PrivateGPT

PrivateGPT is a production-ready AI project that allows you to ask questions about your documents using the power of Large Language Models (LLM), even in scenarios without an Internet connection. 100% private, no data leaves your execution environment at any point.

Articles/Talks

• How to create a private ChatGPT that interacts with your local documents

Models

GPT4ALL

• GPT4ALL
• GPT4AllChat

conda create gpt4all
conda activate gpt4all
conda install python=3.10

• Build GPT4All from source

  • https://github.com/nomic-ai/gpt4all/issues/876
  • https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/python#local-build-instructions

git clone --recurse-submodules https://github.com/nomic-ai/gpt4all
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -DCMAKE_CXX_COMPILER='g++' -DCMAKE_C_COMPILER='gcc' ..
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -DCMAKE_CXX_COMPILER='g++' -DCMAKE_C_COMPILER='gcc' --build . --parallel
cd ../../gpt4all-bindings/python
pip3 install -e .

• Update langchain==0.0.190 in requirements.txt

CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ pip install -r requirements.txt

LLaMa & GPT-J

• LlamaGPTJ-chat

git clone --recurse-submodules https://github.com/kuvaus/LlamaGPTJ-chat
cd LlamaGPTJ-chat
git checkout tags/v0.2.4
mkdir build
cd build
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -DCMAKE_CXX_COMPILER='g++' -DCMAKE_C_COMPILER='gcc' ..
CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -DCMAKE_CXX_COMPILER='g++' -DCMAKE_C_COMPILER='gcc' --build . --parallel
cd build
./chat -m "privateGPT/models/ggml-gpt4all-j-v1.3-groovy.bin" -t 4