github.com/jcaperella29/Ai_LLM_set_up/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240122818,"owners_count":19751180,"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":["ai","llm","machine-learning","nlp","ollama","pdf-processing","python","research"],"created_at":"2025-02-22T04:17:59.939Z","updated_at":"2026-05-02T08:34:42.192Z","avatar_url":"https://github.com/jcaperella29.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ai_LLM_set_up\n\n\n# AI LLM Paper Summarizer with Ollama\n\n## Overview\nThis project automates the extraction and summarization of research papers using **Local Large Language Models (LLMs)** via **Ollama**. It processes **scientific PDFs**, extracts relevant text, and generates structured summaries for each section.\n\n## Features\n- 📄 **Extracts text from scientific PDFs**\n- 🤖 **Summarizes research papers using Ollama** (Mistral, Gemma, or LLaMA models)\n- 🏗️ **Processes large documents in chunks** for better accuracy\n- 🔍 **Identifies key topics in life sciences \u0026 bioinformatics**\n\n## Setup Instructions\n### 1️⃣ Install Dependencies\nFirst, make sure you have Python installed. Then install the required libraries:\n```sh\npip install pymupdf requests\n```\n\n### 2️⃣ Install \u0026 Run Ollama\nDownload and install **Ollama** from [Ollama's website](https://ollama.com).\nStart the Ollama server:\n```sh\nollama serve\n```\nTo use a lighter model, install **Gemma** or **Mistral**:\n```sh\nollama pull gemma\nollama pull mistral\n```\n\n### 3️⃣ Run the Script\nActivate the virtual environment (if using one):\n```sh\ncd path/to/project\n.\\venv\\Scripts\\Activate  # On Windows\n```\nThen execute the script:\n```sh\npython LLM_test.py\n```\n\n## Optimization Options\n- Reduce **chunk size** (from 3000 to 1500 characters) for faster processing.\n- Use **lighter models** like `gemma` for better speed.\n- Adjust **Ollama's thread settings** for better CPU performance:\n  ```sh\n  OLLAMA_NUM_THREADS=8 ollama serve\n  ```\n\n## Next Steps\n- 📌 **Citation \u0026 Figure Extraction** (Upcoming Feature)\n- ⚡ **Parallel Processing** to speed up large document analysis\n- 🌐 **Cloud Integration** for faster summaries with OpenAI API\n\n## Contributing\nFeel free to fork the repo, submit issues, or suggest improvements!\n\n## License\nMIT License - Free to use and modify!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcaperella29%2Fai_llm_set_up","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjcaperella29%2Fai_llm_set_up","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcaperella29%2Fai_llm_set_up/lists"}