From 3e7fd6642a835f97767c7c10fcd9b18fda568113 Mon Sep 17 00:00:00 2001
From: vansangpfiev <vansangpfiev@gmail.com>
Date: Tue, 7 May 2024 08:52:33 +0700
Subject: [PATCH] feat: README.md (#11)

* feat: README.md

* feat: update repo structure

* feat: run server on mac os and linux

* feat: use make

---------

Co-authored-by: vansangpfiev <sang@jan.ai>
---
 README.md | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 88 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index d2353b4..59b1d9b 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,88 @@
-# cortex.llamacpp
\ No newline at end of file
+# cortex.llamacpp
+cortex.llamacpp is a high-efficiency C++ inference engine for edge computing.
+
+# Repo Structure
+```
+.
+├── base -> Engine interface
+├── examples -> Server example to integrate engine
+├── llama.cpp -> Upstream llama C++
+├── src -> Engine implementation
+├── third-party -> Dependencies of the cortex.llamacpp project
+```
+
+## Build from source
+
+This guide provides step-by-step instructions for building cortex.llamacpp from source on Linux, macOS, and Windows systems.
+
+## Clone the Repository
+
+First, you need to clone the cortex.llamacpp repository:
+
+```bash
+git clone --recurse https://github.com/janhq/cortex.llamacpp.git
+```
+
+If you don't have git, you can download the source code as a file archive from [cortex.llamacpp GitHub](https://github.com/janhq/cortex.llamacpp). 
+
+## Build library with server example
+- **On Windows**
+  Install choco
+  Install make
+  ```
+  choco install make -y
+  ```
+
+- **On Linux, and Windows:**
+
+  ```bash
+  make build-example-server
+  ```
+  
+- **On MacOS with Apple Silicon:**
+
+  ```bash
+  make build-example-server CMAKE_EXTRA_FLAGS="-DLLAMA_METAL_EMBED_LIBRARY=ON"
+  ```
+
+- **On MacOS with Intel processors:**
+
+  ```bash
+  make build-example-server CMAKE_EXTRA_FLAGS="-DLLAMA_METAL=OFF"
+  ```
+
+- **On Linux with CUDA:**
+
+  ```bash
+  make build-example-server CMAKE_EXTRA_FLAGS="-DLLAMA_CUDA=ON"
+  ```
+
+## Start process
+
+Finally, let's start Server.
+- **On MacOS and Linux:**
+
+  ```bash
+  mkdir engines\cortex.llamacpp\
+  cp ../../build/libengine.dylib engines/cortex.llamacpp/
+  ./server
+  ```
+
+- **On MacOS and Linux:**
+
+  ```bash
+  mkdir engines\cortex.llamacpp\
+  cp ../../build/libengine.so engines/cortex.llamacpp/
+  ./server
+  ```
+
+- **On Windows:**
+
+  ```bash
+  cd Release
+  mkdir engines\cortex.llamacpp\
+  copy ..\..\..\build\Release\engine.dll engines\cortex.llamacpp\
+  server.exe
+  ```
+# Quickstart
+// TODO
\ No newline at end of file