{"id":20839250,"url":"https://github.com/timoa/ai-gpt-experiments","last_synced_at":"2025-05-08T21:41:52.732Z","repository":{"id":167782192,"uuid":"643405212","full_name":"timoa/ai-gpt-experiments","owner":"timoa","description":"Experimentations related to run a local ChatGPT with privacy in mind","archived":false,"fork":false,"pushed_at":"2024-10-29T21:43:12.000Z","size":432,"stargazers_count":4,"open_issues_count":21,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-29T23:47:39.450Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/timoa.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"2023-05-21T03:48:34.000Z","updated_at":"2023-11-21T23:04:50.000Z","dependencies_parsed_at":"2024-05-03T23:34:22.680Z","dependency_job_id":"dcc08c64-3d88-45a2-b986-843b97206aa8","html_url":"https://github.com/timoa/ai-gpt-experiments","commit_stats":null,"previous_names":["timoa/gpt-experiments","timoa/ai-gpt-experiments"],"tags_count":287,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timoa%2Fai-gpt-experiments","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timoa%2Fai-gpt-experiments/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timoa%2Fai-gpt-experiments/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timoa%2Fai-gpt-experiments/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/timoa","download_url":"https://codeload.github.com/timoa/ai-gpt-experiments/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225110511,"owners_count":17422412,"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":[],"created_at":"2024-11-18T01:13:02.171Z","updated_at":"2024-11-18T01:13:03.324Z","avatar_url":"https://github.com/timoa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI GPT Experiments\n\nExperimentations related to run a local ChatGPT with privacy in mind.\nThe goal is to try to use only open-source LLM models and tools to keep the data private.\n\nNext step will be to expose the model as a service to be able to use it thru an API, and integrate it into as a ChatBot, mobile app or website.\n\nCurrently, it is written in Python, but I hope to be able to convert it in TypeScript when there will be more library available.\n\nBe aware that the ecosystem around AI is still in development and the projects are moving a lot (LLMs, libraries).\n\nI will try to keep this repository up-to-date, but let me know if you face any issue by opening an issue.\n\n\u003e **Note:** This project is still in development and currently run only on Apple M1. I'm currently searching which Python library doesn't work on Intel/AMD processor.\n\n## Introduction\n\nTo start, I'm using [GPT4All][gpt4all-website] to run a local ChatGPT model instead of using the OpenAI API.\n\n[GPT4All][gpt4all-website] is an open-source project that aims to provide a simple way to run a local GPT model ([GitHub][gpt4all-github]).\n\nTo provide more connectivity and features, I'm using [Langchain][langchain-website] to connect to the model and provide a simple CLI to interact with it ([GitHub][langchain-github]).\n\n## Roadmap\n\n- [x] Configure GPT4All to run locally\n- [x] Integrate Langchain with GPT4All\n- [x] Create a simple Question \u0026 Answering system (CLI)\n- [ ] Ingest PDF files and ask question about the content (CLI)\n\n## Installation\n\nFirst, it is recommended to create a virtual environment to install the dependencies.\n\nCreate a virtual environment:\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\n```\n\nThen, install the dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n## Download the LLM models\n\nSimply run the following command to download the models:\n\n```bash\npython setup.py\n```\n\n[gpt4all-website]: https://gpt4all.com/\n[gpt4all-github]: https://github.com/nomic-ai/gpt4all\n[langchain-website]: https://langchain.io/\n[langchain-github]: https://github.com/hwchase17/langchain\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimoa%2Fai-gpt-experiments","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftimoa%2Fai-gpt-experiments","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimoa%2Fai-gpt-experiments/lists"}