TypeChat
LLM-OpenAPI-minifier
TypeChat | LLM-OpenAPI-minifier | |
---|---|---|
12 | 2 | |
7,990 | 37 | |
1.9% | - | |
9.0 | 5.6 | |
5 days ago | 11 months ago | |
TypeScript | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
TypeChat
-
Fuck You, Show Me the Prompt
Not sure it's related to function calling. GPT4 can do function calling without using the specific function-calling API just by injecting the schema you want into the prompt with directions and asking it to return JSON. It works like >99% of the time. Same with 3.5-turbo.
The problem is these libraries convert pydantic models into json schemas and inject them into the prompt, which uses up like 80% more tokens than just describing the schema using typescript type syntax for example. See https://microsoft.github.io/TypeChat/, where they prompt using typescript type descriptions to get json data from LLMs. It's similar to what we built but with more boilerplate.
-
Semantic Kernel
Semantic Memory (renamed to Kernel Memory - https://github.com/microsoft/kernel-memory) complements SK. Guidance's features are being absorbed into SK, following the departure of that team from Microsoft. Additionally, we have TypeChat (https://github.com/microsoft/TypeChat), which aims to ensure type-safe responses from LLMs. Most features of Autogen are also being integrated into SK, along with Assistants. SK serves as the orchestration engine powering Microsoft Copilots.
- Good LLM Validation Is Just Good Validation
-
Show HN: Symphony – Make functions invokable by GPT-4
I tried TypeChat for my use case and ended up defining functions as typescript data types. This approach sounds much better, and leverages the newer OpenAI function calling, which should be more reliable I would think. Thanks for creating+sharing.
https://microsoft.github.io/TypeChat/
-
Show HN: LLMs can generate valid JSON 100% of the time
That re-prompting error on is what this new Microsoft library does, too: https://github.com/microsoft/TypeChat
Here's their prompt for that: https://github.com/microsoft/TypeChat/blob/c45460f4030938da3...
I think the approach using grammars (seen here, but also in things like https://github.com/ggerganov/llama.cpp/pull/1773 ) is a much more elegant solution.
- TypeChat replaces prompt engineering with schema engineering
-
Introducing TypeChat from Microsoft
I'm very surprised that they're not using `guidance` [0] here.
It not only would allow them to suggest that required fields be completed (avoiding the need for validation [1]) and probably save them GPU time in the end.
There must be a reason and I'm dying to know what it is! :)
[0] https://github.com/microsoft/guidance
[1] https://github.com/microsoft/TypeChat/blob/main/src/typechat...
LLM-OpenAPI-minifier
-
Ask HN: Tell us about your project that's not done yet but you want feedback on
Hey, so I got pretty far into implementing open api specs for LLMs. To the point where you can point to an open api spec, ingest it, and then it’s available for GPT to select to satisfy user requests.
I do this by minify the specs and building an index to feed it that it selects from using logit bias.
Im at pause point on it while I figure out how to actually have GPT build the calls, but I think something like you have might solve that.
https://github.com/ShelbyJenkins/LLM-OpenAPI-minifier
-
Introducing TypeChat from Microsoft
https://github.com/ShelbyJenkins/LLM-OpenAPI-minifier
I have a working solution to exposing the toggles.
I’m integrating it into the bot I have in the other repo.
Goal is you point to an openapi spec and then GPT can run choose and run functions. Basically Siri but with access to any API.
What are some alternatives?
outlines - Structured Text Generation
ts-patch - Augment the TypeScript compiler to support extended functionality
guidance - A guidance language for controlling large language models.
israpdead_react - wip react rebuild of israpisdead. v1 is live now
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
CopilotKit - Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps. [Moved to: https://github.com/CopilotKit/CopilotKit]
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
logseq - A local-first, non-linear, outliner notebook for organizing and sharing your personal knowledge base. Use it to organize your todo list, to write your journals, or to record your unique life.
paisa - Paisa – Personal Finance Manager. https://paisa.fyi demo: https://demo.paisa.fyi
ai-agents-laravel - Build AI Agents for popular LLMs quick and easy in Laravel
ContainerSSH - ContainerSSH: Launch containers on demand