From 24e464f51b5017937ba9357c9f0aa1f1129e7d47 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E3=81=B2=E3=81=8B=E3=82=8B?= <88682426+katojunichi893@users.noreply.github.com> Date: Sun, 14 May 2023 04:18:17 +0900 Subject: [PATCH] Update README.md --- README.md | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 32a7693..66a9514 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,6 @@ Built with [LangChain](https://github.com/hwchase17/langchain) and [GPT4All](htt demo # Environment Setup - In order to set your environment up to run the code here, first install all requirements: ```shell @@ -28,6 +27,14 @@ MODEL_N_CTX: Maximum token limit for both embeddings and LLM models Note: because of the way `langchain` loads the `LLAMMA` embeddings, you need to specify the absolute path of your embeddings model binary. This means it will not work if you use a home directory shortcut (eg. `~/` or `$HOME/`). +## Setup C++ Compiler +If you encountered an error with `pip install`, you might need to install a C++ compiler on your computer. + +### For Windows 10/11 +Install Visual Studio 2022 along with nessesary components: Universal Windows Platform development, C++ CMake tools for Windows +Download the MinGW installer from the [MinGW website](https://sourceforge.net/projects/mingw/) +Run the installer and select the "gcc" component + ## Test dataset This repo uses a [state of the union transcript](https://github.com/imartinez/privateGPT/blob/main/source_documents/state_of_the_union.txt) as an example.