{"id":27646912,"url":"https://github.com/wayzeek/customgpt","last_synced_at":"2026-04-30T13:34:11.967Z","repository":{"id":233290580,"uuid":"781121800","full_name":"wayzeek/CustomGPT","owner":"wayzeek","description":"CustomGPT is a multilingual chatbot that streamlines text extraction and analysis from PDFs.","archived":false,"fork":false,"pushed_at":"2024-04-14T13:56:45.000Z","size":16721,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-24T01:32:37.105Z","etag":null,"topics":["ai","huggingface","langchain","llms","mixtral","private-gpt"],"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/wayzeek.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,"zenodo":null}},"created_at":"2024-04-02T19:39:37.000Z","updated_at":"2025-02-08T17:53:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"dc96fda0-ff62-4854-bea6-d66dd9139c1a","html_url":"https://github.com/wayzeek/CustomGPT","commit_stats":null,"previous_names":["wayzeek/customgpt"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wayzeek/CustomGPT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wayzeek%2FCustomGPT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wayzeek%2FCustomGPT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wayzeek%2FCustomGPT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wayzeek%2FCustomGPT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wayzeek","download_url":"https://codeload.github.com/wayzeek/CustomGPT/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wayzeek%2FCustomGPT/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32466333,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"ssl_error","status_checked_at":"2026-04-30T13:12:06.837Z","response_time":57,"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":["ai","huggingface","langchain","llms","mixtral","private-gpt"],"created_at":"2025-04-24T01:25:43.347Z","updated_at":"2026-04-30T13:34:11.962Z","avatar_url":"https://github.com/wayzeek.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🤖 CustomGPT - Chat with your Data 📚 \n\nCustomGPT is a *sophisticated*, **multilingual chatbot** designed to streamline the *extraction, processing, and interaction* with text data from **PDF documents**.\\\nLeveraging *advanced NLP* and *machine learning models*, it enables *rich*, *interactive communication* across multiple languages, making it ideal for businesses, educational institutions or individuals dealing with diverse document formats.\n\n## 📚 Table of Contents\n\n- [Introduction](#introduction)\n- [Features](#features)\n- [Getting Started](#getting-started)\n  - [Installation](#installation)\n- [Usage](#usage)\n- [Contributing](#contributing)\n- [Credits](#credits)\n- [License](#license)\n\n## 📖 Introduction\n\nCustomGPT harnesses the power of *conversational AI* to enhance the way organizations or individuals handle document-based information.\\\nBy *automatically extracting* and *analyzing text from PDFs* and facilitating dynamic interactions through its chatbot interface, CustomGPT transforms static data into *actionable insights*. \\\nThis integration of document processing with advanced dialogue systems offers a *unique solution* that significantly *boosts productivity* and *user engagement*.\n\n### Screenshot\n![image](https://github.com/wayzeek/CustomGPT/assets/112975047/a8cb0a07-af4a-4971-b8d6-002fac673271)\n\n\n## ✨ Features\n\n- **PDF Text Extraction**: Utilizes **PyPDF2** for efficient text extraction from PDFs, handling multiple layouts and formats.\n- **Advanced Text Processing**: Integrates **tokenizers** and **Spacy** text splitters for text segmentation, and employs Spacy Language Detection module for robust language detection, ensuring precise text analysis.\n- **Multilingual Support**: Powered by multiple instances of the transformer-based large language models **Mistral-7B-Instruct-v0.2**, supports interactions in multiple languages using **Hugging Face API**:\n  - **English** 🇬🇧\n  - **Spanish** 🇪🇸\n  - **French** 🇫🇷\n  - **German** 🇩🇪\n  - **Italian** 🇮🇹\n  - **Ukrainian** 🇺🇦\n  - **Russian** 🇷🇺\n  - **Chinese** 🇨🇳\n  - **Japanese** 🇯🇵\n- **Interactive User Interface**: Offers a user-friendly command-line interface that may evolve into a more graphical interface.\n\n## 🚀 Getting Started\n\n### ⚙️ Installation\n- **Step 1:** clone the repo\n```bash\ngit clone https://github.com/wayzeek/CustomGPT.git\n```\n- **Step 2:** navigate to the directory\n```bash\ncd CustomGPT\n```\n- **Step 3:** install dependencies\n```bash\nbash install.sh\n```\n- **Step 4:** move to virtual environment\n```bash\nsource .venv/bin/activate\n```\n- **Step 5:** start application\n```bash\npython3 main.py \n```\n\n## 🔍 Usage\n\n### Process PDFs\n- **Step 1:** add your PDFs to the data directory\n- **Step 2:** launch application\n```python\npython3 main.py\n```\n- **Step 3:** *select* if your PDFs is *structured* by Markdowns (Chapters, Titles, ...) *or not*\n- **Step 4:** Choose the chunk size *aka* the average sizes of your paragraph\n- **Step 5:** *Wait* \u0026 **enjoy chating with your data** !\n\n## 🤝 Contributing\n\n1. Fork the repo\n2. Create your feature branch (`git checkout -b feature/amazingFeature`)\n3. Commit your changes (`git commit -am 'Add some amazingFeature'`)\n4. Push to the branch (`git push origin feature/amazingFeature`)\n5. Open a pull request\n\n## 🏆 Credits\n\nThis is a solo project made by [myself](https://github.com/wayzeek)\n\n## ⚖️ License\n\nMIT License - see the [LICENSE](LICENSE) file for details\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwayzeek%2Fcustomgpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwayzeek%2Fcustomgpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwayzeek%2Fcustomgpt/lists"}