Update app.py

app.py

@@ -1,7 +1,5 @@
 
-from fastapi import FastAPI
 import gradio as gr
-from src.core.cognitive_engine import CognitiveEngine
 from src.utils.hf_packager import HFSpacePackager
 from agents.planner import plan_task
 from agents.executor import execute_step
@@ -17,9 +15,38 @@ import subprocess
 from sentence_transformers import SentenceTransformer
 import numpy as np
 import faiss
+from fastapi import FastAPI
+from ctransformers import AutoModelForCausalLM
+from src.core.cognitive_engine import CognitiveEngine
+cognitive_engine = CognitiveEngine(llm_model)
+
+# Load LLM model
+llm_model = AutoModelForCausalLM.from_pretrained(
+    "TheBloke/zephyr-7B-alpha-GGUF",
+    model_file="zephyr-7b-alpha.Q4_K_M.gguf",
+    model_type="llama",
+    max_new_tokens=256,
+    temperature=0.7
+)
 
+# Initialize FastAPI and engine
 app = FastAPI()
-memory = init_memory()
+cognitive_engine = CognitiveEngine(llm_model)
+
+# 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)
 
 # Initialize components
 cognitive_engine = CognitiveEngine()
@@ -245,36 +272,8 @@ 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="/")
 
-from fastapi import FastAPI
-from ctransformers import AutoModelForCausalLM
-from src.core.cognitive_engine import CognitiveEngine
-cognitive_engine = CognitiveEngine(llm_model)
-
-# Load LLM model
-llm_model = AutoModelForCausalLM.from_pretrained(
-    "TheBloke/zephyr-7B-alpha-GGUF",
-    model_file="zephyr-7b-alpha.Q4_K_M.gguf",
-    model_type="llama",
-    max_new_tokens=256,
-    temperature=0.7
-)
-
-# Initialize FastAPI and engine
-app = FastAPI()
-cognitive_engine = CognitiveEngine(llm_model)
-
-# 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)