Comments (3)
I understand the request and I think OAI did a great job with their function calling models. I am uncertain if support for this in LMQL makes sense, since it is a very vendor-specific API, that will be hard generalize in a model-agnostic way.
I am open to design proposal however. It would be great to somehow abstract their implementation away, and to provide a common interface, that also works e.g. for Gorilla models or other forms of more open function calling.
from lmql.
I understand the request and I think OAI did a great job with their function calling models. I am uncertain if support for this in LMQL makes sense, since it is a very vendor-specific API, that will be hard generalize in a model-agnostic way.
I am open to design proposal however. It would be great to somehow abstract their implementation away, and to provide a common interface, that also works e.g. for Gorilla models or other forms of more open function calling.
I did a bit more research on this issue. There are several major implementations of function/tool calling:
- OpenAI Parallel Function Calling
- Gorilla/OpenFunctions
- Transformers Agents (Huggingface)
- open-interpreter
- litellm
There are of course others. Every agentic framework has some version of this. All of them I have looked at so far have standardized around the OpenAI parallel function calling API, and use the openai
Python package for integration, both for calls to openai and function calling via local LLMs.
This standardization is not confined to agentic frameworks. The fact that Gorilla and litellm are depending on the openai spec for all function calling are pretty good signals.
I would have already submitted a PR but the lmql oai client is more complex than most other packages' openai integrations. The reason for that is obvious. Regardless, I have yet to have time to sit down and take it all in.
Note: As I vaguely recall from my first attempt, logit_bias
and/or logprobs
parameters did not have any effect on the output of a function/tool definition and/or call. I could be misremembering, so citation and/or example needed because that doesn't sound right. Streaming/chunks is supported.
from lmql.
Another thought: check the prompt templates of gorilla and litellm's function-calling for local models.
from lmql.
Related Issues (20)
- Lmql playground crashes with: [WinError 2] The system cannot find the specified file HOT 2
- OpenAI Chat 'choices' ("where")
- Support for Phi-2 HOT 1
- Broken Doc Links HOT 3
- [Question] Support constraining via context free grammar for dsls HOT 2
- does Azure really work ? HOT 8
- OpenAIStreamError: logprobs, best_of and echo parameters are not available on gpt-35-turbo model.
- [Question] SSLCertVerificationError when Using lmql with llamaindex HOT 1
- LMQL distribution: `NameError: name 'CLASSIFICATION' is not defined` HOT 2
- Do any of the playground examples work ? HOT 6
- Dolphin models doesn't run HOT 2
- Allow specifying model path for hf models HOT 1
- Is it possible to run LMQL with LMStudio locally ? HOT 2
- Is there any way to replicate function calling like in openai assistants api? HOT 1
- lmql.runtime.tokenizer.TokenizerNotAvailableError
- How can I get classification to work with OpenAI models? HOT 5
- Quotes aren't always parsed properly HOT 3
- Unable to use model loaded on gpu and cpu HOT 1
- Client-side (decoding) memory leak with async @lmql.query HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lmql.