feat: added code for serving README.md

main.py

@@ -0,0 +1,26 @@
+from llama_cpp.server.app import create_app, Settings
+# from fastapi.staticfiles import StaticFiles
+from fastapi.responses import HTMLResponse
+import os
+
+print("os.cpu_count()", os.cpu_count())
+app = create_app(
+    Settings(
+        n_threads=os.cpu_count(),
+        model="model/ggmlv3-model.bin",
+        embedding=False
+    )
+)
+
+# app.mount("/static", StaticFiles(directory="static"), name="static")
+
+
+@app.get("/", response_class=HTMLResponse)
+async def read_items():
+    with open("README.md", "r") as f:
+        content = f.read()
+    return content
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host=os.environ["HOST"], port=os.environ["PORT"])

start_server.sh

@@ -3,4 +3,4 @@
 # For mlock support
 ulimit -l unlimited
 
-python3 -B -m llama_cpp.server --model model/ggmlv3-model.bin --n_threads 2 --embedding False
+python3 -B main.py