guidance
instructor
guidance | instructor | |
---|---|---|
23 | 14 | |
17,357 | 5,156 | |
2.7% | - | |
9.8 | 9.8 | |
6 days ago | 4 days ago | |
Jupyter Notebook | 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.
guidance
-
Anthropic's Haiku Beats GPT-4 Turbo in Tool Use
[1]: https://github.com/guidance-ai/guidance/tree/main
-
Show HN: Prompts as (WASM) Programs
> The most obvious usage of this is forcing a model to output valid JSON
Isn't this something that Outlines [0], Guidance [1] and others [2] already solve much more elegantly?
0. https://github.com/outlines-dev/outlines
1. https://github.com/guidance-ai/guidance
2. https://github.com/sgl-project/sglang
- Show HN: Fructose, LLM calls as strongly typed functions
-
LiteLlama-460M-1T has 460M parameters trained with 1T tokens
Or combine it with something like llama.cpp's grammer or microsoft's guidance-ai[0] (which I prefer) which would allow adding some react-style prompting and external tools. As others have mentioned, instruct tuning would help too.
[0] https://github.com/guidance-ai/guidance
- Forcing AI to Follow a Specific Answer Pattern Using GBNF Grammar
-
Prompting LLMs to constrain output
have been experimenting with guidance and lmql. a bit too early to give any well formed opinions but really do like the idea of constraining llm output.
- Guidance is back π₯³
- New: LangChain templates β fastest way to build a production-ready LLM app
-
Is supervised learning dead for computer vision?
Thanks for your comment.
I did not know about "Betteridge's law of headlines", quite interesting. Thanks for sharing :)
You raise some interesting points.
1) Safety: It is true that LVMs and LLMs have unknown biases and could potentially create unsafe content. However, this is not necessarily unique to them, for example, Google had the same problem with their supervised learning model https://www.theverge.com/2018/1/12/16882408/google-racist-go.... It all depends on the original data. I believe we need systems on top of our models to ensure safety. It is also possible to restrict the output domain of our models (https://github.com/guidance-ai/guidance). Instead of allowing our LVMs to output any words, we could restrict it to only being able to answer "red, green, blue..." when giving the color of a car.
2) Cost: You are right right now LVMs are quite expensive to run. As you said are a great way to go to market faster but they cannot run on low-cost hardware for the moment. However, they could help with training those smaller models. Indeed, with see in the NLP domain that a lot of smaller models are trained on data created with GPT models. You can still distill the knowledge of your LVMs into a custom smaller model that can run on embedded devices. The advantage is that you can use your LVMs to generate data when it is scarce and use it as a fallback when your smaller device is uncertain of the answer.
3) Labelling data: I don't think labeling data is necessarily cheap. First, you have to collect the data, depending on the frequency of your events could take months of monitoring if you want to build a large-scale dataset. Lastly, not all labeling is necessarily cheap. I worked at a semiconductor company and labeled data was scarce as it required expert knowledge and could only be done by experienced employees. Indeed not all labelling can be done externally.
However, both approaches are indeed complementary and I think systems that will work the best will rely on both.
Thanks again for the thought-provoking discussion. I hope this answer some of the concerns you raised
-
Show HN: Elelem β TypeScript LLMs with tracing, retries, and type safety
I've had a bit of trouble getting function calling to work with cases that aren't just extracting some data from the input. The format is correct but it was harder to get the correct data if it wasn't a simple extraction.
Hopefully OpenAI and others will offer something like https://github.com/guidance-ai/guidance at some point to guarantee overall output structure.
Failed validations will retry, but from what I've seen JSONSchema + generated JSON examples are decently reliable in practice for gpt-3.5-turbo and extremely reliable on gpt-4.
instructor
- Instructor: Structured Outputs for LLMs
-
Anthropic's Haiku Beats GPT-4 Turbo in Tool Use
Ah yes. Have you tried out instructor [0] or Guidance [1]?
[0]: https://github.com/jxnl/instructor/
- Instructor: Structured Data Like JSON from Large Language Models
-
Show HN: Fructose, LLM calls as strongly typed functions
Good stuff. How does this compare to Instructor? Iβve been using this extensively
https://jxnl.github.io/instructor/
-
Show HN: Ellipsis β Automatic pull request reviews
it's super cool! checkout how the Instructor repo uses it to keep various parts of their docs in sync: https://github.com/jxnl/instructor/blob/main/ellipsis.yaml
-
Pushing ChatGPT's Structured Data Support to Its Limits
I've been using the instructor[1] library recently and have found the abstractions simple and extremely helpful for getting great structured outputs from LLMs with pydantic.
1 https://github.com/jxnl/instructor/tree/main
-
Efficiently using python in GPTs
Maybe try using jason liuβs instructor package (https://github.com/jxnl/instructor) to structure the outputs with pydantic? Itβs explained in his presentation from the AI Engineer summit (https://youtu.be/yj-wSRJwrrc)
-
Ask HN: Cheapest way to run local LLMs?
One of the most powerful ways to integrate LLMs with existing systems is constrained generation. Libraries such as outlines[1] and instructor[2] allow structural specification of the expected outputs as regex patterns, simple types, jsonschema or pydantic models.
These outputs often consume significantly fewer tokens than chat or text completion.
[1] https://github.com/outlines-dev/outlines
[2] https://github.com/jxnl/instructor
- OpenAI Function Calls for Humans
-
Unbounded Books: Search by ~Vibes
The best GPT-wrapper youβll see today?
...but this one hasn't raised oodles of cash.
Mike (creator) here, excited to hear what HN-folks think. Anything to add/improve?
Had fun building, extra s/out to Railway, NextJS, and https://github.com/jxnl/instructor
Check it out: https://www.unboundedbooks.com/
What are some alternatives?
lmql - A language for constraint-guided and efficient LLM programming.
langchainjs - π¦π Build context-aware reasoning applications π¦π
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
langchain - π¦π Build context-aware reasoning applications
chatgpt-localfiles - Make local files accessible to ChatGPT
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
PythonGPT - PythonGPT writes and indexes code to implement dynamic code execution using generative models. Younger sibling of DoctorGPT.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
httpx - A next generation HTTP client for Python. π¦
outlines - Structured Text Generation