https://github.com/kwame-mintah/python-chainlit-multi-agents-playground
🛝 \ ˈplā-ˌgrau̇nd \ an area known or suited for activity of a specified sort.
https://github.com/kwame-mintah/python-chainlit-multi-agents-playground
agents chainlit gemini langchain langgraph ollama python312
Last synced: 13 days ago
JSON representation
🛝 \ ˈplā-ˌgrau̇nd \ an area known or suited for activity of a specified sort.
- Host: GitHub
- URL: https://github.com/kwame-mintah/python-chainlit-multi-agents-playground
- Owner: kwame-mintah
- Created: 2025-10-01T16:59:44.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2026-02-14T23:18:24.000Z (4 months ago)
- Last Synced: 2026-02-15T05:30:53.589Z (4 months ago)
- Topics: agents, chainlit, gemini, langchain, langgraph, ollama, python312
- Language: Python
- Homepage:
- Size: 608 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🛝 Python Chainlit Multi-agents Playground
As the name of the repository suggests, it's just a [_playground_](https://dictionary.cambridge.org/dictionary/english/playground).
A place to better understand using [chainlit](https://github.com/Chainlit/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.
## LangGraph diagram
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. 👷 🚧
```mermaid
---
config:
flowchart:
curve: linear
---
graph TD;
__start__([
__start__
]):::first
product_owner(product_owner)
scrum_master(scrum_master)
engineer(engineer)
tools(tools)
wait_for_user(wait_for_user)
__end__([__end__
]):::last
__start__ --> product_owner;
engineer -.-> scrum_master;
engineer -.-> tools;
product_owner -.-> scrum_master;
product_owner -.-> wait_for_user;
scrum_master -. end .-> __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
```
## Prerequisites
1. [Docker for desktop](https://docs.docker.com/desktop/)
2. [Ollama](https://ollama.com/download)
3. [uv](https://docs.astral.sh/uv/#installation)
### Usage via `pip`
1. Install python packages used for the project
```pycon
pip install -r requirements.txt
```
2. Run the application
```pycon
chainlit run app.py
```
### Usage via `uv`
1. Install python packages used for the project
```pycon
uv sync
```
2. Run the application
```pycon
uv run chainlit run app.py
```
### Usage via `docker compose`
1. Run the following command within the root directory, this will build the chainlit [docker image](Dockerfile) and pull various
docker images from [docker hub](https://hub.docker.com/)
```shell
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.
```shell
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
```