Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mneedham/chatbot-arena
A Streamlit-based Chatbot Arena for Ollama LLMs
https://github.com/mneedham/chatbot-arena
llms ollama streamlit
Last synced: 12 days ago
JSON representation
A Streamlit-based Chatbot Arena for Ollama LLMs
- Host: GitHub
- URL: https://github.com/mneedham/chatbot-arena
- Owner: mneedham
- License: mit
- Created: 2024-05-18T21:22:14.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-05-19T17:15:00.000Z (8 months ago)
- Last Synced: 2024-05-20T06:41:47.471Z (8 months ago)
- Topics: llms, ollama, streamlit
- Language: Python
- Homepage:
- Size: 523 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.adoc
- License: LICENSE
Awesome Lists containing this project
README
= Ollama Chatbot Arena
This is an app that lets you do a blind comparison of https://ollama.com[Ollama models^] and vote for which ones answered the prompt better.
It's inspired by the https://lmsys.org/blog/2023-05-03-arena/[LMSYS Chatbot Arena^] that lets you do the same thing for a whole variety of hosted models.image::images/chatbot-arena.jpeg[]
== Pre-requisites
Make sure that Ollama is running and that it can load multiple models at the same time.
You can do this by running the following command:[source, bash]
----
OLLAMA_MAX_LOADED_MODELS=4 ollama serve
----== How do I run the app?
Clone the repository:
[source, bash]
----
git clone [email protected]:mneedham/chatbot-arena.git
cd chatbot-arena
----And then run it using Poetry:
[source, bash]
----
poetry run streamlit run Ollama_Chatbot_Arena.py --server.headless True
----Navigate to http://localhost:8501 and you should see the following:
image::images/home.png[]