Testing new LLMs with Streamlit MultiChat
Testing new LLMs with Streamlit MultiChat
May 25, 2025
Avoid LLM lock-in and the recurring subscription bills.
Simply use APIs.
Together with Streamlit!
ℹ️
OpenAI
They have released recently o3-mini model.
GPT-4o-mini has been my go to in terms of value per money.
But we have now o1 (mini also) and o3-mini with higher context window (200K)
pip install openai==1.61.0See the latest openAI models:
import os
from dotenv import load_dotenv
from openai import OpenAI # pip install openai>0.28
# Load environment variables from the .env file
load_dotenv()
client = OpenAI()
models = client.models.list()
for model in models:
print(model.id)Grok
DeepSeek via Ollama
Conclusions
Companions for this multichat.
Agents with Streamlit
With a very interesting article about agents: https://www.anthropic.com/engineering/built-multi-agent-research-system
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
AIssistant
Read the Web!
https://jalcocert.github.io/JAlcocerT/scrap-and-chat-with-the-web/
YT Summarizer
version: '3.8'
services:
phidata_service:
image: ghcr.io/jalcocert/phidata:yt-groq #phidata_yt_groq #ghcr.io/jalcocert/phidata:yt-groq
container_name: phidata_yt_groq
ports:
- "8501:8501"
environment:
- GROQ_API_KEY=gsk_your_api_key_here #your_api_key_here 😝
command: streamlit run cookbook/llms/groq/video_summary/app.py
#command: tail -f /dev/null # Keep the container running
# networks:
# - cloudflare_tunnel
# - nginx_default
# networks:
# cloudflare_tunnel:
# external: true
# nginx_default:
# external: true