Deploy Flan-T5 Docker with FastAPI Standard

test_hf_api.py

@@ -0,0 +1,33 @@
+import requests
+import time
+
+# The URL of your Hugging Face Space
+# Note: Hugging Face converts usernames and space names to lowercase for the URL.
+API_URL = "https://loomisgitarrist-personal-coder-ai.hf.space/ask"
+
+def test_api():
+    print(f"Testing API at: {API_URL}")
+    prompt = "Translate to German: This is a test of the deployed API."
+    
+    try:
+        print(f"Sending prompt: '{prompt}'...")
+        response = requests.get(API_URL, params={"prompt": prompt}, timeout=30)
+        
+        if response.status_code == 200:
+            data = response.json()
+            print("\n✅ Success!")
+            print(f"Response: {data}")
+            # The model returns a list with 'generated_text' usually, but our app.py returns result[0]
+            # so it should look like {'generated_text': 'Dies ist ein Test...'}
+        else:
+            print(f"\n❌ Error: Status Code {response.status_code}")
+            print(f"Details: {response.text}")
+            
+    except requests.exceptions.ConnectionError:
+        print("\n❌ Connection Error: The Space might still be building or sleeping.")
+        print("Check the build status on Hugging Face: https://huggingface.co/spaces/Loomisgitarrist/personal-coder-ai")
+    except Exception as e:
+        print(f"\n❌ An error occurred: {e}")
+
+if __name__ == "__main__":
+    test_api()

verify_model.py

@@ -0,0 +1,13 @@
+from transformers import pipeline
+import time
+
+print("Loading model...")
+start_time = time.time()
+pipe = pipeline("text2text-generation", model="google/flan-t5-base")
+end_time = time.time()
+print(f"Model loaded in {end_time - start_time:.2f} seconds.")
+
+prompt = "Translate to German: Hello, how are you?"
+print(f"Running inference on: '{prompt}'")
+result = pipe(prompt)
+print(f"Result: {result[0]['generated_text']}")