Comments (13)
I wanted add in the @Wladastic 's comment. I like the idea of using multiple models, perhaps eventually a model could be trained specifically for the functions themselves.
from autogpt.
@ntindle can you give a link to the discord discussion here for those of use arriving from the web at large? Or maybe a summarication here? I think this is a very important topic going forward, this project should not be shackled to openAI.
from autogpt.
Absolutely. Good point. I'll try to be more diligent about that in the future too.
from autogpt.
Link to start of discussion: https://discord.com/channels/1092243196446249134/1095817829405704305/1212845507060437033
Summary:
Do you need function calls
Yes, we need function calls. No, it doesn't have to be natively supported in the model. They can look at the
OpenAIProvider
with_functions_compat_fix_kwargs
and_tool_calls_compat_extract_calls
for a very rough idea of how it could be done.
I think the "middleware" idea does make sense.
fwiw yesterday I did manage to get the
generate_agent_profile_for_task
call working with a locally-running llava-v1.5-7b-q4 model after some hacking. Gonna try to see how far I get with making a full session work today and then I'd be happy to brainstorm about how to make it easier for others to do this with their own local models via middleware or more docs or both.However one question is, is it worth investing refactoring time in the AutoGPT bot itself or is this functionality that should actually just land in the Forge part?
However one question is, is it worth investing refactoring time in the AutoGPT bot itself or is this functionality that should actually just land in the Forge part?
It makes sense to put the work into AutoGPT right now. We are planning on moving library code including
autogpt.core.resource.model_providers
to Forge, in the near future. The cleaner the module, the easier the move.
@Pwuts then put this on the roadmap as #7001
from autogpt.
I just went and ran it myself again, I can confirm the LLM doesnt even respond in the correct format.
What does work though is the one-shot prompt. I think for using local llm's we could at least use these as a first?
It just works for a few steps only though as anything above 3000 tokens is too confusing for Mistral already
from autogpt.
responded on discord :)
from autogpt.
I wanted add in the @Wladastic 's comment. I like the idea of using multiple models, perhaps eventually a model could be trained specifically for the functions themselves.
Thank you :)
I am already working on another ai project due to that.
I figured out a very good way to avoid the down sides. Multi step works amazingly well with neural chat 3.1, capybara mistral7b, gemma 2b and mixtral 8x7b. Funnily gguf models work best.
It requires a shit ton of optimization but its doable. You just have to figure out the params needed for each call
from autogpt.
@Wladastic are you working out of a branch? Or are you able to get all this working on main? And/Or do you have a link to this other project?
from autogpt.
@joshuacox
I wrote a smaller version, working on autogpt directly was too complicated and painful for that haha
from autogpt.
@joshuacox
I wrote a smaller version, working on autogpt directly was too complicated and painful for that haha
from autogpt.
@Wladastic I completely understand, sometimes you need to simplify things to isolate the parts you are working with. I encourage you to put up a branch or repo, it might be easier for some of us to contribute to as well.
from autogpt.
@Wladastic I completely understand, sometimes you need to simplify things to isolate the parts you are working with. I encourage you to put up a branch or repo, it might be easier for some of us to contribute to as well.
I could try to but my project is now merged with my own ai that works different than AutoGPT right now.
I can try to make a simplified version.
from autogpt.
This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.
from autogpt.
Related Issues (20)
- Support GitHub Fine-grained Access Token or Add Description to Document
- Apple Silicone Neural Engine: Core ML model package format support HOT 6
- Autogpt
- ./run agent start autogpt error HOT 1
- Security issue - Docker-compose persisted volumes HOT 1
- Tried to install AutoGPT since 5 days HOT 2
- agent have started ,but the website is empty,and in the gitpod env, it can not be installed and can not HOT 1
- Use Azure OpenAI with AutoGPT latest version, return 'Invalid OpenAI API key' error. Where Can I set Azure key? HOT 9
- should upgrade dependency for multidict when python3.12 HOT 2
- Remove autogpts folder HOT 1
- Cannot create new agent HOT 5
- How to solve this problem
- how to remove login accesse page
- Add support for Image, Video, and Audio input into Forge and AutoGPT
- The discord link is expired. HOT 1
- ./run setup quits at Setup initiated... HOT 9
- support for gpt-4o? HOT 2
- after login agent and create a task but dosen't work
- cant setup HOT 3
- GPT4O HOT 1
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 autogpt.