{"id":27350539,"url":"https://github.com/reinterpretcat/local_assist","last_synced_at":"2026-07-10T14:33:26.225Z","repository":{"id":270472318,"uuid":"910481841","full_name":"reinterpretcat/local_assist","owner":"reinterpretcat","description":"A simple GUI for local hosted LLM (via Ollama)","archived":false,"fork":false,"pushed_at":"2025-02-13T19:48:19.000Z","size":341,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-12T19:42:52.886Z","etag":null,"topics":["ai","llm","llm-apps","ollama-gui"],"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/reinterpretcat.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,"zenodo":null}},"created_at":"2024-12-31T11:50:49.000Z","updated_at":"2025-02-12T20:12:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"22c8698f-975a-41d5-8bae-ac8db4549767","html_url":"https://github.com/reinterpretcat/local_assist","commit_stats":null,"previous_names":["reinterpretcat/local_assist"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/reinterpretcat/local_assist","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reinterpretcat%2Flocal_assist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reinterpretcat%2Flocal_assist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reinterpretcat%2Flocal_assist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reinterpretcat%2Flocal_assist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reinterpretcat","download_url":"https://codeload.github.com/reinterpretcat/local_assist/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reinterpretcat%2Flocal_assist/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35334719,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-10T02:00:06.465Z","response_time":60,"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":["ai","llm","llm-apps","ollama-gui"],"created_at":"2025-04-12T19:39:36.844Z","updated_at":"2026-07-10T14:33:26.208Z","avatar_url":"https://github.com/reinterpretcat.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Personal AI Chat Assistant\n\nAn experimental AI Chat client built with Python/Tkinter for experimentation with local hosted LLMs (ollama). This project represents a \"learn by doing\" approach where various LLMs (including the ones consumed through the chat client itself) helped in the development process.\n\n![image](https://github.com/user-attachments/assets/a9191b08-8666-4f1c-ac7c-cac6d6f0ffd1)\n\n![image](https://github.com/user-attachments/assets/0a53957a-4803-4b6f-ba52-4f1f5410b55a)\n\n\n\n## Project Philosophy\n\nThis is an experimental project focusing on functionality over code architecture. Some interesting aspects:\n\n- Built primarily for personal use and experimentation with local LLM models\n- Code was generated with help of various LLMs\n- The application was partially used to improve itself - it generated some of its own code!\n- Prioritizes rapid experimentation over architectural patterns (no tests, no good design)\n- My primary use cases:\n  - Learning AI Engineering: experimental playground for understanding capabilities of local hosted LLM on consumer hardware\n  - Language learning through AI conversation (e.g. with German TTS/STT configs)\n  - Code assistant\n\n## Key Features\n\n- Integration with Ollama for local LLM hosting\n- Chat history with sqlite database and ability export/import chat data to json\n- Text-to-Speech (TTS) for AI responses\n- Speech-to-Text (STT) for voice input\n- Retrieval-Augmented Generation (RAG) support for chatting about your documents (via llama-index)\n- Code editor with ability to run code for some languages (python/rust)\n- Customizable system prompts and LLM settings (per chat)\n- Custom themes support\n- Basic markdown rendering support and syntax highlighting\n- Basic multi-model support (Image to Text)\n\n## Installation\n\n1. Install Ollama from https://ollama.com/download\n\n2. Pull desired LLM models:\n```bash\n# Basic models\nollama pull llama2:13b\nollama pull mistral:7b\n\n# Code-specific models\nollama pull qwen2.5-coder:7b\n\n# Language learning models (German)\nollama pull cyberwald/llama-3.1-sauerkrautlm-8b-instruct:q8_0\n\n# Multi-modal (to work with images)\nollama run llava-phi3\n```\n\n3. Install Python dependencies:\n```bash\npip install -r requirements.txt\n```\n\n4. Launch the application:\n```bash\npython3 -m src.main\n```\n\nNote: On first run, the application will automatically download required voices and dependencies for STT/TTS functionality.\n\n## Usage Examples\n\n### Basic Usage\n```bash\n# Default configuration\npython3 -m src.main\n\n# Check CUDA availability\npython3 -c 'import torch; print(torch.cuda.is_available())'\n```\n\n### Language Learning Configurations\n```bash\n# German learning mode\npython3 -m src.main --config config-de.json\n\n# Code assistant mode\npython3 -m src.main --config config-code.json\n```\n\n## RAG (Retrieval-Augmented Generation)\n\nThe application supports chatting with your documents through RAG:\n- Upload PDF, Markdown and TXT document formats\n- Automatic document embedding and indexing\n- Context-aware responses based on your documents\n\n## Known Limitations\n\n- Code structure prioritizes experimentation over maintainability\n- Some features may be unstable or experimental\n- UI is functional but basic\n- Limited error handling in some areas\n\n\n## License\n\nThis project is open source and available under the MIT License.\n\n## Acknowledgments\n\n- Initial inspiration from the [june](https://github.com/mezbaul-h/june) project\n- Various LLMs that helped generate and improve the code\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freinterpretcat%2Flocal_assist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freinterpretcat%2Flocal_assist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freinterpretcat%2Flocal_assist/lists"}