Update app.py

app.py

@@ -245,13 +245,11 @@ with gr.Blocks(css="static/style.css", theme=gr.themes.Soft()) as demo:
 # Mount Gradio app to FastAPI
 gr.mount_gradio_app(app, demo, path="/")
 
-@app.get("/status")
-def status():
-    return {"status": "active", "agents": ["planner", "executor", "critic"]}
-
+from fastapi import FastAPI
 from ctransformers import AutoModelForCausalLM
 from src.core.cognitive_engine import CognitiveEngine
 
+# Load LLM model
 llm_model = AutoModelForCausalLM.from_pretrained(
     "TheBloke/zephyr-7B-alpha-GGUF",
     model_file="zephyr-7b-alpha.Q4_K_M.gguf",
@@ -260,11 +258,22 @@ llm_model = AutoModelForCausalLM.from_pretrained(
     temperature=0.7
 )
 
+# Initialize FastAPI and engine
+app = FastAPI()
 cognitive_engine = CognitiveEngine(llm_model)
 
-response = model.generate("Hello, how are you?")
-print(response)
+# Routes
+@app.get("/status")
+def status():
+    return {"status": "active", "agents": ["planner", "executor", "critic"]}
 
+@app.get("/generate")
+def generate(prompt: str):
+    return {"response": llm_model(prompt)}
+
+# Test the model at startup (optional)
 if __name__ == "__main__":
+    print(llm_model("Hello, how are you?"))
+
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=7860)