Edit 26/04/2023

Previous PR closed to rename the branch & feature.

DO NOT ACCEPT

This are core changes introduced in issue #3039

Background

In a 3 layers architecture where you have :

Management of project / instances The capacity to create different project with different targets (example build a website, plan a travel, plan a wedding & do my shopping)
Management of team of agents The capacity to operate different agent willing to work on the same project(example build a website)
Agents The capacity to operate with a AI Model to perform a certain set of task/logical operations.

This PR cover the first level & would be compatible with plugins such as Dolly that manage the second level in a modular set-up.

This are core changes introduced in issue #3039 , PR conflicting with #1937 (who cover the 2 first level) but can complement with doll GPT who covers only the second level

Core model : Should we keep both model ? Should we push one one forward ? I think your Core Model may pose problem when the Agent is not interacting with a LLM. So I will definitively push my idea until proven otherwise.

The separation of projects and agents in my approach was decided to simplify the configs so that they could be transferred to other projects more easily, and to allow for the growth of the agent models.

It could be possible to combine the different models, i.e. have a project folder structure, then a single yaml to handle the projects and agents.

Hey , There is a bit more to that the difference is that :

Via #1937 you can build interaction with each agent of the Project , also agent must be LLM but it is scalable

Via #3039 you interact with a leader that does all the job of managing the other agents

It is why we provide response to similar needs but with two very different solution which are not mergeable, it can be two modes offered but it is definitively two very different way of seeing the product

Changes

Done :

Refactorisation of the core to allow to create multiple instance (project)
Each project has one AI (a lead)
Designed to get each AI able to manage 1 team of Agent (not necessarily LLM)
Renaming AI in Agent

Need :

Split ai_config.py in 3 files
Remove commented code
Create unit test
Put more comment on the code
Manage memory back-ends

Documentation

In code for the moment

Test Plan

Plan to generate Unit Test & Perform End to End test tuning scenarii

PR Quality Checklist

[ ] My pull request is atomic and focuses on a single change.
[ ] I have thoroughly tested my changes with multiple different prompts.
[x] I have considered potential risks and mitigations for my changes.
[x] I have documented my changes clearly and comprehensively.
[x] I have not snuck in any "extra" small tweaks changes => Accidentally pushed changes on file_operations.py & test_write_files.py , please discard them.

Apr 26 '23 12:04 ph-ausseil

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
docs	⬜️ Ignored (Inspect)	Visit Preview		May 2, 2023 6:24pm