lmql
clownfish
lmql | clownfish | |
---|---|---|
30 | 11 | |
3,342 | 302 | |
2.9% | - | |
9.5 | 4.3 | |
7 days ago | 12 months 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.
lmql
- Show HN: Fructose, LLM calls as strongly typed functions
-
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.
-
[D] Prompt Engineering Seems Like Guesswork - How To Evaluate LLM Application Properly?
the only time i've ever felt like it was anything other than guesswork was using LMQL . not coincidentally, LMQL works with LLMs as autocomplete engines rather than q&a ones.
-
Guidance for selecting a function-calling library?
lqml
-
Show HN: Magentic – Use LLMs as simple Python functions
This is also similar in spirit to LMQL
https://github.com/eth-sri/lmql
- Show HN: LLMs can generate valid JSON 100% of the time
- LangChain Agent Simulation – Multi-Player Dungeons and Dragons
-
The Problem with LangChain
LLM calls are just function calls, so most functional composition is already afforded by any general-purpose language out there. If you need fancy stuff, use something like Python‘s functools.
Working on https://github.com/eth-sri/lmql (shameless plug, sorry), we have always found that compositional abstractions on top of LMQL are mostly there already, once you internalize prompts being functions.
- Is there a UI that can limit LLM tokens to a preset list?
-
Local LLMs: After Novelty Wanes
LMQL is another.
clownfish
-
Show HN: LLMs can generate valid JSON 100% of the time
I'm not sure how this is different than:
https://github.com/1rgs/jsonformer
or
https://github.com/newhouseb/clownfish
or
https://github.com/mkuchnik/relm
or
https://github.com/ggerganov/llama.cpp/pull/1773
or
https://github.com/Shopify/torch-grammar
Overall there are a ton of these logit based guidance systems, the reason they don't get tons of traction is the SOTA models are behind REST APIs that don't enable this fine-grained approach.
Those models perform so much better that people generally settle for just re-requesting until they get the correct format (and with GPT-4 that ends up being a fairly rare occurrence in my experience)
- OpenAI Function calling and API updates
-
Adding GPT to a web app. The real experience.
I can see some specific problems there, like malformed json (or json not matching intended schema being generated). Approaches like https://github.com/1rgs/jsonformer and https://github.com/newhouseb/clownfish could be interesting there, as well as approaches to validate outputs like https://medium.com/@markherhold/validating-json-patch-requests-44ca5981a7fc (references jsonpatch which could be interesting as well, but the approach is somewhat agnostic to how the changes actually get applied while still allowing you to enforce structure around what changes and how).
-
When you lose the ability to write, you also lose some of your ability to think
https://github.com/newhouseb/clownfish
Structural Alignment: Modifying Transformers (like GPT) to Follow a JSON Schema
- Clownfish: Constrained Decoding for LLMs Against JSON Schema
-
Jsonformer: A bulletproof way to generate structured output from LLMs
Oh nice! I built a similar system a few weeks ago: https://github.com/newhouseb/clownfish
I think the main differentiating factor here is that this is better if you have a simpler JSON schema without enums or oneOf constraints. If you do have these constraints, i.e. let's say you wanted an array of different types that represented a items on a menu { kind: pizza, toppings: [pepperoni] } or { kind: ice_cream, flavor: vanilla | strawberry } then you would need something more sophisticated like clownfish that can ask the LLM to pick specific properties.
-
Prompt injection: what’s the worst that can happen?
And on the other end, there's https://github.com/newhouseb/clownfish to force the model to produce structured output.
-
Teaching ChatGPT to Speak My Son’s Invented Language
It doesn't help with repetition, but when it comes to force structure on the output data, this approach looks interesting:
https://github.com/newhouseb/clownfish
TL;DR: it exploits the fact that the model returns probabilities for all the possible following tokens to enforce a JSON schema on the output as it is produced, backtracking as needed.
- Structural Alignment: Modifying Transformers (Like GPT) to Follow a JSON Schema
- Structural Alignment of LLMs with ControLogits
What are some alternatives?
guidance - A guidance language for controlling large language models.
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
outlines - Structured Text Generation
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
evals - Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
ChatGPT_DAN - ChatGPT DAN, Jailbreaks prompt
guardrails - Adding guardrails to large language models.
kodumisto - GitHub Issue as ChatGPT Prompt; ChatGPT's Response as a Pull Request
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
AICommand - ChatGPT integration with Unity Editor