Upload 6 files

app.py

@@ -244,8 +244,23 @@ def process_document(text: str, strategy: str, category: str = None, custom_keys
         # Apply selected strategy
         if strategy == "Fact Extraction":
             facts = active_reader.extract_facts(text)
-            result = f"**Extracted {len(facts)} facts:**\n\n" + "\n".join([f"• {fact}" for fact in facts])
-            facts_json = json.dumps(facts, indent=2)
+            
+            # Also include category-specific extractions if custom keys provided
+            category_extractions = []
+            if custom_keys_list:
+                for key, values in category_data["custom_extractions"].items():
+                    category_extractions.extend(values)
+            
+            all_facts = facts + category_extractions
+            result = f"**Extracted {len(all_facts)} facts:**\n\n" + "\n".join([f"• {fact}" for fact in all_facts])
+            
+            # Include category data in facts JSON
+            facts_data = {
+                "traditional_facts": facts,
+                "category_extractions": category_data["extracted_data"] if category_data["extracted_data"] else {},
+                "custom_extractions": category_data["custom_extractions"] if category_data["custom_extractions"] else {}
+            }
+            facts_json = json.dumps(facts_data, indent=2)
             questions_json = ""
             summary_text = ""
             
@@ -268,18 +283,53 @@ def process_document(text: str, strategy: str, category: str = None, custom_keys
             questions = active_reader.generate_questions(text)
             summary = active_reader.generate_summary(text)
             
+            # Include category extractions in complete analysis
+            category_facts = []
+            if category_data["extracted_data"]:
+                for key, values in category_data["extracted_data"].items():
+                    if values:
+                        category_facts.extend([f"{key}: {v}" for v in values[:2]])  # Top 2 per category
+            
+            custom_facts = []
+            if category_data["custom_extractions"]:
+                for key, values in category_data["custom_extractions"].items():
+                    if values:
+                        custom_facts.extend([f"{key}: {v}" for v in values[:1]])  # Top 1 per custom key
+            
+            all_facts = facts + category_facts + custom_facts
+            
             result = f"""**Domain:** {domain} | **Category:** {selected_category}
 
 **Summary:**
 {summary}
 
-**Key Facts ({len(facts)}):**
-""" + "\n".join([f"• {fact}" for fact in facts]) + f"""
+**Traditional Facts ({len(facts)}):**
+""" + "\n".join([f"• {fact}" for fact in facts])
+
+            if category_facts:
+                result += f"""
+
+**Category-Specific Extractions ({len(category_facts)}):**
+""" + "\n".join([f"• {fact}" for fact in category_facts])
+
+            if custom_facts:
+                result += f"""
+
+**Custom Key Extractions ({len(custom_facts)}):**
+""" + "\n".join([f"• {fact}" for fact in custom_facts])
+
+            result += f"""
 
 **Generated Questions ({len(questions)}):**
 """ + "\n".join([f"Q: {q}" for q in questions])
             
-            facts_json = json.dumps(facts, indent=2)
+            # Enhanced facts JSON with all extraction types
+            facts_data = {
+                "traditional_facts": facts,
+                "category_extractions": category_data["extracted_data"],
+                "custom_extractions": category_data["custom_extractions"]
+            }
+            facts_json = json.dumps(facts_data, indent=2)
             questions_json = json.dumps(questions, indent=2)
             summary_text = summary