Upload 8 files

cancer_index_store/Graph.py

@@ -0,0 +1,136 @@
+import json
+from collections import Counter, defaultdict
+
+def create_text_based_relationship_graph():
+    """Create a text-based relationship graph between topics"""
+    
+    JSON_PATH = r"C:\Users\muham\OneDrive\Desktop\Cancer Json\breast_cancer.json"
+    
+    with open(JSON_PATH, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    
+    # Extract all topics
+    topics = [entry.get('topic', 'Unknown') for entry in data]
+    topic_counts = Counter(topics)
+    
+    print(f"📋 Found {len(topic_counts)} unique topics")
+    print("=" * 60)
+    
+    # Show topic frequencies
+    print(f"\n📊 Topic Frequency Distribution:")
+    for topic, count in topic_counts.most_common():
+        percentage = (count / len(data)) * 100
+        print(f"  {topic}: {count} entries ({percentage:.1f}%)")
+    
+    # Create relationships based on shared medical keywords
+    medical_keywords = ['treatment', 'symptoms', 'diagnosis', 'therapy', 'cancer', 'breast', 
+                       'pain', 'surgery', 'radiation', 'chemotherapy', 'health', 'care']
+    
+    print(f"\n🔗 Topic Relationships Based on Shared Keywords:")
+    print("=" * 60)
+    
+    relationships = []
+    
+    # Find relationships between topics
+    topic_list = list(topic_counts.keys())
+    for i, topic1 in enumerate(topic_list):
+        for j, topic2 in enumerate(topic_list):
+            if i < j:  # Avoid duplicate pairs
+                words1 = set(topic1.lower().split())
+                words2 = set(topic2.lower().split())
+                common_words = words1.intersection(words2).intersection(set(medical_keywords))
+                
+                if common_words:
+                    relationships.append((topic1, topic2, len(common_words), common_words))
+    
+    # Sort by relationship strength
+    relationships.sort(key=lambda x: x[2], reverse=True)
+    
+    # Show top relationships
+    print(f"\n🏆 Top 20 Strongest Topic Relationships:")
+    for i, (topic1, topic2, strength, common_words) in enumerate(relationships[:20]):
+        print(f"\n{i+1}. {topic1} ↔ {topic2}")
+        print(f"   Strength: {strength} | Common words: {', '.join(common_words)}")
+    
+    # Create topic clusters
+    print(f"\n🎯 Topic Clusters (Groups of Related Topics):")
+    print("=" * 60)
+    
+    # Group topics by primary medical categories
+    medical_categories = {
+        'Treatment & Therapy': ['treatment', 'therapy', 'chemotherapy', 'radiation', 'surgery'],
+        'Symptoms & Diagnosis': ['symptoms', 'diagnosis', 'pain', 'detection'],
+        'Reproduction & Fertility': ['pregnancy', 'fertility', 'birth', 'reproduction'],
+        'Mental Health & Support': ['support', 'mental', 'emotional', 'health', 'care'],
+        'General Cancer': ['cancer', 'breast', 'disease', 'medical']
+    }
+    
+    topic_clusters = defaultdict(list)
+    
+    for topic in topic_list:
+        topic_lower = topic.lower()
+        assigned = False
+        
+        for category, keywords in medical_categories.items():
+            if any(keyword in topic_lower for keyword in keywords):
+                topic_clusters[category].append((topic, topic_counts[topic]))
+                assigned = True
+                break
+        
+        if not assigned:
+            topic_clusters['Other Topics'].append((topic, topic_counts[topic]))
+    
+    # Display clusters
+    for category, topics_in_cluster in topic_clusters.items():
+        if topics_in_cluster:
+            total_entries = sum(count for _, count in topics_in_cluster)
+            print(f"\n📁 {category} ({total_entries} total entries):")
+            for topic, count in sorted(topics_in_cluster, key=lambda x: x[1], reverse=True):
+                print(f"   • {topic}: {count} entries")
+
+def create_ascii_relationship_map():
+    """Create a simple ASCII art relationship map"""
+    
+    JSON_PATH = r"C:\Users\muham\OneDrive\Desktop\Cancer Json\breast_cancer.json"
+    
+    with open(JSON_PATH, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    
+    topics = [entry.get('topic', 'Unknown') for entry in data]
+    topic_counts = Counter(topics)
+    
+    print(f"\n🎨 ASCII Relationship Map")
+    print("=" * 60)
+    
+    # Get top 15 topics by frequency
+    top_topics = [topic for topic, _ in topic_counts.most_common(15)]
+    
+    print(f"\nTop 15 Topics (by frequency):")
+    print("─" * 40)
+    
+    for i, topic in enumerate(top_topics, 1):
+        count = topic_counts[topic]
+        bar = "█" * (count // 2)  # Simple visual representation
+        print(f"{i:2d}. {topic:<40} {bar} ({count})")
+    
+    # Show connections between top topics
+    print(f"\nKey Relationships Between Top Topics:")
+    print("─" * 50)
+    
+    medical_keywords = ['treatment', 'symptoms', 'diagnosis', 'therapy', 'cancer', 'breast']
+    
+    for i in range(len(top_topics)):
+        for j in range(i + 1, len(top_topics)):
+            topic1, topic2 = top_topics[i], top_topics[j]
+            words1 = set(topic1.lower().split())
+            words2 = set(topic2.lower().split())
+            common_words = words1.intersection(words2).intersection(set(medical_keywords))
+            
+            if common_words:
+                strength = len(common_words)
+                connection_char = "─" * strength + "┼" if strength > 1 else "─┼"
+                print(f"{topic1:<25} {connection_char} {topic2}")
+
+if __name__ == "__main__":
+    create_text_based_relationship_graph()
+    create_ascii_relationship_map()

cancer_index_store/Graph2.py

@@ -0,0 +1,120 @@
+import json
+from collections import defaultdict, Counter
+
+def analyze_topic_network():
+    """Analyze the network of topics without graph libraries"""
+    
+    JSON_PATH = r"C:\Users\muham\OneDrive\Desktop\Cancer Json\breast_cancer.json"
+    
+    with open(JSON_PATH, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    
+    topics = [entry.get('topic', 'Unknown') for entry in data]
+    topic_counts = Counter(topics)
+    
+    print("🌐 Topic Network Analysis")
+    print("=" * 60)
+    
+    # Build adjacency list manually
+    adjacency = defaultdict(list)
+    medical_keywords = ['treatment', 'symptoms', 'diagnosis', 'therapy', 'cancer', 'breast']
+    
+    topic_list = list(topic_counts.keys())
+    
+    for i, topic1 in enumerate(topic_list):
+        for j, topic2 in enumerate(topic_list):
+            if i != j:
+                words1 = set(topic1.lower().split())
+                words2 = set(topic2.lower().split())
+                common_words = words1.intersection(words2).intersection(set(medical_keywords))
+                
+                if common_words:
+                    adjacency[topic1].append((topic2, len(common_words)))
+    
+    # Calculate network metrics
+    print(f"\n📈 Network Statistics:")
+    print(f"   Total nodes (topics): {len(adjacency)}")
+    
+    total_connections = sum(len(connections) for connections in adjacency.values())
+    print(f"   Total connections: {total_connections}")
+    
+    # Find most connected topics (hubs)
+    connection_counts = {topic: len(connections) for topic, connections in adjacency.items()}
+    hubs = sorted(connection_counts.items(), key=lambda x: x[1], reverse=True)[:10]
+    
+    print(f"\n🏆 Most Connected Topics (Network Hubs):")
+    for topic, connections in hubs:
+        print(f"   {topic}: {connections} connections")
+    
+    # Find strongly connected pairs
+    strong_connections = []
+    for topic, connections in adjacency.items():
+        for other_topic, strength in connections:
+            if strength >= 2:  # At least 2 common keywords
+                strong_connections.append((topic, other_topic, strength))
+    
+    print(f"\n💪 Strongly Connected Topic Pairs:")
+    for topic1, topic2, strength in sorted(strong_connections, key=lambda x: x[2], reverse=True)[:15]:
+        print(f"   {topic1} ↔ {topic2} (strength: {strength})")
+    
+    # Find isolated topics (no connections)
+    isolated_topics = [topic for topic in topic_list if topic not in adjacency or not adjacency[topic]]
+    print(f"\n🏝️  Isolated Topics (no connections):")
+    for topic in isolated_topics[:10]:
+        print(f"   • {topic}")
+
+def export_relationship_data():
+    """Export relationship data for external visualization"""
+    
+    JSON_PATH = r"C:\Users\muham\OneDrive\Desktop\Cancer Json\breast_cancer.json"
+    
+    with open(JSON_PATH, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    
+    topics = [entry.get('topic', 'Unknown') for entry in data]
+    topic_counts = Counter(topics)
+    
+    # Build relationships
+    relationships = []
+    medical_keywords = ['treatment', 'symptoms', 'diagnosis', 'therapy', 'cancer', 'breast']
+    
+    topic_list = list(topic_counts.keys())
+    
+    for i, topic1 in enumerate(topic_list):
+        for j, topic2 in enumerate(topic_list):
+            if i < j:
+                words1 = set(topic1.lower().split())
+                words2 = set(topic2.lower().split())
+                common_words = words1.intersection(words2).intersection(set(medical_keywords))
+                
+                if common_words:
+                    relationships.append({
+                        'source': topic1,
+                        'target': topic2,
+                        'weight': len(common_words),
+                        'common_words': list(common_words),
+                        'source_count': topic_counts[topic1],
+                        'target_count': topic_counts[topic2]
+                    })
+    
+    # Export to JSON
+    export_data = {
+        'nodes': [{'id': topic, 'size': count} for topic, count in topic_counts.items()],
+        'links': relationships
+    }
+    
+    with open('topic_relationships.json', 'w', encoding='utf-8') as f:
+        json.dump(export_data, f, indent=2, ensure_ascii=False)
+    
+    print(f"\n💾 Relationship data exported to 'topic_relationships.json'")
+    print(f"   Nodes: {len(export_data['nodes'])}")
+    print(f"   Links: {len(export_data['links'])}")
+    print(f"\n📊 You can import this file into:")
+    print(f"   • https://observablehq.com/@d3/force-directed-graph")
+    print(f"   • https://gephi.org/")
+    print(f"   • Any D3.js force-directed graph visualization")
+
+if __name__ == "__main__":
+    analyze_topic_network()
+    print("\n" + "="*60 + "\n")
+    export_relationship_data()

cancer_index_store/InfoJson.txt

@@ -0,0 +1,27 @@
+Your Index Structure:
+
+    Your cancer_index_store folder now contains:
+
+    docstore.json - Document storage
+
+    graph_store.json - Relationship graphs
+
+    image__vector_store.json - Vector embeddings
+
+    index_store.json - Main index data
+
+
+model_provider → tells your system which API you’re using (OpenRouter).
+
+model_id → specific LLM model.
+✅ You chose LLaMA 3.1 70B Instruct (free) → best open free option for medical Q&A and reasoning.
+
+api_keys_folder → tells your script where to read your key from.
+
+similarity_top_k → retrieves the top 5 most similar answers from your LlamaIndex.
+
+combine_sources: true → combines the LLM’s reasoning + your cancer database info.
+
+strict_breast_cancer_only: true → ensures it never drifts into unrelated topics.
+
+fallback_message → message shown when both sources fail.

cancer_index_store/graph_store.json

@@ -0,0 +1 @@
+{"graph_dict": {}}

cancer_index_store/image__vector_store.json

@@ -0,0 +1 @@
+{"embedding_dict": {}, "text_id_to_ref_doc_id": {}, "metadata_dict": {}}

cancer_index_store/index_store.json

@@ -0,0 +1 @@
+{"index_store/data": {"33903888-ab2e-43e3-91f3-fc99b06e600b": {"__type__": "vector_store", "__data__": "{\"index_id\": \"33903888-ab2e-43e3-91f3-fc99b06e600b\", \"summary\": null, \"nodes_dict\": {\"b8b9f0f5-b488-4a53-9cab-a91be2cfd106\": \"b8b9f0f5-b488-4a53-9cab-a91be2cfd106\", \"c5b7b1c6-b30b-4288-a320-390c674a46bb\": \"c5b7b1c6-b30b-4288-a320-390c674a46bb\", \"9e09bbda-8bce-48c8-8326-a0b6932c5009\": \"9e09bbda-8bce-48c8-8326-a0b6932c5009\", \"b0220a56-60d7-4c15-972c-8083eca33a19\": \"b0220a56-60d7-4c15-972c-8083eca33a19\", \"b7c8dfb3-1ea9-4831-b981-328a83207268\": \"b7c8dfb3-1ea9-4831-b981-328a83207268\", \"6957fbf5-0721-4694-b178-3c98b3076323\": \"6957fbf5-0721-4694-b178-3c98b3076323\", \"1240e983-e5ec-4bea-85e9-955fb68dbe90\": \"1240e983-e5ec-4bea-85e9-955fb68dbe90\", \"d13fd7f3-817c-4027-8d09-f34327aedc72\": \"d13fd7f3-817c-4027-8d09-f34327aedc72\", \"b92fef30-0248-4f8d-a4a9-02e3441a0005\": \"b92fef30-0248-4f8d-a4a9-02e3441a0005\", \"d19beb22-6b07-4978-966b-5bd27a576a49\": \"d19beb22-6b07-4978-966b-5bd27a576a49\", \"1cdd2576-daf9-4315-a020-49c1d364781f\": \"1cdd2576-daf9-4315-a020-49c1d364781f\", \"55dd6731-ae90-47f7-bf0a-468ad99de6a1\": \"55dd6731-ae90-47f7-bf0a-468ad99de6a1\", \"8d1c976f-ab39-4057-ab5f-81bef6ee91ac\": \"8d1c976f-ab39-4057-ab5f-81bef6ee91ac\", \"c49f1213-baa8-4b2b-bb0b-1be02ba14225\": \"c49f1213-baa8-4b2b-bb0b-1be02ba14225\", \"d60b8e7e-f576-4346-aa86-f56b01c24d20\": \"d60b8e7e-f576-4346-aa86-f56b01c24d20\", \"dabf14ac-e1d1-42f9-894e-4e1ed525a21a\": \"dabf14ac-e1d1-42f9-894e-4e1ed525a21a\", \"39d450a6-ad64-4aa9-824f-586b5075671f\": \"39d450a6-ad64-4aa9-824f-586b5075671f\", \"65445201-aa07-44f3-aabe-6d27341cca67\": \"65445201-aa07-44f3-aabe-6d27341cca67\", \"abe4173b-f6c4-496e-9be1-93057f5560b2\": \"abe4173b-f6c4-496e-9be1-93057f5560b2\", \"5f90bc51-edb8-4625-8e4d-af272300bb5f\": \"5f90bc51-edb8-4625-8e4d-af272300bb5f\", \"dbdc49a3-7f44-4956-a657-31637c2b064e\": \"dbdc49a3-7f44-4956-a657-31637c2b064e\", \"ad46e24b-7b39-4c40-bb0e-191ae2ffdfb7\": \"ad46e24b-7b39-4c40-bb0e-191ae2ffdfb7\", \"a84146bb-9c89-447e-b9f2-97c10b5348ed\": \"a84146bb-9c89-447e-b9f2-97c10b5348ed\", \"e1883dab-3275-4cce-ae8f-a43abc451c73\": \"e1883dab-3275-4cce-ae8f-a43abc451c73\", \"112cfcd5-8ff0-431f-85b6-c41412a4b486\": \"112cfcd5-8ff0-431f-85b6-c41412a4b486\", \"362bf81f-9f19-4b8c-b3da-f5ed57b965fc\": \"362bf81f-9f19-4b8c-b3da-f5ed57b965fc\", \"d7accefe-50a1-4907-80a5-dc82f9b36e99\": \"d7accefe-50a1-4907-80a5-dc82f9b36e99\", \"28dc17e0-bdfc-4bf3-9fe1-9bbd8f436abc\": \"28dc17e0-bdfc-4bf3-9fe1-9bbd8f436abc\", \"fde22a92-bd70-462d-b025-e71721050fd0\": \"fde22a92-bd70-462d-b025-e71721050fd0\", \"357cf698-82aa-408e-8a19-5ab17576e2ee\": \"357cf698-82aa-408e-8a19-5ab17576e2ee\", \"f26be9f7-37d2-457a-8138-7244d65d2922\": \"f26be9f7-37d2-457a-8138-7244d65d2922\", \"4d778414-8b8f-4642-94a6-da7958171ddd\": \"4d778414-8b8f-4642-94a6-da7958171ddd\", \"e2524e7a-1fd0-4c06-8ed6-4ab476566399\": \"e2524e7a-1fd0-4c06-8ed6-4ab476566399\", \"defd211d-8c10-48ae-a0f8-db40803effba\": \"defd211d-8c10-48ae-a0f8-db40803effba\", \"dc9c9a13-7660-4b71-b3ef-ed1c8c0104c5\": \"dc9c9a13-7660-4b71-b3ef-ed1c8c0104c5\", \"29d8fc45-71e1-47c9-991e-70dd5dfb0d4b\": \"29d8fc45-71e1-47c9-991e-70dd5dfb0d4b\", \"2b8b103a-ceea-4438-be1f-f6e892f20d70\": \"2b8b103a-ceea-4438-be1f-f6e892f20d70\", \"f56d3634-c3cd-4742-bf9e-7eb4792a5d9f\": \"f56d3634-c3cd-4742-bf9e-7eb4792a5d9f\", \"fac4e5ac-0e16-45b0-a8f4-71f8f25725e9\": \"fac4e5ac-0e16-45b0-a8f4-71f8f25725e9\", \"ef3dba86-2297-4a50-b283-6b68d55e3b46\": \"ef3dba86-2297-4a50-b283-6b68d55e3b46\", \"7fe36737-be63-412c-a43b-b5629bf6d456\": \"7fe36737-be63-412c-a43b-b5629bf6d456\", \"8b2499c5-2a92-4562-84a0-deeedaf7a2c5\": \"8b2499c5-2a92-4562-84a0-deeedaf7a2c5\", \"d3696a31-c63f-400d-9f88-b7f26dfa23b6\": \"d3696a31-c63f-400d-9f88-b7f26dfa23b6\", \"786045c9-8c7f-40d7-9ff5-8f3b04a44cbc\": \"786045c9-8c7f-40d7-9ff5-8f3b04a44cbc\", \"1fdac9b3-9cbc-4fea-8e32-06966190fa22\": \"1fdac9b3-9cbc-4fea-8e32-06966190fa22\", \"165ede0d-add7-4518-9956-5d06b7acbe35\": \"165ede0d-add7-4518-9956-5d06b7acbe35\", \"31ddbce1-557a-4d53-a881-65424f9842ea\": \"31ddbce1-557a-4d53-a881-65424f9842ea\", \"8b4d90e7-f490-469d-8767-18f9a31ece40\": \"8b4d90e7-f490-469d-8767-18f9a31ece40\", \"ce7b7763-591d-481a-8826-143e237f2507\": \"ce7b7763-591d-481a-8826-143e237f2507\", \"5effadbf-6281-425e-82a1-a69be302d8de\": \"5effadbf-6281-425e-82a1-a69be302d8de\", \"ebc2af34-1dee-4f47-89d5-5be2d17a65dd\": \"ebc2af34-1dee-4f47-89d5-5be2d17a65dd\", \"9f097c45-c570-41a8-9584-287a82ba6e84\": \"9f097c45-c570-41a8-9584-287a82ba6e84\", \"407a0124-394a-4f54-b6b0-797517ce5b10\": \"407a0124-394a-4f54-b6b0-797517ce5b10\", \"5aa34644-0ce2-4b7f-977b-f0b797213c03\": \"5aa34644-0ce2-4b7f-977b-f0b797213c03\", \"e5b8caa3-da59-4a8a-a81f-868fd8368463\": \"e5b8caa3-da59-4a8a-a81f-868fd8368463\", \"b2658c2d-3e49-4359-a77b-cb22515f97b2\": \"b2658c2d-3e49-4359-a77b-cb22515f97b2\", \"1e8a9321-dbf8-4d94-95d7-55e972d765d4\": \"1e8a9321-dbf8-4d94-95d7-55e972d765d4\", \"93c03172-26b3-497b-9252-957949f189c1\": \"93c03172-26b3-497b-9252-957949f189c1\", \"c1f3e7b3-2220-4569-a83d-0733d44069f0\": \"c1f3e7b3-2220-4569-a83d-0733d44069f0\", \"ff19228f-45f7-43f7-86e6-bddabf1a9051\": \"ff19228f-45f7-43f7-86e6-bddabf1a9051\", \"84102568-3b85-45a6-9977-a47caddcac29\": \"84102568-3b85-45a6-9977-a47caddcac29\", \"33cbf1a4-ee18-4faa-ba6c-142559f7ea57\": \"33cbf1a4-ee18-4faa-ba6c-142559f7ea57\", \"6c138a4b-fd28-4fe0-a2de-ffafc229de97\": \"6c138a4b-fd28-4fe0-a2de-ffafc229de97\", \"32b305ea-b9cc-420d-9dc1-2d8bd2211375\": \"32b305ea-b9cc-420d-9dc1-2d8bd2211375\", \"10dc98a3-b08d-4d98-8522-52d86df0606a\": \"10dc98a3-b08d-4d98-8522-52d86df0606a\", \"91469a46-c03a-4871-bdc9-573cde2488a4\": \"91469a46-c03a-4871-bdc9-573cde2488a4\", \"efb1df4f-9157-4e89-9b41-5f270ec4cdb1\": \"efb1df4f-9157-4e89-9b41-5f270ec4cdb1\", \"f1c32b14-f151-413d-b4f5-299dd4954135\": \"f1c32b14-f151-413d-b4f5-299dd4954135\", \"35ddc0a0-5ce2-477d-a538-1dbd2bb2b0c5\": \"35ddc0a0-5ce2-477d-a538-1dbd2bb2b0c5\", \"7e6711c3-75ac-43ab-a3c8-d8d08bb9b13f\": \"7e6711c3-75ac-43ab-a3c8-d8d08bb9b13f\", \"ea4f8a59-ac67-4750-9602-71cbbaa19056\": \"ea4f8a59-ac67-4750-9602-71cbbaa19056\", \"2622603e-fa4d-4679-8f33-d6b288bf41e3\": \"2622603e-fa4d-4679-8f33-d6b288bf41e3\", \"e050f617-3c6a-41f3-b21e-6986da55d548\": \"e050f617-3c6a-41f3-b21e-6986da55d548\", \"5107be68-5fed-4084-9e62-a75682c6d074\": \"5107be68-5fed-4084-9e62-a75682c6d074\", \"69432d39-c516-45fd-817c-a11ef2c94dc3\": \"69432d39-c516-45fd-817c-a11ef2c94dc3\", \"50c497e6-8aea-431b-a4e6-7fa8c50041ce\": \"50c497e6-8aea-431b-a4e6-7fa8c50041ce\", \"7007c88f-c806-46d0-9aad-6de56ec916cc\": \"7007c88f-c806-46d0-9aad-6de56ec916cc\", \"713bdc11-772b-4bb7-9f5a-66d776595449\": \"713bdc11-772b-4bb7-9f5a-66d776595449\", \"762d6468-6d66-4ad8-a7ea-b20974bb25db\": \"762d6468-6d66-4ad8-a7ea-b20974bb25db\", \"dba5c8a9-5e09-4c79-9420-50075ca67271\": \"dba5c8a9-5e09-4c79-9420-50075ca67271\", \"ebf870d7-ace6-414b-b158-b0f76b13fcd4\": \"ebf870d7-ace6-414b-b158-b0f76b13fcd4\", \"5853d545-d480-4177-8b6e-32ab1300a328\": \"5853d545-d480-4177-8b6e-32ab1300a328\", \"e2788a4b-7e0d-4982-ae16-4d3df28c8c7d\": \"e2788a4b-7e0d-4982-ae16-4d3df28c8c7d\", \"7cba1342-d7e8-4fcc-8f6e-77e61880336f\": \"7cba1342-d7e8-4fcc-8f6e-77e61880336f\", \"8ae953b5-83f3-43a7-8840-974258ae8161\": \"8ae953b5-83f3-43a7-8840-974258ae8161\", \"e9ea54f4-c634-481f-8c86-d3a5a782ac76\": \"e9ea54f4-c634-481f-8c86-d3a5a782ac76\", \"ee5a0658-4920-488d-b3a2-07d519c97fa9\": \"ee5a0658-4920-488d-b3a2-07d519c97fa9\", \"86f3a0e3-7df5-4708-8cfa-61ee27352573\": \"86f3a0e3-7df5-4708-8cfa-61ee27352573\", \"e397feae-23fe-410d-9e1b-d5cbcf89d09f\": \"e397feae-23fe-410d-9e1b-d5cbcf89d09f\", \"cdc155f0-3450-4aad-bcde-3c5ad8e49a8f\": \"cdc155f0-3450-4aad-bcde-3c5ad8e49a8f\", \"9b748cb2-42c6-4ce3-aafe-a0f59996a3d3\": \"9b748cb2-42c6-4ce3-aafe-a0f59996a3d3\", \"d59d3cbd-00cb-4eb8-a36e-f850c1680172\": \"d59d3cbd-00cb-4eb8-a36e-f850c1680172\", \"e39351ad-940f-4117-af21-81fcf35f88a2\": \"e39351ad-940f-4117-af21-81fcf35f88a2\", \"59fcfa95-0acf-444d-8204-80a70a6c8272\": \"59fcfa95-0acf-444d-8204-80a70a6c8272\", \"a7d61146-c666-4df5-968c-50e5d54d72b3\": \"a7d61146-c666-4df5-968c-50e5d54d72b3\", \"9cc6c3e0-811a-405e-9388-acd9d0a3eeac\": \"9cc6c3e0-811a-405e-9388-acd9d0a3eeac\", \"98fdf258-781c-4430-9fae-f18e5c24197f\": \"98fdf258-781c-4430-9fae-f18e5c24197f\", \"24ce161d-c74a-4699-b27b-40bb6a433068\": \"24ce161d-c74a-4699-b27b-40bb6a433068\", \"de359e98-3f30-4602-8d63-8ffa0be38dfe\": \"de359e98-3f30-4602-8d63-8ffa0be38dfe\", \"75682b5a-856f-4006-aa3f-7e17d27f5d9c\": \"75682b5a-856f-4006-aa3f-7e17d27f5d9c\", \"213fc638-608b-4bbf-aa1d-01786c4b3b52\": \"213fc638-608b-4bbf-aa1d-01786c4b3b52\", \"55a09ad1-910f-473b-b15d-318eccda6cb1\": \"55a09ad1-910f-473b-b15d-318eccda6cb1\", \"2c84b830-a73e-4e0b-acce-598eb63921b2\": \"2c84b830-a73e-4e0b-acce-598eb63921b2\", \"5d01b5d0-d101-440f-8623-67676ffc0f84\": \"5d01b5d0-d101-440f-8623-67676ffc0f84\", \"23458aa0-ddc1-4f60-b93b-a0865cf03684\": \"23458aa0-ddc1-4f60-b93b-a0865cf03684\", \"57dfcef3-fa7b-4e47-b7df-5f28b40f5c40\": \"57dfcef3-fa7b-4e47-b7df-5f28b40f5c40\", \"ee252e99-8850-4604-8a89-7ba767f6a109\": \"ee252e99-8850-4604-8a89-7ba767f6a109\", \"206101f5-1905-4c9b-b275-8cb91afdde50\": \"206101f5-1905-4c9b-b275-8cb91afdde50\", \"ed68fd25-1f15-406b-8786-1ac1eac4d403\": \"ed68fd25-1f15-406b-8786-1ac1eac4d403\", \"457b9918-98fd-4367-849b-2be5bae03ed1\": \"457b9918-98fd-4367-849b-2be5bae03ed1\", \"62429cc1-bad2-4d69-b167-a8ae2a10a9fa\": \"62429cc1-bad2-4d69-b167-a8ae2a10a9fa\", \"10cfb5cc-1663-4c0e-8f62-a9a23d25af03\": \"10cfb5cc-1663-4c0e-8f62-a9a23d25af03\", \"f22ffc7b-3909-42ee-8b34-2f5e234b5df2\": \"f22ffc7b-3909-42ee-8b34-2f5e234b5df2\", \"302c8fe5-c158-4bff-a6e7-772fbcfc7bf7\": \"302c8fe5-c158-4bff-a6e7-772fbcfc7bf7\", \"77b9dcb7-668f-4fb7-aa9a-3d786921b42d\": \"77b9dcb7-668f-4fb7-aa9a-3d786921b42d\", \"1160fad6-3579-4d4a-8c7f-c112bb38cd55\": \"1160fad6-3579-4d4a-8c7f-c112bb38cd55\", \"5e4fc3b8-cfa9-4f59-8ddb-055fc6c0ba7b\": \"5e4fc3b8-cfa9-4f59-8ddb-055fc6c0ba7b\", \"1438257c-5e7b-44ab-a3ea-ae3f269a2a61\": \"1438257c-5e7b-44ab-a3ea-ae3f269a2a61\", \"393f370d-60ea-40dd-93cd-94b1d2492729\": \"393f370d-60ea-40dd-93cd-94b1d2492729\", \"480e722d-f208-4766-bdd1-99e557cc0a3b\": \"480e722d-f208-4766-bdd1-99e557cc0a3b\", \"8d4f89d5-e8fa-410d-9270-c9d68aff0865\": \"8d4f89d5-e8fa-410d-9270-c9d68aff0865\", \"13d00b95-7ca8-4fcb-93db-c8065e37786e\": \"13d00b95-7ca8-4fcb-93db-c8065e37786e\", \"54cc76ad-9ec1-470f-8d8e-c6456a4b6e97\": \"54cc76ad-9ec1-470f-8d8e-c6456a4b6e97\", \"be6a5af2-4ba6-4f2d-a55c-3c266631e7c1\": \"be6a5af2-4ba6-4f2d-a55c-3c266631e7c1\", \"7097010e-fea9-4535-bf4f-c80a61167a9f\": \"7097010e-fea9-4535-bf4f-c80a61167a9f\", \"b5fd5f72-ae19-4826-91c3-a3ab192e5c04\": \"b5fd5f72-ae19-4826-91c3-a3ab192e5c04\", \"4549f151-38cb-4a2e-8f30-75ba628a1ed8\": \"4549f151-38cb-4a2e-8f30-75ba628a1ed8\", \"2e35b066-98e0-40db-8340-86408f8a68b5\": \"2e35b066-98e0-40db-8340-86408f8a68b5\", \"4981976b-815e-45a3-89f7-f1b5ef9cc21f\": \"4981976b-815e-45a3-89f7-f1b5ef9cc21f\", \"08457245-9366-4e01-8cd0-50e977573064\": \"08457245-9366-4e01-8cd0-50e977573064\", \"376f9d67-c327-430f-9e02-f5180d54371c\": \"376f9d67-c327-430f-9e02-f5180d54371c\", \"829efb4b-5cb2-4e1e-bcae-c6c8514cddfc\": \"829efb4b-5cb2-4e1e-bcae-c6c8514cddfc\", \"3076175c-4c80-48af-8965-9fc5caeece4f\": \"3076175c-4c80-48af-8965-9fc5caeece4f\", \"ce35235c-0984-4506-b64f-54c3589bd46d\": \"ce35235c-0984-4506-b64f-54c3589bd46d\", \"3aaeba42-eb86-43de-bec2-f6e4b8207a6a\": \"3aaeba42-eb86-43de-bec2-f6e4b8207a6a\", \"9a504337-1b8f-48b7-bff4-b7ba9332f77a\": \"9a504337-1b8f-48b7-bff4-b7ba9332f77a\", \"f7881a09-4c40-4686-966e-e77e33beb033\": \"f7881a09-4c40-4686-966e-e77e33beb033\", \"823a325f-329c-49df-861f-9a00a13c7986\": \"823a325f-329c-49df-861f-9a00a13c7986\", \"d1142e9a-1c76-45ff-8678-9a7c6774a58b\": \"d1142e9a-1c76-45ff-8678-9a7c6774a58b\", \"43bd23db-bc42-42e9-9167-1746451f15ec\": \"43bd23db-bc42-42e9-9167-1746451f15ec\", \"b5bafc40-848a-43cc-9faf-c378b3b1f66d\": \"b5bafc40-848a-43cc-9faf-c378b3b1f66d\", \"4f76a3b8-1f5d-4a19-9e48-b2f7adc8aa0b\": \"4f76a3b8-1f5d-4a19-9e48-b2f7adc8aa0b\", \"2f026d4a-a769-4f4f-b4cc-ced7cd672bc6\": \"2f026d4a-a769-4f4f-b4cc-ced7cd672bc6\", \"a198cfcb-0117-4a43-bf47-9a23ece7e287\": \"a198cfcb-0117-4a43-bf47-9a23ece7e287\", \"5e1bb198-29c7-4a20-8d02-a91e0189e2b3\": \"5e1bb198-29c7-4a20-8d02-a91e0189e2b3\", \"ecb6799c-d6d0-4bfa-be0f-499e0095dd9a\": \"ecb6799c-d6d0-4bfa-be0f-499e0095dd9a\", \"f60a1af5-ca6a-48c6-9dce-a2f13d3fb78a\": \"f60a1af5-ca6a-48c6-9dce-a2f13d3fb78a\", \"57db1ba6-726e-4919-abdd-8d5bead2a747\": \"57db1ba6-726e-4919-abdd-8d5bead2a747\", \"c6ba3c13-13e5-4bb9-bbeb-9f002e081177\": \"c6ba3c13-13e5-4bb9-bbeb-9f002e081177\", \"1ab7681e-cb01-4272-85ca-284b0106be26\": \"1ab7681e-cb01-4272-85ca-284b0106be26\", \"4e80e2b3-4c06-461d-80f0-3948035dcaf7\": \"4e80e2b3-4c06-461d-80f0-3948035dcaf7\", \"939f9d13-013a-4e66-af67-1cfe69cb82ad\": \"939f9d13-013a-4e66-af67-1cfe69cb82ad\", \"e853ad8f-a853-409e-a460-a2ec86ea42e9\": \"e853ad8f-a853-409e-a460-a2ec86ea42e9\", \"bee1c520-0f06-4f26-a57e-ffeefbfa51f3\": \"bee1c520-0f06-4f26-a57e-ffeefbfa51f3\", \"926c2051-8f4b-4be2-bcf8-310145e186f5\": \"926c2051-8f4b-4be2-bcf8-310145e186f5\", \"98c58cb2-f8a5-4646-ad97-416be00eb965\": \"98c58cb2-f8a5-4646-ad97-416be00eb965\", \"b13c9b90-7854-4325-afcc-e43edaf1e15c\": \"b13c9b90-7854-4325-afcc-e43edaf1e15c\", \"35176457-cdc5-4e0d-843c-8ac2236b1041\": \"35176457-cdc5-4e0d-843c-8ac2236b1041\", \"573a0828-d0bf-4c74-90e3-33c7301aecbf\": \"573a0828-d0bf-4c74-90e3-33c7301aecbf\", \"e6ed0315-c56c-4d72-b21c-9fc430d80164\": \"e6ed0315-c56c-4d72-b21c-9fc430d80164\", \"742bcfe1-d866-4877-bf58-b25c32a71478\": \"742bcfe1-d866-4877-bf58-b25c32a71478\", \"9b3f5d36-6161-48de-b38e-f113b6738c46\": \"9b3f5d36-6161-48de-b38e-f113b6738c46\", \"c5bf45da-caf3-4074-8e9c-544286522820\": \"c5bf45da-caf3-4074-8e9c-544286522820\", \"e5ed6e5a-e8e9-4606-a09e-3947e4cd2350\": \"e5ed6e5a-e8e9-4606-a09e-3947e4cd2350\", \"9b0881c7-f8a2-4913-a8b5-b61da6b65f70\": \"9b0881c7-f8a2-4913-a8b5-b61da6b65f70\", \"8e169903-ba5b-4837-8760-6313df57bf79\": \"8e169903-ba5b-4837-8760-6313df57bf79\", \"3de31585-e7c2-4d60-a312-f57c540492b2\": \"3de31585-e7c2-4d60-a312-f57c540492b2\", \"e5a10d22-83fa-4968-8d23-e84a5eab482e\": \"e5a10d22-83fa-4968-8d23-e84a5eab482e\", \"803d55be-6541-42f9-9b1c-74eeebc820d7\": \"803d55be-6541-42f9-9b1c-74eeebc820d7\", \"5bac77af-cf08-4616-8246-f3d35f191a4c\": \"5bac77af-cf08-4616-8246-f3d35f191a4c\", \"37da908c-dabb-4bc0-9f14-368394642c0c\": \"37da908c-dabb-4bc0-9f14-368394642c0c\", \"7d6e84b0-084d-4ca7-9000-97a8f4efa5a3\": \"7d6e84b0-084d-4ca7-9000-97a8f4efa5a3\", \"96d9193d-782a-4934-b092-a2a852fd4ed5\": \"96d9193d-782a-4934-b092-a2a852fd4ed5\", \"03e8fdd8-ecd1-41f5-94d8-905c5890e0f4\": \"03e8fdd8-ecd1-41f5-94d8-905c5890e0f4\", \"f21dfbdd-3698-4bef-9b43-32c6987775c6\": \"f21dfbdd-3698-4bef-9b43-32c6987775c6\", \"cae22590-2541-478e-980f-77cae820409b\": \"cae22590-2541-478e-980f-77cae820409b\", \"cae8f1e7-bde3-4771-a311-3a393f0a6f71\": \"cae8f1e7-bde3-4771-a311-3a393f0a6f71\", \"f80e5f16-b31b-48a0-8167-86bef442bd0a\": \"f80e5f16-b31b-48a0-8167-86bef442bd0a\", \"1e5a3d85-455b-4728-99d7-2c4525e7af66\": \"1e5a3d85-455b-4728-99d7-2c4525e7af66\", \"73c15250-fe0e-4b6b-a986-3785f8c24ca2\": \"73c15250-fe0e-4b6b-a986-3785f8c24ca2\", \"d1d8591f-7c78-4494-8cc9-880f300b9110\": \"d1d8591f-7c78-4494-8cc9-880f300b9110\", \"bb7ceba2-4d75-49fe-a17d-2789cc2ab88d\": \"bb7ceba2-4d75-49fe-a17d-2789cc2ab88d\", \"c3a4ad5a-496f-414e-af12-f7c08a0a6e02\": \"c3a4ad5a-496f-414e-af12-f7c08a0a6e02\", \"d7a54f1f-1248-4ec1-82fe-94c849505af0\": \"d7a54f1f-1248-4ec1-82fe-94c849505af0\", \"64324da8-e719-492e-8e92-0b45bfa1feda\": \"64324da8-e719-492e-8e92-0b45bfa1feda\", \"80c0559c-1fc5-4d52-ab1a-00f2496917a1\": \"80c0559c-1fc5-4d52-ab1a-00f2496917a1\", \"6cb9fb53-3d54-4c40-bba7-7c738288b97a\": \"6cb9fb53-3d54-4c40-bba7-7c738288b97a\", \"e31fa63f-3297-43e7-b291-dff79e49366d\": \"e31fa63f-3297-43e7-b291-dff79e49366d\", \"b1255708-c521-4fff-b6c1-0f77b92cd29f\": \"b1255708-c521-4fff-b6c1-0f77b92cd29f\", \"f37eaabe-6606-4db5-aef9-24bbcd4ae24f\": \"f37eaabe-6606-4db5-aef9-24bbcd4ae24f\", \"bfd2aa4b-0f64-4d11-a541-b4a0f271a3c3\": \"bfd2aa4b-0f64-4d11-a541-b4a0f271a3c3\", \"2119d3e7-56fa-4410-963a-98120dd158a0\": \"2119d3e7-56fa-4410-963a-98120dd158a0\", \"1420a105-60f8-49af-a8b6-f1437ee1f2f7\": \"1420a105-60f8-49af-a8b6-f1437ee1f2f7\", \"2be381b1-42c9-482d-95e2-41a22a09dbbd\": \"2be381b1-42c9-482d-95e2-41a22a09dbbd\", \"39307a50-552b-47e9-9d58-571f78c7451f\": \"39307a50-552b-47e9-9d58-571f78c7451f\", \"b7236d7d-2cc5-47fb-8488-1b9912776953\": \"b7236d7d-2cc5-47fb-8488-1b9912776953\", \"27441066-fc52-4e32-84f0-bcb7e96b95e3\": \"27441066-fc52-4e32-84f0-bcb7e96b95e3\", \"1a5f54bb-d26d-4578-b12a-1664b02909cb\": \"1a5f54bb-d26d-4578-b12a-1664b02909cb\", \"750185ed-a124-4388-b58b-9ed130293f41\": \"750185ed-a124-4388-b58b-9ed130293f41\", \"7a8c6539-2a0f-4314-b6b7-8134c3ed4613\": \"7a8c6539-2a0f-4314-b6b7-8134c3ed4613\", \"ae0c2a08-b372-4f4c-a8f5-47ef5161b8a3\": \"ae0c2a08-b372-4f4c-a8f5-47ef5161b8a3\", \"1c54f16a-8686-4da5-a670-077a46196f95\": \"1c54f16a-8686-4da5-a670-077a46196f95\", \"31b39139-75e3-4499-8d09-4adb50fccf53\": \"31b39139-75e3-4499-8d09-4adb50fccf53\", \"3849b83a-a21e-4739-a69a-5e8ea520eef0\": \"3849b83a-a21e-4739-a69a-5e8ea520eef0\", \"c0001344-1b35-4acc-914d-b539776588d5\": \"c0001344-1b35-4acc-914d-b539776588d5\", \"139eb3c4-8043-40f4-afd7-909635803c69\": \"139eb3c4-8043-40f4-afd7-909635803c69\", \"42f890c7-5595-40dd-a58b-ace99896bf3f\": \"42f890c7-5595-40dd-a58b-ace99896bf3f\", \"f64f9e11-630f-4d94-94ec-2d10dd62e055\": \"f64f9e11-630f-4d94-94ec-2d10dd62e055\", \"2c760563-876d-4043-ad1a-54f31c7b4608\": \"2c760563-876d-4043-ad1a-54f31c7b4608\", \"1c5d9a30-b419-411e-9a9c-09d63f8f927c\": \"1c5d9a30-b419-411e-9a9c-09d63f8f927c\", \"0ca04eac-1541-4d25-945f-f971c574e295\": \"0ca04eac-1541-4d25-945f-f971c574e295\", \"c9a74eca-8d40-4306-b922-df38c18e9945\": \"c9a74eca-8d40-4306-b922-df38c18e9945\", \"4cf0534f-a5b4-4484-80fb-1bd72110736f\": \"4cf0534f-a5b4-4484-80fb-1bd72110736f\", \"07636726-efbd-45c0-acd4-d85dd14f0416\": \"07636726-efbd-45c0-acd4-d85dd14f0416\", \"1ac6c4c2-3744-4a7b-8464-187aa35b36dc\": \"1ac6c4c2-3744-4a7b-8464-187aa35b36dc\", \"31442d7d-c27b-442b-9348-fd50759a7bf9\": \"31442d7d-c27b-442b-9348-fd50759a7bf9\", \"31b7d28d-29d0-42b0-b160-c406c162cb3c\": \"31b7d28d-29d0-42b0-b160-c406c162cb3c\", \"7bb5cfc4-b922-4f1b-a4b9-aac14b60b8ef\": \"7bb5cfc4-b922-4f1b-a4b9-aac14b60b8ef\", \"893538c5-4bad-4704-8e5e-48903fe2b1b6\": \"893538c5-4bad-4704-8e5e-48903fe2b1b6\", \"8be7b434-7e8a-42cc-9d6f-a74b86d187e9\": \"8be7b434-7e8a-42cc-9d6f-a74b86d187e9\", \"ff451a2a-2f5f-417c-99f0-2c928b6c3579\": \"ff451a2a-2f5f-417c-99f0-2c928b6c3579\", \"bd95b6e4-e79b-4afc-90ed-a062fc567f97\": \"bd95b6e4-e79b-4afc-90ed-a062fc567f97\", \"97f3cc86-8565-47e3-979f-b2848bd7d0f4\": \"97f3cc86-8565-47e3-979f-b2848bd7d0f4\", \"eb8c7ac7-0b86-4863-be49-6bbbee86a5ef\": \"eb8c7ac7-0b86-4863-be49-6bbbee86a5ef\", \"f601eeb1-e587-496a-bcd6-ee5d4fb37dd2\": \"f601eeb1-e587-496a-bcd6-ee5d4fb37dd2\", \"5ff3a051-68c4-47de-af7f-1fd24ce0fb1c\": \"5ff3a051-68c4-47de-af7f-1fd24ce0fb1c\", \"20ea55fc-96a5-4bcd-91b6-e333ea3e9b09\": \"20ea55fc-96a5-4bcd-91b6-e333ea3e9b09\", \"c9574c7d-15d2-4fac-89dd-f2ee66a9244e\": \"c9574c7d-15d2-4fac-89dd-f2ee66a9244e\", \"dda1e291-4ca8-4552-9bde-5b913851a993\": \"dda1e291-4ca8-4552-9bde-5b913851a993\", \"f4883573-68a1-4013-84a9-007b76d7ffb4\": \"f4883573-68a1-4013-84a9-007b76d7ffb4\", \"3fe2d4d4-cb04-4e5b-be41-27904999a055\": \"3fe2d4d4-cb04-4e5b-be41-27904999a055\", \"9eec6401-892f-45f8-b57f-e7939d7af72c\": \"9eec6401-892f-45f8-b57f-e7939d7af72c\", \"446ca316-9419-4a18-b4c1-d38f401e8a91\": \"446ca316-9419-4a18-b4c1-d38f401e8a91\", \"4ab5bf38-4f45-4c9f-944e-0182c3b1291f\": \"4ab5bf38-4f45-4c9f-944e-0182c3b1291f\", \"3923aac7-e013-4c5f-b780-3b993ba32b66\": \"3923aac7-e013-4c5f-b780-3b993ba32b66\", \"ecaaf6d2-52ea-4a97-86e3-ca9352683c14\": \"ecaaf6d2-52ea-4a97-86e3-ca9352683c14\", \"97837e8f-b09e-43e6-b926-9ec42dea6025\": \"97837e8f-b09e-43e6-b926-9ec42dea6025\", \"124e4835-92c0-46f2-81f1-a281f8c9c6a2\": \"124e4835-92c0-46f2-81f1-a281f8c9c6a2\", \"73c45f9d-bdb4-4a8d-b3bb-40daadd0ba21\": \"73c45f9d-bdb4-4a8d-b3bb-40daadd0ba21\", \"fb464bb7-fc5d-4b23-a666-77a47a8158ca\": \"fb464bb7-fc5d-4b23-a666-77a47a8158ca\", \"e8a9f9b6-7c9f-4a53-81f5-ab8a77ded966\": \"e8a9f9b6-7c9f-4a53-81f5-ab8a77ded966\", \"ade4042b-07b2-4f07-9326-9e9a314dda98\": \"ade4042b-07b2-4f07-9326-9e9a314dda98\", \"2cba6dda-6f95-460b-aa95-0b7edfdfb437\": \"2cba6dda-6f95-460b-aa95-0b7edfdfb437\", \"827549f4-652d-47ad-86c7-02d58eaeeb34\": \"827549f4-652d-47ad-86c7-02d58eaeeb34\", \"6b3b813a-8c4a-473e-a541-565bb9b638e9\": \"6b3b813a-8c4a-473e-a541-565bb9b638e9\", \"993e01a2-d24f-4618-95fd-9c9a81ca98f1\": \"993e01a2-d24f-4618-95fd-9c9a81ca98f1\", \"5d0543fc-8e03-473d-bd61-faf57976cf93\": \"5d0543fc-8e03-473d-bd61-faf57976cf93\", \"f5a34731-c855-4850-a04a-e32d679b8444\": \"f5a34731-c855-4850-a04a-e32d679b8444\", \"6b74acf2-b2ba-4125-b1a6-8d585705669a\": \"6b74acf2-b2ba-4125-b1a6-8d585705669a\", \"55a69d19-d181-4fff-990b-32d2be9352b3\": \"55a69d19-d181-4fff-990b-32d2be9352b3\", \"130e5e83-cedf-45ab-9c5d-bc20144c1e09\": \"130e5e83-cedf-45ab-9c5d-bc20144c1e09\", \"c090b8a0-6175-48b4-97be-e1131f6c5394\": \"c090b8a0-6175-48b4-97be-e1131f6c5394\", \"fc46c19f-07b0-4ccd-99ba-a6af49cda1d0\": \"fc46c19f-07b0-4ccd-99ba-a6af49cda1d0\", \"fb2e5634-7132-46bb-955f-5a1dda245a94\": \"fb2e5634-7132-46bb-955f-5a1dda245a94\", \"e059c40e-6a9c-4546-b194-ffb2a36c1f43\": \"e059c40e-6a9c-4546-b194-ffb2a36c1f43\", \"e261c9b7-341f-4ef4-8e40-b2851778c727\": \"e261c9b7-341f-4ef4-8e40-b2851778c727\", \"fdff4819-5cf3-4130-aa0a-71c717008cbd\": \"fdff4819-5cf3-4130-aa0a-71c717008cbd\", \"4dd7a783-409f-45d8-8bfc-e9805d2d9842\": \"4dd7a783-409f-45d8-8bfc-e9805d2d9842\", \"5cd483c2-6828-4ad5-9c4e-4a0a97e14325\": \"5cd483c2-6828-4ad5-9c4e-4a0a97e14325\", \"2658b3eb-0499-4b6a-bf53-3d2b9dcbd82d\": \"2658b3eb-0499-4b6a-bf53-3d2b9dcbd82d\", \"3ad84d57-44b9-49a5-bd80-2fba62964f2f\": \"3ad84d57-44b9-49a5-bd80-2fba62964f2f\", \"09f22c37-e7d2-42ff-b26f-d11719269d16\": \"09f22c37-e7d2-42ff-b26f-d11719269d16\", \"ebc073c0-3157-4f78-955e-16b8c65e66ad\": \"ebc073c0-3157-4f78-955e-16b8c65e66ad\", \"5197c8d1-89e5-458a-82d4-388784ecd4af\": \"5197c8d1-89e5-458a-82d4-388784ecd4af\", \"37adc1c4-13fd-44f4-8d93-4730f37c1933\": \"37adc1c4-13fd-44f4-8d93-4730f37c1933\", \"3d8366b9-4cbd-427f-87e8-8fb84b7fad43\": \"3d8366b9-4cbd-427f-87e8-8fb84b7fad43\", \"ab83f8d2-4964-4dce-9835-3ba52bcd2da1\": \"ab83f8d2-4964-4dce-9835-3ba52bcd2da1\", \"9eafc79b-94e9-4d69-af90-9617f7255d61\": \"9eafc79b-94e9-4d69-af90-9617f7255d61\", \"2a669d17-d183-4fd8-8f13-9ef6cb1612de\": \"2a669d17-d183-4fd8-8f13-9ef6cb1612de\", \"934de2c6-0327-4e01-8c86-69e5212b23ba\": \"934de2c6-0327-4e01-8c86-69e5212b23ba\", \"2feb892c-8546-457d-b922-48e82ae28a5f\": \"2feb892c-8546-457d-b922-48e82ae28a5f\", \"b20ca01c-85c5-4df5-a35c-32cc0ead364c\": \"b20ca01c-85c5-4df5-a35c-32cc0ead364c\", \"0201b283-424c-4291-b9d9-b7f361c8197f\": \"0201b283-424c-4291-b9d9-b7f361c8197f\", \"a96ea954-ac73-4626-b411-08acc7f597dc\": \"a96ea954-ac73-4626-b411-08acc7f597dc\", \"ff73bd01-b280-4b1a-8b16-c5d85b42fa16\": \"ff73bd01-b280-4b1a-8b16-c5d85b42fa16\", \"aa083ad1-dc20-4101-b6ca-ed430ae5fd16\": \"aa083ad1-dc20-4101-b6ca-ed430ae5fd16\", \"313fdfcd-2f5e-4884-8dbc-8dc2240b6f7e\": \"313fdfcd-2f5e-4884-8dbc-8dc2240b6f7e\", \"b67fc1d0-33e0-4642-83a9-e31cb60e6d4a\": \"b67fc1d0-33e0-4642-83a9-e31cb60e6d4a\", \"70228e02-2e3f-4ac9-8499-d6e30e5d2fc1\": \"70228e02-2e3f-4ac9-8499-d6e30e5d2fc1\", \"e89f02c6-0db4-4de5-a244-881341584e19\": \"e89f02c6-0db4-4de5-a244-881341584e19\", \"f9e4248b-8d8f-4916-b936-93a1113e0113\": \"f9e4248b-8d8f-4916-b936-93a1113e0113\", \"495d2a62-60a0-49a4-bf8b-8f869369f8cf\": \"495d2a62-60a0-49a4-bf8b-8f869369f8cf\", \"3ef01d0e-058b-4ca2-a63f-f7eacc59f4f0\": \"3ef01d0e-058b-4ca2-a63f-f7eacc59f4f0\", \"5a7136a2-3709-436f-98a1-e1bbb3a3c689\": \"5a7136a2-3709-436f-98a1-e1bbb3a3c689\", \"9ff32801-66aa-4e30-b96d-75e0b7d30b77\": \"9ff32801-66aa-4e30-b96d-75e0b7d30b77\", \"57a2c8c5-fa58-4bf3-b583-54fb17f35ce4\": \"57a2c8c5-fa58-4bf3-b583-54fb17f35ce4\", \"3bb2fdc0-8280-40cc-8c62-a130a282edea\": \"3bb2fdc0-8280-40cc-8c62-a130a282edea\", \"9930be85-2d36-4fa4-bb82-a6c09c3d1b61\": \"9930be85-2d36-4fa4-bb82-a6c09c3d1b61\", \"05c4da03-af72-418b-9e18-bcd9d36d3496\": \"05c4da03-af72-418b-9e18-bcd9d36d3496\", \"b20e8f91-2d10-4ab0-baf5-f42a30cdc488\": \"b20e8f91-2d10-4ab0-baf5-f42a30cdc488\", \"6a4735fc-649d-441b-a7b4-025dbba1bab4\": \"6a4735fc-649d-441b-a7b4-025dbba1bab4\", \"cbf8a6bc-ee6f-4c54-bebe-31683348e217\": \"cbf8a6bc-ee6f-4c54-bebe-31683348e217\", \"e67fbc5a-faba-44dd-9a0a-b7d034394557\": \"e67fbc5a-faba-44dd-9a0a-b7d034394557\", \"dee4fceb-da69-4772-b7e6-e915c20c00b6\": \"dee4fceb-da69-4772-b7e6-e915c20c00b6\", \"584c549c-0afb-4885-8d58-1168f77ab512\": \"584c549c-0afb-4885-8d58-1168f77ab512\", \"669c27a8-a1e6-42b3-a7b4-4dbd3366ae49\": \"669c27a8-a1e6-42b3-a7b4-4dbd3366ae49\", \"207256ee-5487-47dc-ade7-6acc4e79bffe\": \"207256ee-5487-47dc-ade7-6acc4e79bffe\", \"92a3bb7c-9c35-4a08-8329-888026f97dcb\": \"92a3bb7c-9c35-4a08-8329-888026f97dcb\", \"05d3e2ea-7ae9-4284-8b4f-fdead30c52a7\": \"05d3e2ea-7ae9-4284-8b4f-fdead30c52a7\", \"5c7e8914-4e89-47b2-8225-b79aefbc7d7d\": \"5c7e8914-4e89-47b2-8225-b79aefbc7d7d\", \"2ff0a2b7-c770-4a22-beb0-6161f51e9fcc\": \"2ff0a2b7-c770-4a22-beb0-6161f51e9fcc\", \"5054ede9-f6ee-4e04-908d-8f6282d414ab\": \"5054ede9-f6ee-4e04-908d-8f6282d414ab\", \"7684ea2d-adc0-40ec-9b50-79784e36df63\": \"7684ea2d-adc0-40ec-9b50-79784e36df63\", \"62fd0f7d-f8bb-4bb1-a8fe-4872df316788\": \"62fd0f7d-f8bb-4bb1-a8fe-4872df316788\", \"ab0b4a4b-764d-41d3-a778-991b7169d099\": \"ab0b4a4b-764d-41d3-a778-991b7169d099\", \"75e215e9-c832-4cab-9fa1-54ccf73f39c0\": \"75e215e9-c832-4cab-9fa1-54ccf73f39c0\", \"acfa322d-bba4-4260-a91b-79174806afa9\": \"acfa322d-bba4-4260-a91b-79174806afa9\", \"53249f4b-903f-4ddd-a4f5-e992977b1fb1\": \"53249f4b-903f-4ddd-a4f5-e992977b1fb1\", \"9f0035f7-a1ba-471d-9ab9-2795dcd239f9\": \"9f0035f7-a1ba-471d-9ab9-2795dcd239f9\", \"7c082c06-bdcd-48c8-9fa5-d85af8e865b3\": \"7c082c06-bdcd-48c8-9fa5-d85af8e865b3\", \"7924dc9a-906c-4497-ae05-c77629656616\": \"7924dc9a-906c-4497-ae05-c77629656616\", \"408850d4-300a-45b0-ae77-5ed754682bfd\": \"408850d4-300a-45b0-ae77-5ed754682bfd\", \"ed4d6a3a-ff03-42b4-9302-4c5db74a22cb\": \"ed4d6a3a-ff03-42b4-9302-4c5db74a22cb\", \"810bf241-cf0e-40a5-a4a4-6ccb36521400\": \"810bf241-cf0e-40a5-a4a4-6ccb36521400\", \"1c476bfb-800e-45a2-961d-a7e7c3f9a64c\": \"1c476bfb-800e-45a2-961d-a7e7c3f9a64c\", \"181230b1-9507-4b3d-b685-d5f0271a74a0\": \"181230b1-9507-4b3d-b685-d5f0271a74a0\", \"a756f45d-aa36-4894-93ea-54131b0278f2\": \"a756f45d-aa36-4894-93ea-54131b0278f2\", \"2062c357-c9a6-4b83-901c-8e766321c156\": \"2062c357-c9a6-4b83-901c-8e766321c156\", \"ea502e89-db2c-4b67-9475-39172ec68a0c\": \"ea502e89-db2c-4b67-9475-39172ec68a0c\", \"79a8521d-7bec-4e21-a4c8-cf8101d2e537\": \"79a8521d-7bec-4e21-a4c8-cf8101d2e537\", \"b10a9e9d-b0d1-464b-b9b6-0a057eb5c368\": \"b10a9e9d-b0d1-464b-b9b6-0a057eb5c368\", \"a17581e8-0e36-45e6-941c-1fc0fd170319\": \"a17581e8-0e36-45e6-941c-1fc0fd170319\"}, \"doc_id_dict\": {}, \"embeddings_dict\": {}}"}}}