-
langchain
Discontinued ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain] (by hwchase17)
-
SurveyJS
Open-Source JSON Form Builder to Create Dynamic Forms Right in Your App. With SurveyJS form UI libraries, you can build and style forms in a fully-integrated drag & drop form builder, render them in your JS app, and store form submission data in any backend, inc. PHP, ASP.NET Core, and Node.js.
-
transynthetical-engine
Applied methods of analytical augmentation to build tools using large-language models.
-
simpleaichat
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
-
guidance
Discontinued A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance] (by microsoft)
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
tree-of-thought-llm
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
-
prompting
A batteries-included, model-agnostic prompt engineering library for Node.js and TypeScript.
Langchain added support for `function_call` args yesterday: https://github.com/hwchase17/langchain/pull/6099/files
IMHO, this should make Langchain much easier and less chaotic to use.
After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary.
As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical use cases. You could coerce ChatGPT to "output results as JSON" with a system prompt but in practice results are mixed, although even with this finetuned model the docs warn that there still could be parsing errors.
OpenAI's demo for function calling is not a Hello World, to put it mildly: https://github.com/openai/openai-cookbook/blob/main/examples...
Here’s an approach to return just JavaScript:
https://github.com/williamcotton/transynthetical-engine
The key is the addition of few-shot exemplars.
Here's a demo of some system prompt engineering which resulted in better results for the older ChatGPT: https://github.com/minimaxir/simpleaichat/blob/main/examples...
Coincidentially, the new gpt-3.5-turbo-0613 model also has better system prompt guidance: for the demo above and some further prompt tweaking, it's possible to get ChatGPT to output code super reliably.
Wouldnt this be possible with a solution like Guidance where you have a pre structured JSON format ready to go and all you need is text: https://github.com/microsoft/guidance
I like to define a JOSN schema (https://json-schema.org/) and prompt GPT-4 to output JSON based on that schema.
This lets me specify general requirements(not just JSON structure) inline with the schema and in a very detailed and structured manor.
formerly cocreator of Django, now Datasette, but pretty much the top writer/hacker on HN making AI topics accessible to engineers https://hn.algolia.com/?dateRange=pastYear&page=0&prefix=tru...
I've had good luck with both:
https://github.com/drorm/gish/blob/main/tasks/coding.txt
and
https://github.com/drorm/gish/blob/main/tasks/webapp.txt
With the second one, I reliably generated half a dozen apps with one command.
Not to say that it won't fail sometimes.
Sounds like you want something like tree of thoughts: https://arxiv.org/abs/2305.10601
Coincidentally, I just published this JS library[1] over the weekend that helps prompt LLMs to return typed JSON data and validates it for you. Would love feedback on it if this is something people here are interested in. Haven’t played around with the new API yet but I think this is super exciting stuff!
[1] https://github.com/jacobsimon/prompting