As the name of the repository suggests, it's just a playground. A place to better understand using chainlit, while employing various agents utilising large language models (LLM) via various inference providers to accomplish a given task. This project aims to be agent development kit (adk) agnostic as possible.

Here's a step-by-step interpretation of the flow of the LLM.

🚧 👷 Currently in the early stages of development, current graph implementation might change. 👷 🚧

---
config:
  flowchart:
    curve: linear
---
graph TD;
	__start__([<p>__start__</p>]):::first
	product_owner(product_owner)
	scrum_master(scrum_master)
	engineer(engineer)
	tools(tools)
	wait_for_user(wait_for_user)
	__end__([<p>__end__</p>]):::last
	__start__ --> product_owner;
	engineer -.-> scrum_master;
	engineer -.-> tools;
	product_owner -.-> scrum_master;
	product_owner -.-> wait_for_user;
	scrum_master -. &nbsp;end&nbsp; .-> __end__;
	scrum_master -.-> engineer;
	scrum_master -.-> product_owner;
	tools --> engineer;
	wait_for_user --> __end__;
	classDef default fill:#f2f0ff,line-height:1.2
	classDef first fill-opacity:0
	classDef last fill:#bfb6fc

1. Docker for desktop
2. Ollama
3. uv

1. Install python packages used for the project

pip install -r requirements.txt

2. Run the application

chainlit run app.py

1. Install python packages used for the project

uv sync

2. Run the application

uv run chainlit run app.py

1. Run the following command within the root directory, this will build the chainlit docker image and pull various docker images from docker hub

docker compose up --build -d

2. As this container also runs Ollama, please wait for the ollama-setup-1 to finish pulling your specified large language model.

 2024-01-31 23:36:50 {"status":"verifying sha256 digest"}
 2024-01-31 23:36:50 {"status":"writing manifest"}
 2024-01-31 23:36:50 {"status":"removing any unused layers"}
 2024-01-31 23:36:50 {"status":"success"}
 100 1128k    0 1128k    0    21   2546      0 --:--:--  0:07:33 --:--:--    23