ChainForge/chainforge/oaievals/2d_movement.cforge

1 line
30 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-2d_movement", "type": "prompt", "data": {"prompt": "{prompt}", "n": 1, "llms": [{"key": "aa3c0f03-22bd-416e-af4d-4bf5c4278c99", "settings": {"system_msg": "Please note: In the following EXERCISE, it is important that you only respond with a single line in the format (x, y). Imagine you are standing in a 2D coordinate grid at (0, 0) where coordinates are represented like (x, y). You are currently facing the positive y direction.", "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": "Please note: In the following EXERCISE, it is important that you only respond with a single line in the format (x, y). Imagine you are standing in a 2D coordinate grid at (0, 0) where coordinates are represented like (x, y). You are currently facing the positive y direction.", "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-2d_movement", "type": "evaluator", "data": {"code": "function evaluate(response) {\n\tlet ideal = response.meta['Ideal'];\n\treturn response.text.includes(ideal);\n}", "language": "javascript"}, "position": {"x": 820, "y": 150}, "positionAbsolute": {"x": 820, "y": 150}}, {"width": 228, "height": 196, "id": "vis-2d_movement", "type": "vis", "data": {"input": "eval-2d_movement"}, "position": {"x": 1200, "y": 250}, "positionAbsolute": {"x": 1200, "y": 250}}, {"width": 302, "height": 260, "id": "inspect-2d_movement", "type": "inspect", "data": {"input": "prompt-2d_movement"}, "position": {"x": 820, "y": 400}, "positionAbsolute": {"x": 820, "y": 400}}, {"width": 423, "height": 417, "id": "table-2d_movement", "type": "table", "data": {"rows": [{"prompt": "EXERCISE: If you take 5 steps forward, then turn 90 degrees left, then take 2 steps forward, then turn 90 degrees left, then take 1 step backward, then turn 90 degrees left, then take two steps backward, what coordinate are you at?", "ideal": "(-4, 6)"}, {"prompt": "EXERCISE: If you take 3 steps backward, then take 1 step backward, what coordinate are you at?", "ideal": "(0, -4)"}, {"prompt": "EXERCISE: If you turn 90 degrees right, then turn 90 degrees right, what coordinate are you at?", "ideal": "(0, 0)"}, {"prompt": "EXERCISE: If you take 1 step forward, then take 1 step backward, what coordinate are you at?", "ideal": "(0, 0)"}, {"prompt": "EXERCISE: If you turn 90 degrees right, then take 2 steps backward, what coordinate are you at?", "ideal": "(-2, 0)"}, {"prompt": "EXERCISE: If you turn 90 degrees left, then take 3 steps forward, what coordinate are you at?", "ideal": "(-3, 0)"}, {"prompt": "EXERCISE: If you take 5 steps forward, then take 2 steps forward, what coordinate are you at?", "ideal": "(0, 7)"}, {"prompt": "EXERCISE: If you turn 90 degrees left, then take 1 step forward, what coordinate are you at?", "ideal": "(-1, 0)"}, {"prompt": "EXERCISE: If you turn 90 degrees left, then take 3 steps forward, what coordinate are you at?", "ideal": "(-3, 0)"}, {"prompt": "EXERCISE: If you turn 90 degrees right, then turn 90 degrees left, what coordinate are you at?", "ideal": "(0, 0)"}, {"prompt": "EXERCISE: If you take 5 steps backward, then take 4 steps forward, then turn 90 degrees left, then take 1 step backward, what coordinate are you at?", "ideal": "(1, -1)"}, {"prompt": "EXERCISE: If you take 3 steps backward, then turn 90 degrees left, then turn 90 degrees right, then take 2 steps forward, what coordinate are you at?", "ideal": "(0, -1)"}, {"prompt": "EXERCISE: If you turn 90 degrees right, then turn 90 degrees left, then take 4 steps backward, then take 5 steps backward, what coordinate are you at?", "idea