Set up generation function.

app.py

@@ -27,6 +27,23 @@ To do
 """
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
-
-
-
+import gradio as gr
+
+# ----- Get Model ----- #
+# Download Q4_K_M GGUF file from the repo
+model_path = hf_hub_download(
+    repo_id="Qwen/Qwen2.5-Coder-7B-Instruct-GGUF",
+    filename="qwen2.5-coder-7b-instruct-q4_k_m.gguf"
+)
+
+# Initialize llama.cpp with the local cached path
+llm = Llama(
+    model_path=model_path,
+    n_ctx=2048,
+    n_threads=2
+)
+
+# ----- Generation function ----- #
+def generate_flowchart(src_code: str):
+    # use llm.create_chat_completion
+    pass