recall the failed call

total_app.py

@@ -29,7 +29,7 @@ with open(EDSS_INSTRUCTIONS_PATH, 'r') as f:
     EDSS_INSTRUCTIONS = f.read().strip()
 
 # === RUN INFERENCE 2 ===
-def run_inference(patient_text):
+def run_inference(patient_text, max_retries=3):
     prompt = f'''Du bist ein medizinischer Assistent, der spezialisiert darauf ist, EDSS-Scores (Expanded Disability Status Scale) sowie alle Unterkategorien aus klinischen Berichten zu extrahieren.
 ### Regeln für die Ausgabe:
 1. **Reason**: Erstelle eine prägnante Zusammenfassung (max. 400 Zeichen) der Befunde auf **DEUTSCH**, die zur Einstufung führen.
@@ -65,44 +65,49 @@ Patientenbericht:
 '''
 
     start_time = time.time()
-    try:
-        # Make API call using OpenAI client
-        response = client.chat.completions.create(
-            messages=[
-                {
-                    "role": "system",
-                    "content": "You extract EDSS scores and all subcategories. You prioritize providing values even if data is partial, by using clinical inference."
-                },
-                {
-                    "role": "user",
-                    "content": prompt
+    for attempt in range(max_retries + 1):
+        try:
+            response = client.chat.completions.create(
+                messages=[
+                    {
+                        "role": "system",
+                        "content": "You extract EDSS scores and all subcategories. You prioritize providing values even if data is partial, by using clinical inference."
+                    },
+                    {
+                        "role": "user",
+                        "content": prompt
+                    }
+                ],
+                model=MODEL_NAME,
+                max_tokens=2048,
+                temperature=0.0,
+                response_format={"type": "json_object"}
+            )
+            content = response.choices[0].message.content
+
+            if content is None or content.strip() == "":
+                raise ValueError("API returned empty or None response content")
+
+            parsed = json.loads(content)
+            inference_time = time.time() - start_time
+            return {
+                "success": True,
+                "result": parsed,
+                "inference_time_sec": inference_time
+            }
+
+        except Exception as e:
+            print(f"Attempt {attempt + 1} failed: {e}")
+            if attempt < max_retries:
+                time.sleep(2 ** attempt)  # Exponential backoff
+                continue
+            else:
+                print("All retries exhausted.")
+                return {
+                    "success": False,
+                    "error": str(e),
+                    "inference_time_sec": -1
                 }
-            ],
-            model=MODEL_NAME,
-            max_tokens=2048,
-            temperature=0.0,
-            response_format={"type": "json_object"}
-        )
-        # Extract content from response
-        content = response.choices[0].message.content
-        # Check if content is None or empty
-        if content is None or content.strip() == "":
-            raise ValueError("API returned empty or None response content")
-        # Parse the JSON response
-        parsed = json.loads(content)
-        inference_time = time.time() - start_time
-        return {
-            "success": True,
-            "result": parsed,
-            "inference_time_sec": inference_time
-        }
-    except Exception as e:
-        print(f"Inference error: {e}")
-        return {
-            "success": False,
-            "error": str(e),
-            "inference_time_sec": -1
-        }
 
 # === BUILD PATIENT TEXT ===
 def build_patient_text(row):