{"id":23958188,"url":"https://github.com/ikajdan/llem","last_synced_at":"2026-05-04T22:41:15.735Z","repository":{"id":271079652,"uuid":"912215589","full_name":"ikajdan/llem","owner":"ikajdan","description":"A self-contained web interface for LLMs ","archived":false,"fork":false,"pushed_at":"2025-01-05T17:09:46.000Z","size":14,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-20T10:54:03.776Z","etag":null,"topics":["flask","llm","machine-learning","python","transformers"],"latest_commit_sha":null,"homepage":"","language":"CSS","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/ikajdan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2025-01-04T23:41:26.000Z","updated_at":"2025-01-05T19:23:48.000Z","dependencies_parsed_at":"2025-01-05T11:21:26.272Z","dependency_job_id":"24b9922d-1d0f-48c2-964d-0d5a99d0b2fa","html_url":"https://github.com/ikajdan/llem","commit_stats":null,"previous_names":["ikajdan/llem"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ikajdan/llem","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikajdan%2Fllem","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikajdan%2Fllem/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikajdan%2Fllem/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikajdan%2Fllem/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ikajdan","download_url":"https://codeload.github.com/ikajdan/llem/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikajdan%2Fllem/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32628211,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"ssl_error","status_checked_at":"2026-05-04T10:08:02.005Z","response_time":58,"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":["flask","llm","machine-learning","python","transformers"],"created_at":"2025-01-06T17:30:00.078Z","updated_at":"2026-05-04T22:41:15.708Z","avatar_url":"https://github.com/ikajdan.png","language":"CSS","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLEM\n\nLLEM is a simple and self-contained web interface for interacting with a Large Language Model (LLM) that can generate text based on user input. This project provides a Flask-based web application that allows users to chat with a model, giving answers to questions or completing prompts. It can be used with any model that supports the Hugging Face Transformers library.\n\n\u003cbr\u003e\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/user-attachments/assets/e653900c-57a7-49e4-b7ec-835852916452\" width=\"700\" height=\"auto\"/\u003e\n  \u003cbr\u003e\u003cbr\u003e\n  \u003cem\u003eDemo of the interface.\u003c/em\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n## Features\n\n- A web interface to interact with a pre-trained Large Language Model.\n- Simple prompt-based interactions where users can chat with the AI.\n- Powered by the Hugging Face transformers library for model handling.\n\n## Setup\n\nYou can run the application using Docker or manually. The manual setup has only been tested with Python 3.12.\n\n### Download the Model\n\nThe `download_model.py` script downloads the pre-trained model from Hugging Face and saves it locally in the `model` directory. By default, it fetches the `SmolLM2-135M-Instruct` model.\n\nMake sure the required dependencies are installed and then run the script:\n```bash\npython download_model.py\n```\n\n### Docker Setup\n\nThe easiest way to run the application is using Docker. This will handle all dependencies and environment setup.\n\n1. Download the model as described above.\n2. Build the image:\n  ```bash\n  docker compose build\n  ```\n3. Run the container:\n  ```bash\n  docker compose up\n  ```\n\nThe app will be accessible at [http://localhost:5000](http://localhost:5000).\n\n### Manual Setup\n\nIf you prefer to run the application manually, follow steps below.\n\n1. Set up a Python virtual environment:\n  ```bash\n  python3 -m venv .venv\n  source .venv/bin/activate\n  ```\n2. Install the required dependencies:\n  ```bash\n  pip install -r app/requirements.txt\n  ```\n3. Start the Flask web server:\n  ```bash\n  python app/app.py\n  ```\n\nThe app will be accessible at [http://localhost:5000](http://localhost:5000).\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE.md](LICENSE.md) file for more information.\n\nBackround image: [Inspiration Geometry](https://www.transparenttextures.com/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fikajdan%2Fllem","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fikajdan%2Fllem","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fikajdan%2Fllem/lists"}