Update app.py

app.py

@@ -145,6 +145,7 @@ class InformationExtractor:
 
         for attempt in range(retries):
             try:
+                # We use a context manager for the create call
                 with openai.ChatCompletion.create(
                     model="gpt-4o-mini",  # or "gpt-4" or any other available model
                     messages=[
@@ -211,7 +212,41 @@ class InformationExtractor:
             analysis = json.loads(raw_content)
             extracted_items = []
 
-            for item in analysis.get("extracted_
+            # This line must NOT be truncated or it will cause a syntax error
+            for item in analysis.get("extracted_items", []):
+                new_info = ExtractedInfo(
+                    text=item.get("text", ""),
+                    category=item.get("category", "misc"),
+                    confidence=float(item.get("confidence", 0.0)),
+                    metadata=item.get("metadata", {})
+                )
+                extracted_items.append(new_info)
+
+            return extracted_items
+
+        except json.JSONDecodeError as e:
+            logger.error(f"Error parsing extraction response: {str(e)}")
+            return []
+        except Exception as e:
+            logger.error(f"Error during information extraction: {str(e)}")
+            return []
+
+    def _update_completion_status(self) -> None:
+        """
+        Update completion status based on categories covered and confidence levels.
+        """
+        total_categories = len(self.extraction_categories)
+        covered_categories = len(self.state.categories_covered)
+        base_completion = (covered_categories / total_categories) * 100 if total_categories > 0 else 0
+
+        if self.state.extracted_items:
+            avg_confidence = sum(item.confidence for item in self.state.extracted_items) / len(self.state.extracted_items)
+            adjusted_completion = base_completion * avg_confidence
+        else:
+            adjusted_completion = 0.0
+
+        # Cap at 100%
+        self.state.completion_percentage = min(adjusted_completion, 100.0)
     def process_message(self, message: str, api_key: str) -> Dict[str, Any]:
         """
         Process a user message: 
@@ -232,7 +267,7 @@ class InformationExtractor:
         # Always return a dictionary so that the UI can parse it
         try:
             if not message.strip():
-                # Return a 5-element tuple anyway (the UI needs 5 outputs)
+                # Return placeholders if message is empty
                 return {
                     "response": "Please enter a message.",
                     "extracted_info": [],
@@ -278,7 +313,11 @@ class InformationExtractor:
                     "categories_covered": self.state.categories_covered,
                     "current_focus": self.state.current_focus
                 },
-                "analysis_text": "Successfully extracted new information." if new_info else "No new information extracted.",
+                "analysis_text": (
+                    "Successfully extracted new information."
+                    if new_info else
+                    "No new information extracted."
+                ),
                 "history_message": f"Added user message '{message}' and assistant response to history."
             }
 
@@ -474,8 +513,7 @@ def create_gradio_interface() -> gr.Blocks:
             """
             result = extractor.process_message(user_input, key)
 
-            # Update chat history
-            # We will append the user message + assistant response
+            # Update chat history: append the user message + assistant response
             history.append({"role": "user", "content": user_input})
             history.append({"role": "assistant", "content": result["response"]})
 
@@ -514,19 +552,15 @@ def create_gradio_interface() -> gr.Blocks:
 
                 # Flatten everything for a final analysis string
                 flat_items = []
-                for cat_items in content["extracted_information"].values():
-                    flat_items.extend(cat_items)
-
-                final_analysis = format_extraction_summary([
-                    {
-                        "text": i["text"],
-                        "confidence": i["confidence"],
-                        "category": cat
-                    }
-                    for cat in content["extracted_information"].keys()
-                    for i in content["extracted_information"][cat]
-                ])
-
+                for cat_key, cat_items in content["extracted_information"].items():
+                    for item_data in cat_items:
+                        flat_items.append({
+                            "category": cat_key,
+                            "confidence": item_data["confidence"],
+                            "text": item_data["text"]
+                        })
+
+                final_analysis = format_extraction_summary(flat_items)
                 return filename, content_preview, "Report generated successfully!", final_analysis
             else:
                 return None, {"error": gen_result["error"]}, "Error generating report.", "No analysis."
@@ -573,9 +607,14 @@ def create_gradio_interface() -> gr.Blocks:
         clear.click(
             fn=clear_interface,
             outputs=[
-                chatbot, progress, categories_covered,
-                current_focus, extracted_info, file_output,
-                analysis_text, msg
+                chatbot,
+                progress,
+                categories_covered,
+                current_focus,
+                extracted_info,
+                file_output,
+                analysis_text,
+                msg
             ]
         )