Create api.py

api.py

@@ -0,0 +1,21 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from llama_cpp import Llama  # Change this import as per your LLaMA library
+
+app = FastAPI()
+
+# Initialize LLaMA model
+model = Llama(model_path="path/to/llama-3.2-model.bin")  # Specify the correct path to your model
+
+class LlamaRequest(BaseModel):
+    prompt: str
+
+@app.post("/llama/")
+async def get_llama_response(request: LlamaRequest):
+    try:
+        response = model.generate(request.prompt)  # Call the LLaMA model
+        return {"response": response}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# To run the API, use 'uvicorn api:app --reload' in the terminal.