Leetmonkey In Action. Darn LeetMonkey these days

app.py

@@ -128,6 +128,38 @@ def update_solution(problem, model_name):
     logger.info("Solution generated successfully")
     return formatted_code
 
+def stream_solution(problem, model_name):
+    if model_name == "Q8_0 (8-bit)":
+        model = llm
+    else:
+        model_path = download_model(gguf_models[model_name])
+        model = Llama(model_path=model_path, n_ctx=2048, n_threads=4, n_gpu_layers=0, verbose=False)
+    
+    logger.info(f"Generating solution using {model_name} model")
+    system_prompt = "You are a Python coding assistant specialized in solving LeetCode problems. Provide only the complete implementation of the given function. Ensure proper indentation and formatting. Do not include any explanations or multiple solutions."
+    full_prompt = f"""### Instruction:
+{system_prompt}
+
+Implement the following function for the LeetCode problem:
+
+{problem}
+
+### Response:
+Here's the complete Python function implementation:
+
+```python
+"""
+    
+    generated_text = ""
+    for chunk in model(full_prompt, stream=True, **generation_kwargs):
+        token = chunk["choices"]["text"]
+        generated_text += token
+        yield generated_text
+    
+    formatted_code = extract_and_format_code(generated_text)
+    logger.info("Solution generated successfully")
+    yield formatted_code
+
 with gr.Blocks() as demo:
     gr.Markdown("# LeetCode Problem Solver")
     
@@ -142,7 +174,7 @@ with gr.Blocks() as demo:
             generate_btn = gr.Button("Generate Solution")
     
     select_problem_btn.click(select_random_problem, outputs=problem_display)
-    generate_btn.click(update_solution, inputs=[problem_display, model_dropdown], outputs=solution_display)
+    generate_btn.click(stream_solution, inputs=[problem_display, model_dropdown], outputs=solution_display)
 
 if __name__ == "__main__":
     logger.info("Starting Gradio interface")