ChainForge/chainforge/oaievals/asl-classifiers.cforge

1 line
6.2 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-asl-classifiers", "type": "prompt", "data": {"prompt": "{prompt}", "n": 1, "llms": [{"key": "aa3c0f03-22bd-416e-af4d-4bf5c4278c99", "settings": {"system_msg": "You are an American Sign Language (ASL) interpreter. You will be prompted with a description in quotes followed by an ASL classifier. You want to see if you can sign the given description using the given ASL classifier. Briefly go through your thought process for how the description could be or could not be represented by the classifier and write your final answer as YES or NO.", "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 an American Sign Language (ASL) interpreter. You will be prompted with a description in quotes followed by an ASL classifier. You want to see if you can sign the given description using the given ASL classifier. Briefly go through your thought process for how the description could be or could not be represented by the classifier and write your final answer as YES or NO.", "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-asl-classifiers", "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-asl-classifiers", "type": "vis", "data": {"input": "eval-asl-classifiers"}, "position": {"x": 1200, "y": 250}, "positionAbsolute": {"x": 1200, "y": 250}}, {"width": 302, "height": 260, "id": "inspect-asl-classifiers", "type": "inspect", "data": {"input": "prompt-asl-classifiers"}, "position": {"x": 820, "y": 400}, "positionAbsolute": {"x": 820, "y": 400}}, {"width": 423, "height": 417, "id": "table-asl-classifiers", "type": "table", "data": {"rows": [{"prompt": "\"a walking person\" CL:2", "ideal": "YES"}, {"prompt": "\"people standing in line\" CL:4", "ideal": "YES"}, {"prompt": "\"a plane taking off\" CL:O", "ideal": "NO"}, {"prompt": "\"a sailing boat\" CL:3", "ideal": "YES"}, {"prompt": "\"a flying mosquito\" CL:F", "ideal": "YES"}, {"prompt": "\"a cluster of houses\" CL:I", "ideal": "NO"}, {"prompt": "\"a leaking faucet\" CL:4", "ideal": "YES"}, {"prompt": "\"a thick stack of paper\" CL:C", "ideal": "YES"}, {"prompt": "\"a driver's license\" CL:V", "ideal": "NO"}, {"prompt": "\"coins\" CL:F", "ideal": "YES"}, {"prompt": "\"a long string\" CL:I", "ideal": "YES"}, {"prompt": "\"sticking out a tongue\" CL:A", "ideal": "NO"}, {"prompt": "\"hanging up a picture frame\" CL:L", "ideal": "YES"}, {"prompt": "\"a long pipe\" CL:O", "ideal": "YES"}, {"prompt": "\"smoking a cigar\" CL:R", "ideal": "YES"}, {"prompt": "\"a thin stack of paper\" CL:R", "ideal": "NO"}, {"prompt": "\"a bobbing head\" CL:S", "ideal": "YES"}, {"prompt": "\"a row of fences\" CL:G", "ideal": "NO"}, {"prompt": "\"peering through binoculars\" CL:X", "ideal": "NO"}, {"prompt": "\"skiing down a mountain\" CL:X", "ideal": "YES"}, {"prompt": "\"a moon in the sky\" CL:V", "ideal": "NO"}, {"prompt": "\"pouring a pitcher of beer\" CL:Y", "ideal": "YES"}, {"prompt": "\"spreading butter\" CL:U", "ideal": "YES"}, {"prompt": "\"a falling person\" CL:Y", "ideal": "NO"}, {"prompt": "\"a bouncing ball\" CL:4", "ideal": "NO"}, {"prompt": "\"using a power drill\" CL:L", "ideal": "YES"}, {"prompt": "\"wearing a mohawk\" CL:5", "ideal": "YES"}, {"prompt": "\"movement of wind\" CL:5", "ideal": "YES"}, {"prompt": "\"spray painting a house\" CL:B", "ideal": "NO"}, {"prompt": "\"launching a rocket\" CL