ChainForge/chainforge/oaievals/date-booking.cforge

1 line
7.8 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-date-booking", "type": "prompt", "data": {"prompt": "{prompt}", "n": 1, "llms": [{"key": "aa3c0f03-22bd-416e-af4d-4bf5c4278c99", "settings": {"system_msg": "You are BookGPT, can help to find best lesson time.\nUser tell lesson type and preferred date and time or time range.\nChoose closest time to request in future.\n\nLesson types: Social club, Complementary, Encounter.\nDate format: YYYY-MM-dd hh:mm\n\nAnswer as concisely as possible: list of lessons: lesson type and booking date and time.\nIf no available slots, just reply \"Unknown\", no other output.\n\nExample: \nSocial club: 2023-03-21 18:00\nEncounter: 2023-03-28 19:00\n\nCurrent date: 2023-03-20T18:24:02.886Z\n\nAvailable booking slots for 3 types of lesson:\n\nSocial club:\n - Mar 21 at 10:30\n - Mar 21 at 11:00\n - Mar 21 at 13:00\n - Mar 21 at 15:00\n - Mar 21 at 17:00\n\nComplementary:\n - Mar 21 at 12:00\n - Mar 23 at 16:00\n - Mar 23 at 17:00\n - Mar 25 at 17:00\n - Mar 26 at 17:00\n\nEncounter:\n - 2023-03-27 18:00\n - 2023-03-28 18:00\n - 2023-03-28 19:00\n - 2023-03-29 18:00\n - 2023-03-30 18:00\n", "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": "You are BookGPT, can help to find best lesson time.\nUser tell lesson type and preferred date and time or time range.\nChoose closest time to request in future.\n\nLesson types: Social club, Complementary, Encounter.\nDate format: YYYY-MM-dd hh:mm\n\nAnswer as concisely as possible: list of lessons: lesson type and booking date and time.\nIf no available slots, just reply \"Unknown\", no other output.\n\nExample: \nSocial club: 2023-03-21 18:00\nEncounter: 2023-03-28 19:00\n\nCurrent date: 2023-03-20T18:24:02.886Z\n\nAvailable booking slots for 3 types of lesson:\n\nSocial club:\n - Mar 21 at 10:30\n - Mar 21 at 11:00\n - Mar 21 at 13:00\n - Mar 21 at 15:00\n - Mar 21 at 17:00\n\nComplementary:\n - Mar 21 at 12:00\n - Mar 23 at 16:00\n - Mar 23 at 17:00\n - Mar 25 at 17:00\n - Mar 26 at 17:00\n\nEncounter:\n - 2023-03-27 18:00\n - 2023-03-28 18:00\n - 2023-03-28 19:00\n - 2023-03-29 18:00\n - 2023-03-30 18:00\n", "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-date-booking", "type": "evaluator", "data": {"code": "function evaluate(response) {\n\tlet ideal = response.meta['Ideal'];\n\treturn response.text.startsWith(ideal);\n}", "language": "javascript"}, "position": {"x": 820, "y": 150}, "positionAbsolute": {"x": 820, "y": 150}}, {"width": 228, "height": 196, "id": "vis-date-booking", "type": "vis", "data": {"input": "eval-date-booking"}, "position": {"x": 1200, "y": 250}, "positionAbsolute": {"x": 1200, "y": 250}}, {"width": 302, "height": 260, "id": "inspect-date-booking", "type": "inspect", "data": {"input": "prompt-date-booking"}, "position": {"x": 820, "y": 400}, "positionAbsolute": {"x": 820, "y": 400}}, {"width": 423, "height": 417, "id": "table-date-booking", "type": "table", "data": {"rows": [{"prompt": "Hello, please, book for Social club: Mar 21, at 13:00.", "ideal": "Social club: 2023-03-21 13:00"}, {"prompt": "Book for Complementary lesson on Mar 21, after 10 hours.", "ideal": "Complementary: 2023-03-21 12:00"}, {"prompt": "Book for Encounter: Mar 28, near 18 hours.", "ideal": "Encounter: 2023-03-28 18:00"}, {"prompt": "Could you book me for Encounter: Mar 28, about 17-18 hours?", "ideal": "Encounter: 2023-03-28 18:00"}, {"prompt": "Book for Complementary: Mar 21, between 10 and 13 hours.", "ideal": "Complementary: 2023-03-21 12:00"}, {"prompt": "Hello, please, book me for lessons: 1. Social club: March 21