Completed the generate flowchart function besides the system prompt

app.py

@@ -20,14 +20,13 @@ Model:
 https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF
 
 To do
-- need to create the basic gradio looks
-- need to use llama.cpp
-- code and pipeline
+- need to create the basic gradio looks & pipeline
 
 """
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
 import gradio as gr
+from typing import Any, cast # to resolve PyLance freaking out over llama-cpp-python in the generate_flowchart function
 
 # ----- Get Model ----- #
 # Download Q4_K_M GGUF file from the repo
@@ -45,5 +44,30 @@ llm = Llama(
 
 # ----- Generation function ----- #
 def generate_flowchart(src_code: str):
-    # use llm.create_chat_completion
-    pass
+    # check if src_code is empty
+    if not src_code.strip(): return ""
+
+    system_prompt = (
+        "..."
+        "..."
+    )
+
+    # Casting else PyLance gets mad
+    response = cast(Any, llm.create_chat_completion(
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": src_code}
+        ],
+        temperature=0.1, # Keep it quite deterministic for now
+        max_tokens=1024,
+        stream=False
+    ))
+
+    content = response["choices"][0]["message"]["content"]
+
+    # Fallback to fix the .strip() on None error
+    mermaid_raw = (content or "").strip()
+
+    return mermaid_raw
+
+# ----- Gradio Interface (Basic, Not Custom) ----- #