Need to use Chapple AI for my accounts
SOFTWARE
-
Embedchain GitHub Data Source Documentation Details
By
–
Yes. More details are on the documentation: https://
docs.embedchain.ai/components/dat
a-sources/github
… -
Streamlit Chat Application Demo Setup Guide
By
–
Working Application demo using Streamlit
— Shubham Saboo (@Saboo_Shubham_) 5 mai 2024
Paste the above code in vscode or pycharm and run the following command: 'streamlit run chat_github.py' pic.twitter.com/QAZDihgiPIWorking Application demo using Streamlit Paste the above code in vscode or pycharm and run the following command: 'streamlit run chat_github.py'
-
Full RAG Application Code for GitHub Repository Chat
By
–
Full RAG Application Code to Chat with GitHub Repo
-
Build Email Q&A App Using Embedchain and Streamlit
By
–
5. Ask question about your emails and get the answer • Create a text input for the user to enter their question using 'st.text_input()'
• If a question is asked, get the answer from the Embedchain app and display it using 'st.write()' -
Building RAG Web App with Streamlit and Embedchain
By
–
1. Import necessary libraries • Streamlit for building the web app
• Embedchain for the RAG functionality -
Build LLM RAG App Chat GitHub 30 Lines Python
By
–
Build a LLM app with RAG to chat with GitHub in just 30 lines of Python Code (step-by-step instructions):
-
Google Deprecates PaLM Model, Suggests Vertex and Gemini
By
–
PaLM is deprecated by Google, try changing to Vertex or Gemini model
-
Fused Classifier Kernel: Algorithmic Improvement Beyond Torch Compile
By
–
this is exactly what we're doing in the fused classifier kernel, and this is an *algorithmic* improvement on top of today's torch compile, which doesn't do this
-
cuBLASLt and cuDNN Dependencies for Optimized Performance
By
–
Yes, cuBLASLt for gemms, cuDNN for flash attention
The fp32 version will become more educational and will delete these dependencies. The "mainline" version we just want to be really fast, so we're less discriminating. cuBLASLt I think is ~ok dep, but cuDNN turned out surprisingly