{"id":21135250,"url":"https://github.com/cloneofsimo/adaptive-icl-labeler","last_synced_at":"2025-03-14T12:43:42.788Z","repository":{"id":218383188,"uuid":"746278152","full_name":"cloneofsimo/adaptive-icl-labeler","owner":"cloneofsimo","description":null,"archived":false,"fork":false,"pushed_at":"2024-01-21T16:07:35.000Z","size":3167,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-21T06:43:24.192Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","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/cloneofsimo.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}},"created_at":"2024-01-21T15:49:08.000Z","updated_at":"2024-01-21T15:49:15.000Z","dependencies_parsed_at":"2024-01-21T16:59:10.812Z","dependency_job_id":null,"html_url":"https://github.com/cloneofsimo/adaptive-icl-labeler","commit_stats":null,"previous_names":["cloneofsimo/adaptive-icl-labeler"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cloneofsimo%2Fadaptive-icl-labeler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cloneofsimo%2Fadaptive-icl-labeler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cloneofsimo%2Fadaptive-icl-labeler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cloneofsimo%2Fadaptive-icl-labeler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cloneofsimo","download_url":"https://codeload.github.com/cloneofsimo/adaptive-icl-labeler/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243581061,"owners_count":20314163,"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":"2024-11-20T06:46:55.731Z","updated_at":"2025-03-14T12:43:42.769Z","avatar_url":"https://github.com/cloneofsimo.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptive In-Context-Labeler\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"460\" height=\"460\" src=\"contents/main.png\"\u003e\n\u003c/p\u003e\n\n*Using In-Context Learning Capability, LMQL, and multi-armed bandit examplars optimization for fast labeling pipeline*\n\n\n\nCurrently WIP, but feel free to try out.\n\nBuilt with react, LMQL, fastap, replicate\n\n\n## Demo\n\n\u003ccenter\u003e\n    \u003cimg src=\"contents/image.png\"\u003e\n\u003c/center\u003e\n \n1. First, run frontend and backend server via\n\n```bash\ncd frontend\nnpm run start\ncd ../backend\nuvicorn main:app --reload\n```\n\n2. Run local server or use replicate backend. (\"replicate:charles-dyfis-net/llama-2-13b-hf--lmtp-8bit\")\n  * For local server, for example, run `lmql serve-model meta-llama/Llama-2-13b-chat-hf --port 8010 --cuda --load_in_4bit True`\n  * For replicate backend, don't run anything, instead, set osenv variables including [api token](https://replicate.com/account/api-tokens)\n\n    ```\n    export REPLICATE_API_TOKEN= ... # YOUR API TOKEN\n    export MODEL_ID=\"meta-llama/Llama-2-13b-chat-hf\"\n    export ENDPOINT=\"replicate:charles-dyfis-net/llama-2-13b-hf--lmtp-8bit\"\n    ```\n\n3. Use the app at `http://localhost:3000/`. You would have to have your data in backend/data.csv file, with `item_id,text,processed_value,is_processed` columns. You can use `backend/seed.py` as an example dataset creation.\n\n---\n\nTODOS:\n\n- [ ] Keep track of preference statistics per examplars, and use UCB based multi-armed bandit to select examplars\n\n- [ ] Add more flexibility for saving - loading current state, maybe like json file or something\n\n- [ ] Upload data CSV and have option to do everything in browser maybe?\n\n- [ ] Able to edit examplars after creation\n\n- [ ] Abstract out LMQL so that non-tech people can use it\n\n- [ ] Put nice documentations\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcloneofsimo%2Fadaptive-icl-labeler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcloneofsimo%2Fadaptive-icl-labeler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcloneofsimo%2Fadaptive-icl-labeler/lists"}