ChainForge/chainforge/oaievals/test_japanese_units.cforge

1 line
15 KiB
Plaintext
Raw Permalink Normal View History

TypeScript backend, HuggingFace models, JavaScript evaluators, Comment Nodes, and more (#81) * Beginning to convert Python backend to Typescript * Change all fetch() calls to fetch_from_backend switcher * wip converting query.py to query.ts * wip started utils.js conversion. Tested that OpenAI API call works * more progress on converting utils.py to Typescript * jest tests for query, utils, template.ts. Confirmed PromptPipeline works. * wip converting queryLLM in flask_app to TS * Tested queryLLM and StorageCache compressed saving/loading * wip execute() in backend.ts * Added execute() and tested w concrete func. Need to test eval() * Added craco for optional webpack config. Config'd for TypeScript with Node.js packages browserify'd * Execute JS code on iframe sandbox * Tested and working JS Evaluator execution. * wip swapping backends * Tested TypeScript backendgit status! :) woot * Added fetchEnvironAPIKeys to Flask server to fetch os.environ keys when running locally * Route Anthropic calls through Flask when running locally * Added info button to Eval nodes. Rebuilt react * Edits to info modal on Eval node * Remove/error out on Python eval nodes when not running locally. * Check browser compat and display error if not supported * Changed all example flows to use JS. Bug fix in query.ts * Refactored to LLMProvider to streamline model additions * Added HuggingFace models API * Added back Dalai call support, routing through Flask * Remove flask app calls and socketio server that are no longer used * Added Comment Nodes. Rebuilt react. * Fix PaLM temp=0 build, update package vers and rebuild react
2023-06-30 15:11:20 -04:00
{"flow": {"nodes": [{"width": 312, "height": 311, "id": "prompt-test_japanese_units", "type": "prompt", "data": {"prompt": "{prompt}", "n": 1, "llms": [{"key": "aa3c0f03-22bd-416e-af4d-4bf5c4278c99", "settings": {"system_msg": "\u30e6\u30fc\u30b6\u30fc\u306e\u8cea\u554f\u3059\u308b\u300c\u3007\u3007\u306e\u5358\u4f4d\u300d\u306b\u5bfe\u3057\u3066\u3001\u65e5\u672c\u3067\u3088\u304f\u4f7f\u308f\u308c\u308b\u5358\u4f4d\u3092\u56de\u7b54\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u5358\u4f4d\u306e\u307f\u3092\u56de\u7b54\u3057\u3066\u8aad\u307f\u65b9\u3084\u88dc\u8db3\u306f\u8981\u308a\u307e\u305b\u3093\u3002", "temperature": 1, "functions": [], "function_call": "", "top_p": 1, "stop": [], "presence_penalty": 0, "frequency_penalty": 0}, "name": "GPT3.5", "emoji": "\ud83d\ude42", "model": "gpt-3.5-turbo", "base_model": "gpt-3.5-turbo", "temp": 1, "formData": {"shortname": "GPT3.5", "model": "gpt-3.5-turbo", "system_msg": "\u30e6\u30fc\u30b6\u30fc\u306e\u8cea\u554f\u3059\u308b\u300c\u3007\u3007\u306e\u5358\u4f4d\u300d\u306b\u5bfe\u3057\u3066\u3001\u65e5\u672c\u3067\u3088\u304f\u4f7f\u308f\u308c\u308b\u5358\u4f4d\u3092\u56de\u7b54\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u5358\u4f4d\u306e\u307f\u3092\u56de\u7b54\u3057\u3066\u8aad\u307f\u65b9\u3084\u88dc\u8db3\u306f\u8981\u308a\u307e\u305b\u3093\u3002", "temperature": 1, "functions": "", "function_call": "", "top_p": 1, "stop": "", "presence_penalty": 0, "frequency_penalty": 0}}]}, "position": {"x": 448, "y": 224}, "selected": false, "positionAbsolute": {"x": 448, "y": 224}, "dragging": false}, {"width": 333, "height": 182, "id": "eval-test_japanese_units", "type": "evaluator", "data": {"code": "function evaluate(response) {\n\tlet txt = response.text;\n\tlet ideal = response.meta['Ideal'];\n\treturn ideal.includes(txt) || txt.includes(ideal);\n}", "language": "javascript"}, "position": {"x": 820, "y": 150}, "positionAbsolute": {"x": 820, "y": 150}}, {"width": 228, "height": 196, "id": "vis-test_japanese_units", "type": "vis", "data": {"input": "eval-test_japanese_units"}, "position": {"x": 1200, "y": 250}, "positionAbsolute": {"x": 1200, "y": 250}}, {"width": 302, "height": 260, "id": "inspect-test_japanese_units", "type": "inspect", "data": {"input": "prompt-test_japanese_units"}, "position": {"x": 820, "y": 400}, "positionAbsolute": {"x": 820, "y": 400}}, {"width": 423, "height": 417, "id": "table-test_japanese_units", "type": "table", "data": {"rows": [{"prompt": "\u4eba\u9593\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u4eba"}, {"prompt": "\u8eca\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u53f0"}, {"prompt": "\u6905\u5b50\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u811a"}, {"prompt": "\u30a4\u30eb\u30ab\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u982d"}, {"prompt": "\u732b\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u5339"}, {"prompt": "\u72ac\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u5339"}, {"prompt": "\u725b\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u982d"}, {"prompt": "\u9be8\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u982d"}, {"prompt": "\u9774\u4e0b\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u8db3"}, {"prompt": "\u6d99\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u7c92"}, {"prompt": "\u304a\u5bff\u53f8\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u8cab"}, {"prompt": "\u3055\u3057\u307f\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u5207\u308c"}, {"prompt": "\u4e7e\u9eba\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u675f"}, {"prompt": "\u9ce5\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u7fbd"}, {"prompt": "\u670d\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u7740"}, {"prompt": "\u9774\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u8db3"}, {"prompt": "\u96fb\u8eca\u3092\u6570\u3048\u308b\u6642\u306e\u5358\u4f4d", "ideal": "\u4e21"}, {"prompt": "\u98db\u884c\u6a5f\u3092\u6570\u3048\u308b\u6642\u306e\