Creating Interactive GenAI applications powered by Streamlit, open source LLMs
summary
Shows a working Streamlit app that pairs the Pieces Python SDK and Pieces OS via WebSocket to call cloud and local LLMs (GPT‑3.5, GPT‑4, Llama 2, Mistral), using the model snapshots and qgp stream output endpoints to generate responses and a README generator that successfully creates markdown from uploaded project files, demonstrating 30 lines of code to spin up a chatbot, relevance‑augmented retrieval (RAG) for file context, and the option to run models locally with quantization and CPU/GPU variants.
AI-written summary · about
chapters (7)
- 0:00Introduction and welcome
- 2:06What is generative AI
- 10:57Streamlit for AI apps
- 18:41Pieces OS and SDK
- 26:06Demo chatbot with Streamlit
- 32:07Demo readme generator
- 38:12Resources and Q&A
related talks
36mGenerative AI + Python: Unlocking Efficiency, Personalization, and Insight
01h 30mBuilding Your First Multimodal Gen AI App 🚀
39mAdvanced Streamlit for Python Developers
18mRapid Prototyping in AI Project using Colab and Streamlit
34mUsing Appsmith for building GenerativeAI apps
01h 34mA Practical Starter's Guide to building LLM based projects
28mAPIs and GenAI : Your Perfect Combo with LLM-Powered Frameworks.
49mNext-Gen Documentation with AI