outlines
instructor
outlines | instructor | |
---|---|---|
33 | 17 | |
5,799 | 5,292 | |
11.0% | - | |
9.7 | 9.8 | |
7 days ago | 3 days ago | |
Python | Python | |
Apache License 2.0 | 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.
outlines
-
Infini-Gram: Scaling unbounded n-gram language models to a trillion tokens
> [2]: https://github.com/outlines-dev/outlines?tab=readme-ov-file#...
It's interesting as speech recognition has become more popular than ever through services like Alexa, and other iot devices support for OS speech recognition
Unfortunately most implementations (especially those that are iot focused) don't have very important features for robust speech recognition.
1. Ability to enable and disable a grammar
-
Show HN: LLM-powered NPCs running on your hardware
[4] https://github.com/outlines-dev/outlines/tree/main
-
Advanced RAG with guided generation
The next step is defining how to guide generation. For this step, we'll use the Outlines library. Outlines is a library for controlling how tokens are generated. It applies logic to enforce schemas, regular expressions and/or specific output formats such as JSON.
-
Anthropic's Haiku Beats GPT-4 Turbo in Tool Use
No benchmarks, just my anecdotal experience trying to get local LLM's to respond with JSON. The method above works for my use case nearly 100% of the time. Other things I've tried (e.g. `outlines`[0]) are really slow or don't work at all. Would love to hear what others have tried!
0 - https://github.com/outlines-dev/outlines
-
Show HN: Chess-LLM, using constrained-generation to force LLMs to battle it out
As I was playing with the Outlines library (https://outlines-dev.github.io/outlines/), I discussed with my friend Maxime how funny it would be if we set up a way to pair LLMs in chess matches till one wins. The first time I tried it, it required substantial prompt engineering to get some of those LLMs to propose valid moves. Large language models can mostly stay focused and even play rather well; see https://news.ycombinator.com/item?id=37616170 for example. However small language models aren't as easy to convince.
Some of those LLMs have seen very little chess notation and so after the first few opening moves there aren't any valid tactics, let alone strategy, so they would end up either repeating the same move, or hallucinate moves that are not valid (Kxe5, but there would be a queen on e5!)
Then Outlines came along and we could force them to pick valid moves with little cost! Maxime worked super fast and got a first version of this idea as a gradio space.
I think it is pretty fun to see the (mostly terrible, but otherwise valid) chess that those LLMs play. Maybe it will even be instructive to how we can create small LLMs that can play much better than the ones on the leaderboard.
Anyway, you can check it out here:
https://huggingface.co/spaces/mlabonne/chessllm
What is interactive about it: you can pick the LLMs from available models on HuggingFace (within reason, small LLMs are preferable so that the space does not crash) or push one of your own small models to HF and have it fight with others. At the end of the game the leaderboard is updated.
Hope you find it fun!
-
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
-
Unlocking the frontend – a call for standardizing component APIs pt.2
And I think “just” Markdown doesn’t quite cut it for safe guidance. For example: directly generating content for your components. But I’m really excited about tooling like outlines appearing, with a greater focus on guided generation for structured data. Because this is often what we actually need!
-
Ask HN: What are some actual use cases of AI Agents?
It's pretty easy to force a locally running model to always output valid JSON: when it gives you probabilities for the next tokens, discard all tokens that would result in invalid JSON at that point (basically reverse parsing), and then apply the usual techniques to pick the completion only from the remaining tokens. You can even validate against a JSON schema that way, so long as it is simple enough.
There are a bunch of libraries for this already, e.g.: https://github.com/outlines-dev/outlines
-
Launch HN: AgentHub (YC W24) – A no-code automation platform
https://github.com/outlines-dev/outlines/blob/7fae436345e621... squares with my experience using LLMs for anything real
sequence = generator("Alice had 4 apples and Bob ate 2. Write an expression for Alice's apples:")
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? I’ve been using this extensively
https://jxnl.github.io/instructor/
-
Show HN: Ellipsis – 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 liu’s instructor package (https://github.com/jxnl/instructor) to structure the outputs with pydantic? It’s 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 you’ll 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?
guidance - A guidance language for controlling large language models.
langchainjs - 🦜🔗 Build context-aware reasoning applications 🦜🔗
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
json-schema-spec - The JSON Schema specification
chatgpt-localfiles - Make local files accessible to ChatGPT
Constrained-Text-Genera
PythonGPT - PythonGPT writes and indexes code to implement dynamic code execution using generative models. Younger sibling of DoctorGPT.
torch-grammar
httpx - A next generation HTTP client for Python. 🦋
langroid - Harness LLMs with Multi-Agent Programming
TypeChat - TypeChat is a library that makes it easy to build natural language interfaces using types.