refac

.gitignore

@@ -1,2 +1,3 @@
 llama_cpp_cache
-cache
+cache
+dist

hello.py

@@ -1,6 +0,0 @@
-def main():
-    print("Hello from llama-cpp-runner!")
-
-
-if __name__ == "__main__":
-    main()

pyproject.toml

@@ -1,7 +1,14 @@
 [project]
 name = "llama-cpp-runner"
 version = "0.1.0"
-description = "Add your description here"
+description = "A runner for llama-cpp"
 readme = "README.md"
+authors = [
+    { name = "Timothy Jaeryang Baek", email = "tim@openwebui.com" }
+]
 requires-python = ">=3.11"
 dependencies = []
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

src/llama_cpp_runner/__init__.py

@@ -0,0 +1,5 @@
+from llama_cpp_runner.main import LlamaCppServer
+
+
+def hello() -> str:
+    return "Hello from llama-cpp-runner!"