Upload app.py with huggingface_hub

app.py

@@ -1,5 +1,6 @@
 import os
 import sys
+import time
 
 sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), "src"))
 
@@ -32,15 +33,19 @@ def answer(question):
         context_block = "\n\n".join(
             f"[{chunk['source']}]\n{chunk['text']}" for chunk, _ in contexts
         )
-        response = client.chat_completion(
-            messages=[
-                {"role": "system", "content": "Answer the question using only the provided context. If the answer is not in the context, say you don't know. Cite the source filename in square brackets after each fact you use."},
-                {"role": "user", "content": f"Context:\n{context_block}\n\nQuestion: {question}"},
-            ],
-            model=MODEL,
-            max_tokens=400,
-        )
-        return response.choices[0].message.content.strip()
+        messages = [
+            {"role": "system", "content": "Answer the question using only the provided context. If the answer is not in the context, say you don't know. Cite the source filename in square brackets after each fact you use."},
+            {"role": "user", "content": f"Context:\n{context_block}\n\nQuestion: {question}"},
+        ]
+        last_error = None
+        for attempt in range(3):
+            try:
+                response = client.chat_completion(messages=messages, model=MODEL, max_tokens=400)
+                return response.choices[0].message.content.strip()
+            except Exception as error:
+                last_error = error
+                time.sleep(1.5 * (attempt + 1))
+        raise last_error
     except Exception:
         return "The service is busy or unavailable right now. Please try again in a moment."
 
@@ -57,6 +62,7 @@ demo = gr.Interface(
         "from them, citing the source file for each fact."
     ),
     article="Code: https://github.com/delcenjo/rag-document-assistant",
+    cache_examples=False,
     examples=[
         ["What is the refund policy?"],
         ["How do I authenticate with the API?"],