diff --git a/dsLightRag/Config/Config.py b/dsLightRag/Config/Config.py
index 6bfe7776..6bcc5fb5 100644
--- a/dsLightRag/Config/Config.py
+++ b/dsLightRag/Config/Config.py
@@ -1,13 +1,13 @@
# 大模型 【DeepSeek深度求索官方】
-LLM_API_KEY = "sk-44ae895eeb614aa1a9c6460579e322f1"
-LLM_BASE_URL = "https://api.deepseek.com"
-LLM_MODEL_NAME = "deepseek-chat"
+#LLM_API_KEY = "sk-44ae895eeb614aa1a9c6460579e322f1"
+#LLM_BASE_URL = "https://api.deepseek.com"
+#LLM_MODEL_NAME = "deepseek-chat"
# 阿里云提供的大模型服务
-#LLM_API_KEY="sk-f6da0c787eff4b0389e4ad03a35a911f"
-#LLM_BASE_URL = "https://dashscope.aliyuncs.com/compatible-mode/v1"
+LLM_API_KEY="sk-f6da0c787eff4b0389e4ad03a35a911f"
+LLM_BASE_URL = "https://dashscope.aliyuncs.com/compatible-mode/v1"
#LLM_MODEL_NAME = "qwen-plus" # 不要使用通义千问，会导致化学方程式不正确！
-#LLM_MODEL_NAME = "deepseek-v3"
+LLM_MODEL_NAME = "deepseek-v3"
EMBED_MODEL_NAME = "BAAI/bge-m3"
EMBED_API_KEY = "sk-pbqibyjwhrgmnlsmdygplahextfaclgnedetybccknxojlyl"
diff --git a/dsLightRag/Config/__pycache__/Config.cpython-310.pyc b/dsLightRag/Config/__pycache__/Config.cpython-310.pyc
index 5133b3f2..98847505 100644
Binary files a/dsLightRag/Config/__pycache__/Config.cpython-310.pyc and b/dsLightRag/Config/__pycache__/Config.cpython-310.pyc differ
diff --git a/dsLightRag/Start.py b/dsLightRag/Start.py
index 3ac5312e..638c5036 100644
--- a/dsLightRag/Start.py
+++ b/dsLightRag/Start.py
@@ -42,13 +42,13 @@ app.mount("/static", StaticFiles(directory="Static"), name="static")
@app.post("/api/rag")
async def rag(request: fastapi.Request):
data = await request.json()
- topic = data.get("topic") # Chinese, Math
+ topic = data.get("topic") # Chinese, Math
# 拼接路径
- WORKING_PATH= "./Topic/" + topic
+ WORKING_PATH = "./Topic/" + topic
# 查询的问题
query = data.get("query")
# 关闭参考资料
- user_prompt="\n 1、不要输出参考资料 或者 References ！"
+ user_prompt = "\n 1、不要输出参考资料 或者 References ！"
user_prompt = user_prompt + "\n 2、如果问题与提供的知识库内容不符，则明确告诉未在知识库范围内提到！"
async def generate_response_stream(query: str):
@@ -63,7 +63,7 @@ async def rag(request: fastapi.Request):
await initialize_pipeline_status()
resp = await rag.aquery(
query=query,
- param=QueryParam(mode="hybrid", stream=True))
+ param=QueryParam(mode="hybrid", stream=True, user_prompt=user_prompt))
async for chunk in resp:
if not chunk:
diff --git a/dsLightRag/Topic/Chemistry/graph_chunk_entity_relation.graphml b/dsLightRag/Topic/Chemistry/graph_chunk_entity_relation.graphml
new file mode 100644
index 00000000..6b6da159
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/graph_chunk_entity_relation.graphml
@@ -0,0 +1,193 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 硝酸
+ category
+ 硝酸是一种化学物质，化学式为HNO₃，在光照或加热条件下会分解。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 二氧化氮
+ category
+ 二氧化氮是硝酸分解的产物之一，化学式为NO₂，以气体形式释放。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 氧气
+ category
+ 氧气是硝酸分解的产物之一，化学式为O₂，以气体形式释放。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 水
+ category
+ 水是硝酸分解的产物之一，化学式为H₂O。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 硝酸分解反应
+ event
+ 硝酸在光照或加热条件下分解为二氧化氮、氧气和水，是一种典型的化学分解反应。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 光照条件
+ event
+ 光照是引发硝酸分解反应的重要外部条件之一。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 加热条件
+ event
+ 加热是引发硝酸分解反应的另一种重要外部条件。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 化学方程式
+ category
+ 描述硝酸分解反应过程的符号表示：4HNO₃→4NO₂↑+O₂↑+2H₂O。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 分解反应
+ category
+ 一种化学反应类型，指单一化合物分解为两种或多种较简单物质。
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 9.0
+ 硝酸是分解反应的反应物，在光照或加热条件下发生分解。
+ 化学反应,物质转化
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 9.0
+ 硝酸分解产生二氧化氮作为主要产物。
+ 产物生成,化学反应
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 8.0
+ 硝酸分解产生氧气作为副产物。
+ 化学反应,气体生成
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 8.0
+ 硝酸分解产生水作为副产物。
+ 化学反应,液体生成
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 7.0
+ 光照是引发硝酸分解的重要条件之一。
+ 反应条件,能量输入
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 7.0
+ 加热是引发硝酸分解的另一种重要条件。
+ 反应条件,能量输入
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 9.0
+ 硝酸的分解是典型的分解反应实例。
+ 化学变化,反应类型
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 8.0
+ 硝酸分解反应生成二氧化氮作为产物之一。
+ 化学产物,气体释放
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 6.0
+ 两者都是硝酸分解的气态产物。
+ 共同产物,气体释放
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 8.0
+ 硝酸分解反应生成氧气作为产物之一。
+ 化学产物,气体释放
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 7.0
+ 硝酸分解反应生成水作为产物之一。
+ 化学产物,液体生成
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 10.0
+ 化学方程式准确描述了硝酸分解的反应过程。
+ 反应描述,符号表示
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+ 5.0
+ 两者都是引发硝酸分解的能量输入方式。
+ 反应条件,能量来源
+ chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6
+ unknown_source
+ 1752042117
+
+
+
diff --git a/dsLightRag/Topic/Chemistry/kv_store_doc_status.json b/dsLightRag/Topic/Chemistry/kv_store_doc_status.json
index 52a7be3f..e8ea794c 100644
--- a/dsLightRag/Topic/Chemistry/kv_store_doc_status.json
+++ b/dsLightRag/Topic/Chemistry/kv_store_doc_status.json
@@ -1,12 +1,12 @@
{
"doc-fa4cbbef47ac19e90c1a1de96f1ce2f6": {
- "status": "processing",
+ "status": "processed",
"chunks_count": 1,
"content": "硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$",
"content_summary": "硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$",
"content_length": 120,
"created_at": "2025-07-09T06:20:51.851607+00:00",
- "updated_at": "2025-07-09T06:20:51.854134+00:00",
+ "updated_at": "2025-07-09T06:21:58.453864+00:00",
"file_path": "unknown_source"
}
}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/kv_store_full_docs.json b/dsLightRag/Topic/Chemistry/kv_store_full_docs.json
new file mode 100644
index 00000000..346ff139
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/kv_store_full_docs.json
@@ -0,0 +1,5 @@
+{
+ "doc-fa4cbbef47ac19e90c1a1de96f1ce2f6": {
+ "content": "硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$"
+ }
+}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/kv_store_llm_response_cache.json b/dsLightRag/Topic/Chemistry/kv_store_llm_response_cache.json
index 3083f3ec..da7e9eed 100644
--- a/dsLightRag/Topic/Chemistry/kv_store_llm_response_cache.json
+++ b/dsLightRag/Topic/Chemistry/kv_store_llm_response_cache.json
@@ -2411,6 +2411,26 @@
"embedding_min": null,
"embedding_max": null,
"original_prompt": "[{\"role\": \"user\", \"content\": \"---Goal---\\nGiven a text document that is potentially relevant to this activity and a list of entity types, identify all entities of those types from the text and all relationships among the identified entities.\\nUse English as output language.\\n\\n---Steps---\\n1. Identify all entities. For each identified entity, extract the following information:\\n- entity_name: Name of the entity, use same language as input text. If English, capitalized the name.\\n- entity_type: One of the following types: [organization,person,geo,event,category]\\n- entity_description: Comprehensive description of the entity's attributes and activities\\nFormat each entity as (\\\"entity\\\"<|><|><|>)\\n\\n2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\\nFor each pair of related entities, extract the following information:\\n- source_entity: name of the source entity, as identified in step 1\\n- target_entity: name of the target entity, as identified in step 1\\n- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\\n- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity\\n- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details\\nFormat each relationship as (\\\"relationship\\\"<|><|><|><|><|>)\\n\\n3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.\\nFormat the content-level key words as (\\\"content_keywords\\\"<|>)\\n\\n4. Return output in English as a single list of all the entities and relationships identified in steps 1 and 2. Use **##** as the list delimiter.\\n\\n5. When finished, output <|COMPLETE|>\\n\\n######################\\n---Examples---\\n######################\\nExample 1:\\n\\nEntity_types: [person, technology, mission, organization, location]\\nText:\\n```\\nwhile Alex clenched his jaw, the buzz of frustration dull against the backdrop of Taylor's authoritarian certainty. It was this competitive undercurrent that kept him alert, the sense that his and Jordan's shared commitment to discovery was an unspoken rebellion against Cruz's narrowing vision of control and order.\\n\\nThen Taylor did something unexpected. They paused beside Jordan and, for a moment, observed the device with something akin to reverence. \\\"If this tech can be understood...\\\" Taylor said, their voice quieter, \\\"It could change the game for us. For all of us.\\\"\\n\\nThe underlying dismissal earlier seemed to falter, replaced by a glimpse of reluctant respect for the gravity of what lay in their hands. Jordan looked up, and for a fleeting heartbeat, their eyes locked with Taylor's, a wordless clash of wills softening into an uneasy truce.\\n\\nIt was a small transformation, barely perceptible, but one that Alex noted with an inward nod. They had all been brought here by different paths\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"Alex\\\"<|>\\\"person\\\"<|>\\\"Alex is a character who experiences frustration and is observant of the dynamics among other characters.\\\")##\\n(\\\"entity\\\"<|>\\\"Taylor\\\"<|>\\\"person\\\"<|>\\\"Taylor is portrayed with authoritarian certainty and shows a moment of reverence towards a device, indicating a change in perspective.\\\")##\\n(\\\"entity\\\"<|>\\\"Jordan\\\"<|>\\\"person\\\"<|>\\\"Jordan shares a commitment to discovery and has a significant interaction with Taylor regarding a device.\\\")##\\n(\\\"entity\\\"<|>\\\"Cruz\\\"<|>\\\"person\\\"<|>\\\"Cruz is associated with a vision of control and order, influencing the dynamics among other characters.\\\")##\\n(\\\"entity\\\"<|>\\\"The Device\\\"<|>\\\"technology\\\"<|>\\\"The Device is central to the story, with potential game-changing implications, and is revered by Taylor.\\\")##\\n(\\\"relationship\\\"<|>\\\"Alex\\\"<|>\\\"Taylor\\\"<|>\\\"Alex is affected by Taylor's authoritarian certainty and observes changes in Taylor's attitude towards the device.\\\"<|>\\\"power dynamics, perspective shift\\\"<|>7)##\\n(\\\"relationship\\\"<|>\\\"Alex\\\"<|>\\\"Jordan\\\"<|>\\\"Alex and Jordan share a commitment to discovery, which contrasts with Cruz's vision.\\\"<|>\\\"shared goals, rebellion\\\"<|>6)##\\n(\\\"relationship\\\"<|>\\\"Taylor\\\"<|>\\\"Jordan\\\"<|>\\\"Taylor and Jordan interact directly regarding the device, leading to a moment of mutual respect and an uneasy truce.\\\"<|>\\\"conflict resolution, mutual respect\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Jordan\\\"<|>\\\"Cruz\\\"<|>\\\"Jordan's commitment to discovery is in rebellion against Cruz's vision of control and order.\\\"<|>\\\"ideological conflict, rebellion\\\"<|>5)##\\n(\\\"relationship\\\"<|>\\\"Taylor\\\"<|>\\\"The Device\\\"<|>\\\"Taylor shows reverence towards the device, indicating its importance and potential impact.\\\"<|>\\\"reverence, technological significance\\\"<|>9)##\\n(\\\"content_keywords\\\"<|>\\\"power dynamics, ideological conflict, discovery, rebellion\\\")<|COMPLETE|>\\n#############################\\nExample 2:\\n\\nEntity_types: [company, index, commodity, market_trend, economic_policy, biological]\\nText:\\n```\\nStock markets faced a sharp downturn today as tech giants saw significant declines, with the Global Tech Index dropping by 3.4% in midday trading. Analysts attribute the selloff to investor concerns over rising interest rates and regulatory uncertainty.\\n\\nAmong the hardest hit, Nexon Technologies saw its stock plummet by 7.8% after reporting lower-than-expected quarterly earnings. In contrast, Omega Energy posted a modest 2.1% gain, driven by rising oil prices.\\n\\nMeanwhile, commodity markets reflected a mixed sentiment. Gold futures rose by 1.5%, reaching $2,080 per ounce, as investors sought safe-haven assets. Crude oil prices continued their rally, climbing to $87.60 per barrel, supported by supply constraints and strong demand.\\n\\nFinancial experts are closely watching the Federal Reserve's next move, as speculation grows over potential rate hikes. The upcoming policy announcement is expected to influence investor confidence and overall market stability.\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"Global Tech Index\\\"<|>\\\"index\\\"<|>\\\"The Global Tech Index tracks the performance of major technology stocks and experienced a 3.4% decline today.\\\")##\\n(\\\"entity\\\"<|>\\\"Nexon Technologies\\\"<|>\\\"company\\\"<|>\\\"Nexon Technologies is a tech company that saw its stock decline by 7.8% after disappointing earnings.\\\")##\\n(\\\"entity\\\"<|>\\\"Omega Energy\\\"<|>\\\"company\\\"<|>\\\"Omega Energy is an energy company that gained 2.1% in stock value due to rising oil prices.\\\")##\\n(\\\"entity\\\"<|>\\\"Gold Futures\\\"<|>\\\"commodity\\\"<|>\\\"Gold futures rose by 1.5%, indicating increased investor interest in safe-haven assets.\\\")##\\n(\\\"entity\\\"<|>\\\"Crude Oil\\\"<|>\\\"commodity\\\"<|>\\\"Crude oil prices rose to $87.60 per barrel due to supply constraints and strong demand.\\\")##\\n(\\\"entity\\\"<|>\\\"Market Selloff\\\"<|>\\\"market_trend\\\"<|>\\\"Market selloff refers to the significant decline in stock values due to investor concerns over interest rates and regulations.\\\")##\\n(\\\"entity\\\"<|>\\\"Federal Reserve Policy Announcement\\\"<|>\\\"economic_policy\\\"<|>\\\"The Federal Reserve's upcoming policy announcement is expected to impact investor confidence and market stability.\\\")##\\n(\\\"relationship\\\"<|>\\\"Global Tech Index\\\"<|>\\\"Market Selloff\\\"<|>\\\"The decline in the Global Tech Index is part of the broader market selloff driven by investor concerns.\\\"<|>\\\"market performance, investor sentiment\\\"<|>9)##\\n(\\\"relationship\\\"<|>\\\"Nexon Technologies\\\"<|>\\\"Global Tech Index\\\"<|>\\\"Nexon Technologies' stock decline contributed to the overall drop in the Global Tech Index.\\\"<|>\\\"company impact, index movement\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Gold Futures\\\"<|>\\\"Market Selloff\\\"<|>\\\"Gold prices rose as investors sought safe-haven assets during the market selloff.\\\"<|>\\\"market reaction, safe-haven investment\\\"<|>10)##\\n(\\\"relationship\\\"<|>\\\"Federal Reserve Policy Announcement\\\"<|>\\\"Market Selloff\\\"<|>\\\"Speculation over Federal Reserve policy changes contributed to market volatility and investor selloff.\\\"<|>\\\"interest rate impact, financial regulation\\\"<|>7)##\\n(\\\"content_keywords\\\"<|>\\\"market downturn, investor sentiment, commodities, Federal Reserve, stock performance\\\")<|COMPLETE|>\\n#############################\\nExample 3:\\n\\nEntity_types: [economic_policy, athlete, event, location, record, organization, equipment]\\nText:\\n```\\nAt the World Athletics Championship in Tokyo, Noah Carter broke the 100m sprint record using cutting-edge carbon-fiber spikes.\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"World Athletics Championship\\\"<|>\\\"event\\\"<|>\\\"The World Athletics Championship is a global sports competition featuring top athletes in track and field.\\\")##\\n(\\\"entity\\\"<|>\\\"Tokyo\\\"<|>\\\"location\\\"<|>\\\"Tokyo is the host city of the World Athletics Championship.\\\")##\\n(\\\"entity\\\"<|>\\\"Noah Carter\\\"<|>\\\"athlete\\\"<|>\\\"Noah Carter is a sprinter who set a new record in the 100m sprint at the World Athletics Championship.\\\")##\\n(\\\"entity\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"record\\\"<|>\\\"The 100m sprint record is a benchmark in athletics, recently broken by Noah Carter.\\\")##\\n(\\\"entity\\\"<|>\\\"Carbon-Fiber Spikes\\\"<|>\\\"equipment\\\"<|>\\\"Carbon-fiber spikes are advanced sprinting shoes that provide enhanced speed and traction.\\\")##\\n(\\\"entity\\\"<|>\\\"World Athletics Federation\\\"<|>\\\"organization\\\"<|>\\\"The World Athletics Federation is the governing body overseeing the World Athletics Championship and record validations.\\\")##\\n(\\\"relationship\\\"<|>\\\"World Athletics Championship\\\"<|>\\\"Tokyo\\\"<|>\\\"The World Athletics Championship is being hosted in Tokyo.\\\"<|>\\\"event location, international competition\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Noah Carter\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"Noah Carter set a new 100m sprint record at the championship.\\\"<|>\\\"athlete achievement, record-breaking\\\"<|>10)##\\n(\\\"relationship\\\"<|>\\\"Noah Carter\\\"<|>\\\"Carbon-Fiber Spikes\\\"<|>\\\"Noah Carter used carbon-fiber spikes to enhance performance during the race.\\\"<|>\\\"athletic equipment, performance boost\\\"<|>7)##\\n(\\\"relationship\\\"<|>\\\"World Athletics Federation\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"The World Athletics Federation is responsible for validating and recognizing new sprint records.\\\"<|>\\\"sports regulation, record certification\\\"<|>9)##\\n(\\\"content_keywords\\\"<|>\\\"athletics, sprinting, record-breaking, sports technology, competition\\\")<|COMPLETE|>\\n#############################\\n\\n#############################\\n---Real Data---\\n######################\\nEntity_types: [organization,person,geo,event,category]\\nText:\\n硝酸光照分解的方程式\\n 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O\\n######################\\nOutput:\"}, {\"role\": \"assistant\", \"content\": \"(\\\"entity\\\"<|>\\\"硝酸\\\"<|>\\\"category\\\"<|>\\\"硝酸是一种化学物质，化学式为HNO₃，在光照或加热条件下会分解。\\\")##\\n(\\\"entity\\\"<|>\\\"NO₂\\\"<|>\\\"category\\\"<|>\\\"二氧化氮是一种气体，化学式为NO₂，是硝酸分解的产物之一。\\\")##\\n(\\\"entity\\\"<|>\\\"O₂\\\"<|>\\\"category\\\"<|>\\\"氧气是一种气体，化学式为O₂，是硝酸分解的产物之一。\\\")##\\n(\\\"entity\\\"<|>\\\"H₂O\\\"<|>\\\"category\\\"<|>\\\"水是一种液体，化学式为H₂O，是硝酸分解的产物之一。\\\")##\\n(\\\"relationship\\\"<|>\\\"硝酸\\\"<|>\\\"NO₂\\\"<|>\\\"硝酸在光照或加热条件下分解产生二氧化氮。\\\"<|>\\\"化学反应, 分解产物\\\"<|>9)##\\n(\\\"relationship\\\"<|>\\\"硝酸\\\"<|>\\\"O₂\\\"<|>\\\"硝酸在光照或加热条件下分解产生氧气。\\\"<|>\\\"化学反应, 分解产物\\\"<|>9)##\\n(\\\"relationship\\\"<|>\\\"硝酸\\\"<|>\\\"H₂O\\\"<|>\\\"硝酸在光照或加热条件下分解产生水。\\\"<|>\\\"化学反应, 分解产物\\\"<|>9)##\\n(\\\"content_keywords\\\"<|>\\\"化学方程式, 分解反应, 硝酸, 光照分解\\\")<|COMPLETE|>\"}]\nMANY entities and relationships were missed in the last extraction.\n\n---Remember Steps---\n\n1. Identify all entities. For each identified entity, extract the following information:\n- entity_name: Name of the entity, use same language as input text. If English, capitalized the name.\n- entity_type: One of the following types: [organization,person,geo,event,category]\n- entity_description: Comprehensive description of the entity's attributes and activities\nFormat each entity as (\"entity\"<|><|><|>)\n\n2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\nFor each pair of related entities, extract the following information:\n- source_entity: name of the source entity, as identified in step 1\n- target_entity: name of the target entity, as identified in step 1\n- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\n- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity\n- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details\nFormat each relationship as (\"relationship\"<|><|><|><|><|>)\n\n3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.\nFormat the content-level key words as (\"content_keywords\"<|>)\n\n4. Return output in English as a single list of all the entities and relationships identified in steps 1 and 2. Use **##** as the list delimiter.\n\n5. When finished, output <|COMPLETE|>\n\n---Output---\n\nAdd them below using the same format:"
+ },
+ "1ff009f35a9a64f51fc01eec41507ce6": {
+ "return": "(\"entity\"<|>\"硝酸\"<|>\"category\"<|>\"硝酸是一种化学物质，化学式为HNO₃，在光照或加热条件下会分解。\")## \n(\"entity\"<|>\"二氧化氮\"<|>\"category\"<|>\"二氧化氮是硝酸分解的产物之一，化学式为NO₂，以气体形式释放。\")## \n(\"entity\"<|>\"氧气\"<|>\"category\"<|>\"氧气是硝酸分解的产物之一，化学式为O₂，以气体形式释放。\")## \n(\"entity\"<|>\"水\"<|>\"category\"<|>\"水是硝酸分解的产物之一，化学式为H₂O。\")## \n(\"entity\"<|>\"硝酸分解反应\"<|>\"event\"<|>\"硝酸在光照或加热条件下分解为二氧化氮、氧气和水，是一种典型的化学分解反应。\")## \n(\"relationship\"<|>\"硝酸\"<|>\"硝酸分解反应\"<|>\"硝酸是分解反应的反应物，在光照或加热条件下发生分解。\"<|>\"化学反应, 物质转化\"<|>9)## \n(\"relationship\"<|>\"硝酸分解反应\"<|>\"二氧化氮\"<|>\"硝酸分解反应生成二氧化氮作为产物之一。\"<|>\"化学产物, 气体释放\"<|>8)## \n(\"relationship\"<|>\"硝酸分解反应\"<|>\"氧气\"<|>\"硝酸分解反应生成氧气作为产物之一。\"<|>\"化学产物, 气体释放\"<|>8)## \n(\"relationship\"<|>\"硝酸分解反应\"<|>\"水\"<|>\"硝酸分解反应生成水作为产物之一。\"<|>\"化学产物, 液体生成\"<|>7)## \n(\"content_keywords\"<|>\"化学分解, 硝酸, 反应方程式, 光照条件\")<|COMPLETE|>",
+ "cache_type": "extract",
+ "chunk_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6",
+ "embedding": null,
+ "embedding_shape": null,
+ "embedding_min": null,
+ "embedding_max": null,
+ "original_prompt": "---Goal---\nGiven a text document that is potentially relevant to this activity and a list of entity types, identify all entities of those types from the text and all relationships among the identified entities.\nUse English as output language.\n\n---Steps---\n1. Identify all entities. For each identified entity, extract the following information:\n- entity_name: Name of the entity, use same language as input text. If English, capitalized the name.\n- entity_type: One of the following types: [organization,person,geo,event,category]\n- entity_description: Comprehensive description of the entity's attributes and activities\nFormat each entity as (\"entity\"<|><|><|>)\n\n2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\nFor each pair of related entities, extract the following information:\n- source_entity: name of the source entity, as identified in step 1\n- target_entity: name of the target entity, as identified in step 1\n- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\n- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity\n- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details\nFormat each relationship as (\"relationship\"<|><|><|><|><|>)\n\n3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.\nFormat the content-level key words as (\"content_keywords\"<|>)\n\n4. Return output in English as a single list of all the entities and relationships identified in steps 1 and 2. Use **##** as the list delimiter.\n\n5. When finished, output <|COMPLETE|>\n\n######################\n---Examples---\n######################\nExample 1:\n\nEntity_types: [person, technology, mission, organization, location]\nText:\n```\nwhile Alex clenched his jaw, the buzz of frustration dull against the backdrop of Taylor's authoritarian certainty. It was this competitive undercurrent that kept him alert, the sense that his and Jordan's shared commitment to discovery was an unspoken rebellion against Cruz's narrowing vision of control and order.\n\nThen Taylor did something unexpected. They paused beside Jordan and, for a moment, observed the device with something akin to reverence. \"If this tech can be understood...\" Taylor said, their voice quieter, \"It could change the game for us. For all of us.\"\n\nThe underlying dismissal earlier seemed to falter, replaced by a glimpse of reluctant respect for the gravity of what lay in their hands. Jordan looked up, and for a fleeting heartbeat, their eyes locked with Taylor's, a wordless clash of wills softening into an uneasy truce.\n\nIt was a small transformation, barely perceptible, but one that Alex noted with an inward nod. They had all been brought here by different paths\n```\n\nOutput:\n(\"entity\"<|>\"Alex\"<|>\"person\"<|>\"Alex is a character who experiences frustration and is observant of the dynamics among other characters.\")##\n(\"entity\"<|>\"Taylor\"<|>\"person\"<|>\"Taylor is portrayed with authoritarian certainty and shows a moment of reverence towards a device, indicating a change in perspective.\")##\n(\"entity\"<|>\"Jordan\"<|>\"person\"<|>\"Jordan shares a commitment to discovery and has a significant interaction with Taylor regarding a device.\")##\n(\"entity\"<|>\"Cruz\"<|>\"person\"<|>\"Cruz is associated with a vision of control and order, influencing the dynamics among other characters.\")##\n(\"entity\"<|>\"The Device\"<|>\"technology\"<|>\"The Device is central to the story, with potential game-changing implications, and is revered by Taylor.\")##\n(\"relationship\"<|>\"Alex\"<|>\"Taylor\"<|>\"Alex is affected by Taylor's authoritarian certainty and observes changes in Taylor's attitude towards the device.\"<|>\"power dynamics, perspective shift\"<|>7)##\n(\"relationship\"<|>\"Alex\"<|>\"Jordan\"<|>\"Alex and Jordan share a commitment to discovery, which contrasts with Cruz's vision.\"<|>\"shared goals, rebellion\"<|>6)##\n(\"relationship\"<|>\"Taylor\"<|>\"Jordan\"<|>\"Taylor and Jordan interact directly regarding the device, leading to a moment of mutual respect and an uneasy truce.\"<|>\"conflict resolution, mutual respect\"<|>8)##\n(\"relationship\"<|>\"Jordan\"<|>\"Cruz\"<|>\"Jordan's commitment to discovery is in rebellion against Cruz's vision of control and order.\"<|>\"ideological conflict, rebellion\"<|>5)##\n(\"relationship\"<|>\"Taylor\"<|>\"The Device\"<|>\"Taylor shows reverence towards the device, indicating its importance and potential impact.\"<|>\"reverence, technological significance\"<|>9)##\n(\"content_keywords\"<|>\"power dynamics, ideological conflict, discovery, rebellion\")<|COMPLETE|>\n#############################\nExample 2:\n\nEntity_types: [company, index, commodity, market_trend, economic_policy, biological]\nText:\n```\nStock markets faced a sharp downturn today as tech giants saw significant declines, with the Global Tech Index dropping by 3.4% in midday trading. Analysts attribute the selloff to investor concerns over rising interest rates and regulatory uncertainty.\n\nAmong the hardest hit, Nexon Technologies saw its stock plummet by 7.8% after reporting lower-than-expected quarterly earnings. In contrast, Omega Energy posted a modest 2.1% gain, driven by rising oil prices.\n\nMeanwhile, commodity markets reflected a mixed sentiment. Gold futures rose by 1.5%, reaching $2,080 per ounce, as investors sought safe-haven assets. Crude oil prices continued their rally, climbing to $87.60 per barrel, supported by supply constraints and strong demand.\n\nFinancial experts are closely watching the Federal Reserve's next move, as speculation grows over potential rate hikes. The upcoming policy announcement is expected to influence investor confidence and overall market stability.\n```\n\nOutput:\n(\"entity\"<|>\"Global Tech Index\"<|>\"index\"<|>\"The Global Tech Index tracks the performance of major technology stocks and experienced a 3.4% decline today.\")##\n(\"entity\"<|>\"Nexon Technologies\"<|>\"company\"<|>\"Nexon Technologies is a tech company that saw its stock decline by 7.8% after disappointing earnings.\")##\n(\"entity\"<|>\"Omega Energy\"<|>\"company\"<|>\"Omega Energy is an energy company that gained 2.1% in stock value due to rising oil prices.\")##\n(\"entity\"<|>\"Gold Futures\"<|>\"commodity\"<|>\"Gold futures rose by 1.5%, indicating increased investor interest in safe-haven assets.\")##\n(\"entity\"<|>\"Crude Oil\"<|>\"commodity\"<|>\"Crude oil prices rose to $87.60 per barrel due to supply constraints and strong demand.\")##\n(\"entity\"<|>\"Market Selloff\"<|>\"market_trend\"<|>\"Market selloff refers to the significant decline in stock values due to investor concerns over interest rates and regulations.\")##\n(\"entity\"<|>\"Federal Reserve Policy Announcement\"<|>\"economic_policy\"<|>\"The Federal Reserve's upcoming policy announcement is expected to impact investor confidence and market stability.\")##\n(\"relationship\"<|>\"Global Tech Index\"<|>\"Market Selloff\"<|>\"The decline in the Global Tech Index is part of the broader market selloff driven by investor concerns.\"<|>\"market performance, investor sentiment\"<|>9)##\n(\"relationship\"<|>\"Nexon Technologies\"<|>\"Global Tech Index\"<|>\"Nexon Technologies' stock decline contributed to the overall drop in the Global Tech Index.\"<|>\"company impact, index movement\"<|>8)##\n(\"relationship\"<|>\"Gold Futures\"<|>\"Market Selloff\"<|>\"Gold prices rose as investors sought safe-haven assets during the market selloff.\"<|>\"market reaction, safe-haven investment\"<|>10)##\n(\"relationship\"<|>\"Federal Reserve Policy Announcement\"<|>\"Market Selloff\"<|>\"Speculation over Federal Reserve policy changes contributed to market volatility and investor selloff.\"<|>\"interest rate impact, financial regulation\"<|>7)##\n(\"content_keywords\"<|>\"market downturn, investor sentiment, commodities, Federal Reserve, stock performance\")<|COMPLETE|>\n#############################\nExample 3:\n\nEntity_types: [economic_policy, athlete, event, location, record, organization, equipment]\nText:\n```\nAt the World Athletics Championship in Tokyo, Noah Carter broke the 100m sprint record using cutting-edge carbon-fiber spikes.\n```\n\nOutput:\n(\"entity\"<|>\"World Athletics Championship\"<|>\"event\"<|>\"The World Athletics Championship is a global sports competition featuring top athletes in track and field.\")##\n(\"entity\"<|>\"Tokyo\"<|>\"location\"<|>\"Tokyo is the host city of the World Athletics Championship.\")##\n(\"entity\"<|>\"Noah Carter\"<|>\"athlete\"<|>\"Noah Carter is a sprinter who set a new record in the 100m sprint at the World Athletics Championship.\")##\n(\"entity\"<|>\"100m Sprint Record\"<|>\"record\"<|>\"The 100m sprint record is a benchmark in athletics, recently broken by Noah Carter.\")##\n(\"entity\"<|>\"Carbon-Fiber Spikes\"<|>\"equipment\"<|>\"Carbon-fiber spikes are advanced sprinting shoes that provide enhanced speed and traction.\")##\n(\"entity\"<|>\"World Athletics Federation\"<|>\"organization\"<|>\"The World Athletics Federation is the governing body overseeing the World Athletics Championship and record validations.\")##\n(\"relationship\"<|>\"World Athletics Championship\"<|>\"Tokyo\"<|>\"The World Athletics Championship is being hosted in Tokyo.\"<|>\"event location, international competition\"<|>8)##\n(\"relationship\"<|>\"Noah Carter\"<|>\"100m Sprint Record\"<|>\"Noah Carter set a new 100m sprint record at the championship.\"<|>\"athlete achievement, record-breaking\"<|>10)##\n(\"relationship\"<|>\"Noah Carter\"<|>\"Carbon-Fiber Spikes\"<|>\"Noah Carter used carbon-fiber spikes to enhance performance during the race.\"<|>\"athletic equipment, performance boost\"<|>7)##\n(\"relationship\"<|>\"World Athletics Federation\"<|>\"100m Sprint Record\"<|>\"The World Athletics Federation is responsible for validating and recognizing new sprint records.\"<|>\"sports regulation, record certification\"<|>9)##\n(\"content_keywords\"<|>\"athletics, sprinting, record-breaking, sports technology, competition\")<|COMPLETE|>\n#############################\n\n#############################\n---Real Data---\n######################\nEntity_types: [organization,person,geo,event,category]\nText:\n硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$\n######################\nOutput:"
+ },
+ "3ebd3094cc029528b2f1ab3488b328bf": {
+ "return": "(\"entity\"<|>\"硝酸\"<|>\"category\"<|>\"硝酸（HNO₃）是一种强酸，在光照或加热条件下会发生分解反应，生成二氧化氮、氧气和水。\")## \n(\"entity\"<|>\"二氧化氮\"<|>\"category\"<|>\"二氧化氮（NO₂）是硝酸分解的主要产物之一，呈红棕色气体，具有刺激性气味。\")## \n(\"entity\"<|>\"氧气\"<|>\"category\"<|>\"氧气（O₂）是硝酸分解的产物之一，无色无味，支持燃烧。\")## \n(\"entity\"<|>\"水\"<|>\"category\"<|>\"水（H₂O）是硝酸分解的产物之一，常温下为无色液体。\")## \n(\"entity\"<|>\"光照条件\"<|>\"event\"<|>\"光照是引发硝酸分解反应的重要外部条件之一。\")## \n(\"entity\"<|>\"加热条件\"<|>\"event\"<|>\"加热是引发硝酸分解反应的另一种重要外部条件。\")## \n(\"entity\"<|>\"化学方程式\"<|>\"category\"<|>\"描述硝酸分解反应过程的符号表示：4HNO₃→4NO₂↑+O₂↑+2H₂O。\")## \n(\"entity\"<|>\"分解反应\"<|>\"category\"<|>\"一种化学反应类型，指单一化合物分解为两种或多种较简单物质。\")## \n(\"relationship\"<|>\"硝酸\"<|>\"二氧化氮\"<|>\"硝酸分解产生二氧化氮作为主要产物。\"<|>\"化学反应,产物生成\"<|>9)## \n(\"relationship\"<|>\"硝酸\"<|>\"氧气\"<|>\"硝酸分解产生氧气作为副产物。\"<|>\"化学反应,气体生成\"<|>8)## \n(\"relationship\"<|>\"硝酸\"<|>\"水\"<|>\"硝酸分解产生水作为副产物。\"<|>\"化学反应,液体生成\"<|>8)## \n(\"relationship\"<|>\"硝酸\"<|>\"光照条件\"<|>\"光照是引发硝酸分解的重要条件之一。\"<|>\"反应条件,能量输入\"<|>7)## \n(\"relationship\"<|>\"硝酸\"<|>\"加热条件\"<|>\"加热是引发硝酸分解的另一种重要条件。\"<|>\"反应条件,能量输入\"<|>7)## \n(\"relationship\"<|>\"硝酸\"<|>\"分解反应\"<|>\"硝酸的分解是典型的分解反应实例。\"<|>\"反应类型,化学变化\"<|>9)## \n(\"relationship\"<|>\"化学方程式\"<|>\"硝酸分解反应\"<|>\"化学方程式准确描述了硝酸分解的反应过程。\"<|>\"符号表示,反应描述\"<|>10)## \n(\"relationship\"<|>\"二氧化氮\"<|>\"氧气\"<|>\"两者都是硝酸分解的气态产物。\"<|>\"共同产物,气体释放\"<|>6)## \n(\"relationship\"<|>\"光照条件\"<|>\"加热条件\"<|>\"两者都是引发硝酸分解的能量输入方式。\"<|>\"反应条件,能量来源\"<|>5)## \n(\"content_keywords\"<|>\"化学分解,硝酸反应,反应条件,化学方程式,产物生成\")<|COMPLETE|>",
+ "cache_type": "extract",
+ "chunk_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6",
+ "embedding": null,
+ "embedding_shape": null,
+ "embedding_min": null,
+ "embedding_max": null,
+ "original_prompt": "[{\"role\": \"user\", \"content\": \"---Goal---\\nGiven a text document that is potentially relevant to this activity and a list of entity types, identify all entities of those types from the text and all relationships among the identified entities.\\nUse English as output language.\\n\\n---Steps---\\n1. Identify all entities. For each identified entity, extract the following information:\\n- entity_name: Name of the entity, use same language as input text. If English, capitalized the name.\\n- entity_type: One of the following types: [organization,person,geo,event,category]\\n- entity_description: Comprehensive description of the entity's attributes and activities\\nFormat each entity as (\\\"entity\\\"<|><|><|>)\\n\\n2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\\nFor each pair of related entities, extract the following information:\\n- source_entity: name of the source entity, as identified in step 1\\n- target_entity: name of the target entity, as identified in step 1\\n- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\\n- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity\\n- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details\\nFormat each relationship as (\\\"relationship\\\"<|><|><|><|><|>)\\n\\n3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.\\nFormat the content-level key words as (\\\"content_keywords\\\"<|>)\\n\\n4. Return output in English as a single list of all the entities and relationships identified in steps 1 and 2. Use **##** as the list delimiter.\\n\\n5. When finished, output <|COMPLETE|>\\n\\n######################\\n---Examples---\\n######################\\nExample 1:\\n\\nEntity_types: [person, technology, mission, organization, location]\\nText:\\n```\\nwhile Alex clenched his jaw, the buzz of frustration dull against the backdrop of Taylor's authoritarian certainty. It was this competitive undercurrent that kept him alert, the sense that his and Jordan's shared commitment to discovery was an unspoken rebellion against Cruz's narrowing vision of control and order.\\n\\nThen Taylor did something unexpected. They paused beside Jordan and, for a moment, observed the device with something akin to reverence. \\\"If this tech can be understood...\\\" Taylor said, their voice quieter, \\\"It could change the game for us. For all of us.\\\"\\n\\nThe underlying dismissal earlier seemed to falter, replaced by a glimpse of reluctant respect for the gravity of what lay in their hands. Jordan looked up, and for a fleeting heartbeat, their eyes locked with Taylor's, a wordless clash of wills softening into an uneasy truce.\\n\\nIt was a small transformation, barely perceptible, but one that Alex noted with an inward nod. They had all been brought here by different paths\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"Alex\\\"<|>\\\"person\\\"<|>\\\"Alex is a character who experiences frustration and is observant of the dynamics among other characters.\\\")##\\n(\\\"entity\\\"<|>\\\"Taylor\\\"<|>\\\"person\\\"<|>\\\"Taylor is portrayed with authoritarian certainty and shows a moment of reverence towards a device, indicating a change in perspective.\\\")##\\n(\\\"entity\\\"<|>\\\"Jordan\\\"<|>\\\"person\\\"<|>\\\"Jordan shares a commitment to discovery and has a significant interaction with Taylor regarding a device.\\\")##\\n(\\\"entity\\\"<|>\\\"Cruz\\\"<|>\\\"person\\\"<|>\\\"Cruz is associated with a vision of control and order, influencing the dynamics among other characters.\\\")##\\n(\\\"entity\\\"<|>\\\"The Device\\\"<|>\\\"technology\\\"<|>\\\"The Device is central to the story, with potential game-changing implications, and is revered by Taylor.\\\")##\\n(\\\"relationship\\\"<|>\\\"Alex\\\"<|>\\\"Taylor\\\"<|>\\\"Alex is affected by Taylor's authoritarian certainty and observes changes in Taylor's attitude towards the device.\\\"<|>\\\"power dynamics, perspective shift\\\"<|>7)##\\n(\\\"relationship\\\"<|>\\\"Alex\\\"<|>\\\"Jordan\\\"<|>\\\"Alex and Jordan share a commitment to discovery, which contrasts with Cruz's vision.\\\"<|>\\\"shared goals, rebellion\\\"<|>6)##\\n(\\\"relationship\\\"<|>\\\"Taylor\\\"<|>\\\"Jordan\\\"<|>\\\"Taylor and Jordan interact directly regarding the device, leading to a moment of mutual respect and an uneasy truce.\\\"<|>\\\"conflict resolution, mutual respect\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Jordan\\\"<|>\\\"Cruz\\\"<|>\\\"Jordan's commitment to discovery is in rebellion against Cruz's vision of control and order.\\\"<|>\\\"ideological conflict, rebellion\\\"<|>5)##\\n(\\\"relationship\\\"<|>\\\"Taylor\\\"<|>\\\"The Device\\\"<|>\\\"Taylor shows reverence towards the device, indicating its importance and potential impact.\\\"<|>\\\"reverence, technological significance\\\"<|>9)##\\n(\\\"content_keywords\\\"<|>\\\"power dynamics, ideological conflict, discovery, rebellion\\\")<|COMPLETE|>\\n#############################\\nExample 2:\\n\\nEntity_types: [company, index, commodity, market_trend, economic_policy, biological]\\nText:\\n```\\nStock markets faced a sharp downturn today as tech giants saw significant declines, with the Global Tech Index dropping by 3.4% in midday trading. Analysts attribute the selloff to investor concerns over rising interest rates and regulatory uncertainty.\\n\\nAmong the hardest hit, Nexon Technologies saw its stock plummet by 7.8% after reporting lower-than-expected quarterly earnings. In contrast, Omega Energy posted a modest 2.1% gain, driven by rising oil prices.\\n\\nMeanwhile, commodity markets reflected a mixed sentiment. Gold futures rose by 1.5%, reaching $2,080 per ounce, as investors sought safe-haven assets. Crude oil prices continued their rally, climbing to $87.60 per barrel, supported by supply constraints and strong demand.\\n\\nFinancial experts are closely watching the Federal Reserve's next move, as speculation grows over potential rate hikes. The upcoming policy announcement is expected to influence investor confidence and overall market stability.\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"Global Tech Index\\\"<|>\\\"index\\\"<|>\\\"The Global Tech Index tracks the performance of major technology stocks and experienced a 3.4% decline today.\\\")##\\n(\\\"entity\\\"<|>\\\"Nexon Technologies\\\"<|>\\\"company\\\"<|>\\\"Nexon Technologies is a tech company that saw its stock decline by 7.8% after disappointing earnings.\\\")##\\n(\\\"entity\\\"<|>\\\"Omega Energy\\\"<|>\\\"company\\\"<|>\\\"Omega Energy is an energy company that gained 2.1% in stock value due to rising oil prices.\\\")##\\n(\\\"entity\\\"<|>\\\"Gold Futures\\\"<|>\\\"commodity\\\"<|>\\\"Gold futures rose by 1.5%, indicating increased investor interest in safe-haven assets.\\\")##\\n(\\\"entity\\\"<|>\\\"Crude Oil\\\"<|>\\\"commodity\\\"<|>\\\"Crude oil prices rose to $87.60 per barrel due to supply constraints and strong demand.\\\")##\\n(\\\"entity\\\"<|>\\\"Market Selloff\\\"<|>\\\"market_trend\\\"<|>\\\"Market selloff refers to the significant decline in stock values due to investor concerns over interest rates and regulations.\\\")##\\n(\\\"entity\\\"<|>\\\"Federal Reserve Policy Announcement\\\"<|>\\\"economic_policy\\\"<|>\\\"The Federal Reserve's upcoming policy announcement is expected to impact investor confidence and market stability.\\\")##\\n(\\\"relationship\\\"<|>\\\"Global Tech Index\\\"<|>\\\"Market Selloff\\\"<|>\\\"The decline in the Global Tech Index is part of the broader market selloff driven by investor concerns.\\\"<|>\\\"market performance, investor sentiment\\\"<|>9)##\\n(\\\"relationship\\\"<|>\\\"Nexon Technologies\\\"<|>\\\"Global Tech Index\\\"<|>\\\"Nexon Technologies' stock decline contributed to the overall drop in the Global Tech Index.\\\"<|>\\\"company impact, index movement\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Gold Futures\\\"<|>\\\"Market Selloff\\\"<|>\\\"Gold prices rose as investors sought safe-haven assets during the market selloff.\\\"<|>\\\"market reaction, safe-haven investment\\\"<|>10)##\\n(\\\"relationship\\\"<|>\\\"Federal Reserve Policy Announcement\\\"<|>\\\"Market Selloff\\\"<|>\\\"Speculation over Federal Reserve policy changes contributed to market volatility and investor selloff.\\\"<|>\\\"interest rate impact, financial regulation\\\"<|>7)##\\n(\\\"content_keywords\\\"<|>\\\"market downturn, investor sentiment, commodities, Federal Reserve, stock performance\\\")<|COMPLETE|>\\n#############################\\nExample 3:\\n\\nEntity_types: [economic_policy, athlete, event, location, record, organization, equipment]\\nText:\\n```\\nAt the World Athletics Championship in Tokyo, Noah Carter broke the 100m sprint record using cutting-edge carbon-fiber spikes.\\n```\\n\\nOutput:\\n(\\\"entity\\\"<|>\\\"World Athletics Championship\\\"<|>\\\"event\\\"<|>\\\"The World Athletics Championship is a global sports competition featuring top athletes in track and field.\\\")##\\n(\\\"entity\\\"<|>\\\"Tokyo\\\"<|>\\\"location\\\"<|>\\\"Tokyo is the host city of the World Athletics Championship.\\\")##\\n(\\\"entity\\\"<|>\\\"Noah Carter\\\"<|>\\\"athlete\\\"<|>\\\"Noah Carter is a sprinter who set a new record in the 100m sprint at the World Athletics Championship.\\\")##\\n(\\\"entity\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"record\\\"<|>\\\"The 100m sprint record is a benchmark in athletics, recently broken by Noah Carter.\\\")##\\n(\\\"entity\\\"<|>\\\"Carbon-Fiber Spikes\\\"<|>\\\"equipment\\\"<|>\\\"Carbon-fiber spikes are advanced sprinting shoes that provide enhanced speed and traction.\\\")##\\n(\\\"entity\\\"<|>\\\"World Athletics Federation\\\"<|>\\\"organization\\\"<|>\\\"The World Athletics Federation is the governing body overseeing the World Athletics Championship and record validations.\\\")##\\n(\\\"relationship\\\"<|>\\\"World Athletics Championship\\\"<|>\\\"Tokyo\\\"<|>\\\"The World Athletics Championship is being hosted in Tokyo.\\\"<|>\\\"event location, international competition\\\"<|>8)##\\n(\\\"relationship\\\"<|>\\\"Noah Carter\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"Noah Carter set a new 100m sprint record at the championship.\\\"<|>\\\"athlete achievement, record-breaking\\\"<|>10)##\\n(\\\"relationship\\\"<|>\\\"Noah Carter\\\"<|>\\\"Carbon-Fiber Spikes\\\"<|>\\\"Noah Carter used carbon-fiber spikes to enhance performance during the race.\\\"<|>\\\"athletic equipment, performance boost\\\"<|>7)##\\n(\\\"relationship\\\"<|>\\\"World Athletics Federation\\\"<|>\\\"100m Sprint Record\\\"<|>\\\"The World Athletics Federation is responsible for validating and recognizing new sprint records.\\\"<|>\\\"sports regulation, record certification\\\"<|>9)##\\n(\\\"content_keywords\\\"<|>\\\"athletics, sprinting, record-breaking, sports technology, competition\\\")<|COMPLETE|>\\n#############################\\n\\n#############################\\n---Real Data---\\n######################\\nEntity_types: [organization,person,geo,event,category]\\nText:\\n硝酸光照分解的方程式\\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$\\n######################\\nOutput:\"}, {\"role\": \"assistant\", \"content\": \"(\\\"entity\\\"<|>\\\"硝酸\\\"<|>\\\"category\\\"<|>\\\"硝酸是一种化学物质，化学式为HNO₃，在光照或加热条件下会分解。\\\")## \\n(\\\"entity\\\"<|>\\\"二氧化氮\\\"<|>\\\"category\\\"<|>\\\"二氧化氮是硝酸分解的产物之一，化学式为NO₂，以气体形式释放。\\\")## \\n(\\\"entity\\\"<|>\\\"氧气\\\"<|>\\\"category\\\"<|>\\\"氧气是硝酸分解的产物之一，化学式为O₂，以气体形式释放。\\\")## \\n(\\\"entity\\\"<|>\\\"水\\\"<|>\\\"category\\\"<|>\\\"水是硝酸分解的产物之一，化学式为H₂O。\\\")## \\n(\\\"entity\\\"<|>\\\"硝酸分解反应\\\"<|>\\\"event\\\"<|>\\\"硝酸在光照或加热条件下分解为二氧化氮、氧气和水，是一种典型的化学分解反应。\\\")## \\n(\\\"relationship\\\"<|>\\\"硝酸\\\"<|>\\\"硝酸分解反应\\\"<|>\\\"硝酸是分解反应的反应物，在光照或加热条件下发生分解。\\\"<|>\\\"化学反应, 物质转化\\\"<|>9)## \\n(\\\"relationship\\\"<|>\\\"硝酸分解反应\\\"<|>\\\"二氧化氮\\\"<|>\\\"硝酸分解反应生成二氧化氮作为产物之一。\\\"<|>\\\"化学产物, 气体释放\\\"<|>8)## \\n(\\\"relationship\\\"<|>\\\"硝酸分解反应\\\"<|>\\\"氧气\\\"<|>\\\"硝酸分解反应生成氧气作为产物之一。\\\"<|>\\\"化学产物, 气体释放\\\"<|>8)## \\n(\\\"relationship\\\"<|>\\\"硝酸分解反应\\\"<|>\\\"水\\\"<|>\\\"硝酸分解反应生成水作为产物之一。\\\"<|>\\\"化学产物, 液体生成\\\"<|>7)## \\n(\\\"content_keywords\\\"<|>\\\"化学分解, 硝酸, 反应方程式, 光照条件\\\")<|COMPLETE|>\"}]\nMANY entities and relationships were missed in the last extraction.\n\n---Remember Steps---\n\n1. Identify all entities. For each identified entity, extract the following information:\n- entity_name: Name of the entity, use same language as input text. If English, capitalized the name.\n- entity_type: One of the following types: [organization,person,geo,event,category]\n- entity_description: Comprehensive description of the entity's attributes and activities\nFormat each entity as (\"entity\"<|><|><|>)\n\n2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.\nFor each pair of related entities, extract the following information:\n- source_entity: name of the source entity, as identified in step 1\n- target_entity: name of the target entity, as identified in step 1\n- relationship_description: explanation as to why you think the source entity and the target entity are related to each other\n- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity\n- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details\nFormat each relationship as (\"relationship\"<|><|><|><|><|>)\n\n3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.\nFormat the content-level key words as (\"content_keywords\"<|>)\n\n4. Return output in English as a single list of all the entities and relationships identified in steps 1 and 2. Use **##** as the list delimiter.\n\n5. When finished, output <|COMPLETE|>\n\n---Output---\n\nAdd them below using the same format:"
}
}
}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/kv_store_text_chunks.json b/dsLightRag/Topic/Chemistry/kv_store_text_chunks.json
new file mode 100644
index 00000000..423e3b48
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/kv_store_text_chunks.json
@@ -0,0 +1,9 @@
+{
+ "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6": {
+ "tokens": 69,
+ "content": "硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$",
+ "chunk_order_index": 0,
+ "full_doc_id": "doc-fa4cbbef47ac19e90c1a1de96f1ce2f6",
+ "file_path": "unknown_source"
+ }
+}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/vdb_chunks.json b/dsLightRag/Topic/Chemistry/vdb_chunks.json
new file mode 100644
index 00000000..70811ca3
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/vdb_chunks.json
@@ -0,0 +1 @@
+{"embedding_dim": 1024, "data": [{"__id__": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "__created_at__": 1752042051, "content": "硝酸光照分解的方程式\n$$ 4HNO_{ 3 } begin{array} {} {underline{ Δ }} 或光照 end{array} 4NO_{ 2 } ↑+O_{ 2 } ↑+2H_{ 2 } O $$", "full_doc_id": "doc-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}], "matrix": "w+DFPOpKAT0eHdq8N2yhvKj3tbyWQh+9v0a2PE27ND3Jx9M82S/su+rKCr0xhQC9w+BFu10jOrzP4Q09sSsvPWQKorsjt1a8Sm7JPOuXuLwFgdu8cNjQPMh6VTwhakU9eAy3PNjiNLy6rEy8QzoXvGtxEz1OCEY8lo98vOSwPb1cI2C9rMQEvRq2iTwLm4I8U9UBvRbpOr3R+/K8CM7sO7PFdz27rDm9eL8lPbwsHb1XPL88pF1MuSqemDzaLzO9zRQGvaIQ9Lzy/gO9qURau7gSFz3iY9I75/3OvH2moLtxWI69AOfxu0I6vbzWlba8JQSvu9NI8Tz9TDy9XnBeu/TLCzsqnqs8az5nPRPPDj35sr+8l49WPLAr1bxtPi496UonvPTLi7x1v169WYmquyuehTypRO28B87/PDa5/jwjBPs8YHAlvMCT7bw5ORY8b9hQuyw4dD3NYeM8VjxlPMh6QjxJbu+8Z9cDvUkhpbmrRCG9ARqLvKyRRTu5Xzu9KZ4+vfJ+jTxmV7O86kqBuymePrsd0LU8zmG9PNRIuDzR+1+9O1NVu+3kIzovhTm82S/ZO3El4rxa1uE8zRQGPIYn9zy2ElA99Bjpuz2gZruDjS69lkIfvZZCsjvYlZC9c3JgPBScT71c1pU9ohAoPO3kozwKGzK8jo6JPAobMrttvhG9XVYMvMGTNLz8f4484mM/vfL+gzyukTK8l8KCPJKojzzwsQU8JgQJPaVdgL1eox09mNznu0tuIzwd0LW8hNpSPXXyir0OtUG8Ve9AvADncbv2Zfq7kahbvCvr4jzS+188Ibf8PFEIjbpti1I95v3hOw81EjzR+3K9X3BLvUWHFb15DJE8bYtlvKWqXb2yeNO79piTvUDtUTs1bO08LOspvD6g5rzqSoE93vyBO+WwKjsTnGK7kvXsvFBV6jxaiZc9MtK3PH2mMzxToq86sXjmvFKi1byDjZu8r14Uvb35Sj39TDw90/umvDMfXLxUIoA73cnoPN/Jibz9TOK8OTkDvYFAMD3Kx60850rzvDdsoTz0S4K8ivQMvc/hDb17WTU7AZoUPZvciLyQWxG9bT6bugsbHzxppB69jg4mvVqJPbwBmgG9mtwuuydRLb1p8dW8AjTwPCdR07wB58s8EQLAuw3oE71WPFI8XFYMvRICLbxOCMY8i8HNO+pKlDzyy1c9pyobvZ/2DrziY1I9QO1RPSmePjtxJXW90vvfu8PgsjyMDl+90ftyPY8OAL1lCg+98H5ZPRwDiDzoSmC97BcJvQ3oAL037Bc9xmADPXW/3ry9+XA8vkbcu97JVTwFNCS9nnYrvbXFKz2WQjI7sN4KvOYwjj1Dh2E9Ek++vEtutrw5Bte7fKZGvcLg2LzjsPY8LGuNPUCgGj15DCQ9jg4mPSqeK7xcI2A8Nrl+PSdRwDs1bFo9NB82PdsvxjyvXpS78LEYPWG93Ly6rEw7XnBxO97JQjzpSro99RjDPEkhpTwgati8MIWmPM6u9LvxMY89/P+qvU0If72wXoE8I7fDOga0GroUnDy8MIUmPFi8Dz3ELX28xOCfu5L1bDyqRMe7G4Mkvm0+rryhwxY7sF4BPVzWzroqHo88sXj5vOf9zrzVSJK9xi0LvRq2ib2Ojgm9ohD0PKWq3bytERa9X3BLPKtEjrzU+4A8B87/PGiksbxlihi8isFgPHcM3TzC4Ni8tcXRu+j9Aj3XFRo7WYnQOP5Mqbw2uX66UIiWvW2L5bz1GGk8kvX/uxbp4DxzJQM97BccvUvumbvoSs081xWavBc2cj2KdBY9CU6EvHgMyrqUQn68ohC7PJbCFTxQVdc8UtUUveNjrLweUAY9dnIBvFSiCbzu5CM8faYgvQjO2Ts/IBE9GDZMPcPgMr0QAtM6DeiTPPCxBb0Fgcg8f/MevTxTQrxEh/Q6q0QhPO7kI7xLbjY9/kzPvOqXyzzE4Aw9avGcPGQKtbzfFme9AuclPTCFk71fcMu8hA2SPaIQ4b2EjYg84mPSOzVs7Tsgatg8dXInu/qymbx+pg29ZlcgPFKi1Tw8oHk+/UxPPe3kozwqnhi92eIhPFBV6rxDuo08e6bsO20+iLxeIyc89RhDve3kIz1W74e7eL8lvAxosLuhwxY98n4gO7hfzjxp8Wg9iCeFuspHkblS1RQ7Tbu0PIp0gzx5DBG95LC9OzSfmbs2bLQ8wuB+O+lKOr2qRMe8g41BPLgShLxJbm88sXj5OgsbDDsYNsy8IGrYtyvrPD3D4MW89EuCO/3/hDrOYb27uqzfO9kvfzyT9ca8/kxPPB4dR73sl5I9qUTtvFKiaDyIJxi8JbeKuyhRmrzAk1o7cdiEvBbpOr1hvTY8WYk9vQI08DyCjWe8J1HTO1bvBzyrkWu91PsAvFc8v7uODqa7lPUzvalEWj04uUU9P6CHPDQfozxCOj28X3A4PW/Y4zsqnpg81pW2O/r/Yz04uUW8EU/kvHW/Xr1Lu+071+JaPOJj0jocgzc8s3gtvBWcljsz0hG8ciW8Of/MDLttPq68yscaPOPjj7zuMVu8ZAqiOwxosDzfFuc6yXqcu7uspr2w3oo9j1vKPESHTrshakW8zmHQuiUErz2NDjm9kvV/vLF4+TtSolW5K54FvD1THL0/7fc8Z1cNu2+LBj00HzY8faYgPR4d7buqRMc8Hx0hvW0+CD1gcKW8Kh4PvPQY1rpRovs5NGxtO2WKhbz0S4K8UFV9vChRmjzRrpU9GGkLvRk2pryDjUG9PVOcO6Nd3zvaL7M8q0QhPU27obwOtdQ8ciWpPOzk3DrXlRC76koBvMQtfb1YvI88QO2+PO9+/zxlV9m82eKhu+4x2zyrRKE87zE1vL5GXD0s6xa99MuLPJV1BL1lCg+7CRvYvN/Jib1opJ68SSGSuvTLHjyBQDC97uQQPYzBlDz+TCm6vfk3PT1TnD3Bk7Q8dnIBvVOiLzygw6k715UjvToGxDwUnE891PsTvB4dx7yxKy+83snCuxACeT2JdCk923x9PHFYDj1npNc7WDyZO6IQuzzTewq9d7/LvMITmD0onnc5Hh3HvKlE2j0B50u8CM7ZvF9wSz0c0Mi8zmE9PWtxAL0IG348WYkqvMCTWj2wXoE8BbQHPUu77Tw8Uy+9VjxlvWK9ozwgnYS8VKIJvOWwqroENCQ8lUJYvQcBBr1Eh067A2cJvfHL/bzFLUQ9pV0APYxBi7wlBC+9cyWDPALnJbww0vC8S+4ZvUu77buQqO48WgkOvdL7TL3TSN673XyLvPJ+jbvUSDg7Yr2jO6RdzDw5OYM81pVJPSdRwDxFB4w89EsCu45b8LvkY4a6BDS3u+8xtTzfya86jEELvcLg/jzXFQe9uV+oPPiy+DyCjXq6xi0LvRXp87xDOqo8/UzPuv1MYjsr6zw8YL3vujAFHTsHzv+8E0+YvPmyUrxdI7o8AuclPcwUrLzC4Ou7dz+JvWBwpTwkNwE86ErNu3gMt7x8ptm8SNSAO918izwPAua8VjxSvezkyTw4bA48dz8cveh9DD1dI828cdgXvW/YUDwQAvk8/Uz1vBRPhbsFgUi8f/MevbTF9zxFh5U8c6UMvbqsTDy8+d28b9hQvacqiD1RVZ48eAzKu93J+7wnUcA5RoeCvMDGhrqedtG8j1tKvcIThbziY1K9K56FvL9GSb09U5w88H5sO047hbqmqsq8rMSEO8/hjb1XPD+9BYFIPJKoDz0s6088fKZZPXHYF7yTqA+8GjYTvEOH9Ly5X+G8d7+SvHa/8bvqyoo7BYFuPAsbnzyQWyS8afFVvW6Lvzw3bDS7ChvFvLIrCb1x2AS8pqo3PcDGBr3ql0s8Auc4valEbT3OYSq93fwUPMd6Vb3rl7g9P6AtvKlE7Tzu5BC4oxCCvB5QGbuOjgm7LTjOuZop+TwqHg+9dXKUvByDET0y0iQ8+rIsvOqXSzypd5k8Aue4PAKaAbwz0pG7fFk1vXNy4LzwMY+7nCkavQW0hz2n91s8K+tiPAGagbu8rBO8v0Y2vUbUTDniY/i7PVOJu5GoNb3lsKo8k/VZO7lfuzv7soa8g9p4Ov5MKbzpSie7mI8wvSG3/Lt/87E8JQQvvbR4hzww0nA8Mx9JPXIlPLytkdi81pXJvCxrDTg/7fe7n8P1vWDwmzxGh4K7KZ73Ok8IM7zoSmA8kajuu2txgDuAQEM7avHCvB8dIbwaNgA7kNsHPB3QtbzOrvQ73cnoOp0pB7yMwYE8UtWUPMPgRT1G1Ew7AZqBvILAkzyT9dm8BwEGO+uXODya3ME76H2MPPhlCDxpJJW7gUAwPdwvoDyD2vg7RIc7PNuvljxV7y08jMEUPJVCWLxmVzO88LEFPKl3Bj2vXhQ8dwzdvBg2TLwW6c27txKquTDS8Lz8/yq9xi2xu/iyZbzWlba8qPe1OxJPPr0cgyQ8d7/LvCzrqTyp90i9zZQPvcTgjL2t3mm8MlIbvSLqAjxEhzu96pdevU8IILw8Uy88+LL4vAjOWT1Mu8e700hevGBwkrytkZ8965c4uQ61Lr2UQv66LDj0Oxk2JrxZieO7CAGGvedKczzwsQW9OwaePJP12byRqG475/3hPNN7Cr0OtS69H2p+PKpEtLz7/70842MsvZL17LyvK/u8cNiqvDLSN70x0t08sCtCu32mID0ag0q7WYmqu45b8DwZtpy8UAiNvGI9mjzn/bs76pdLPE27oTws6ym8N7lrPYgnGLzfyS88yhT4u9Gugrw0HzY96Uq6u9aVyTyWj+k7HAOIvOIWCDwLGx+8IuoVvL9GybxWPNK7hI2IuwobxTx/87G8PFPCu//MDL3XFYe8sCtVPZ7D9bxQiBY8GjYTPaaqyjwJG1g8Wom9PNniDr3yy9c8GDZMveOw9rsBmhS5hdqsuyqemDupdwa8mI+dOz/tZLwTzw49afFVPGG93DsnUVO8FulgOx4dxzy0xeS8htqZPUHtGL0FNBE9HNDIvAobsr2jkAs8Qjo9PZR1F7zXlTa9wuD+ufjlET2fdoW8RYcVPdniobymqje7pardupspZjzn/ag8A+eSPLcSqrt7WSK9z650PQLnODxU79M8ZFdsvJBbET27rLk7uJINPT+gBz2WQh89tcXRPMnHwDzIepw9HNDIPEE6drxMu0c9UqLVO6aqSryukTI8Mx/cvCLqAjyqRLQ8wZPHPJDbBz1dI7o8yXqvO8BGozzwsYW8vKy5ujuGlLxlV0a7/Uy8O/QYab3Iehw9aPH7u8ITmLos66k8KFEHvcPgxbzyy1c8nsP1O9niIbxZiVC96H2MPNuvAz2yeFM97eQ2vYcnvjxUopw8gEBDPMKTIT2T9Vm87zG1vL75kbxMu9o8avEvvHumbDwRAhq9uV+7vCO3Q7p7pv+700hLPBECmjyDja68TLvHPHIlvDzcfLE8Vzy/OYXav7vE4J88OTmWPA=="}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/vdb_entities.json b/dsLightRag/Topic/Chemistry/vdb_entities.json
new file mode 100644
index 00000000..71041ffa
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/vdb_entities.json
@@ -0,0 +1 @@
+{"embedding_dim": 1024, "data": [{"__id__": "ent-44635b939a0dac857d1d84583d9cdbfc", "__created_at__": 1752042117, "entity_name": "硝酸", "content": "硝酸\n硝酸是一种化学物质，化学式为HNO₃，在光照或加热条件下会分解。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-af78119e75a899a37b59c6d3cdf9bd8f", "__created_at__": 1752042117, "entity_name": "二氧化氮", "content": "二氧化氮\n二氧化氮是硝酸分解的产物之一，化学式为NO₂，以气体形式释放。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-5efee68823291bc4ac21479758bde4c4", "__created_at__": 1752042117, "entity_name": "氧气", "content": "氧气\n氧气是硝酸分解的产物之一，化学式为O₂，以气体形式释放。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-eab619fba24a1ea828eebee4f54a138f", "__created_at__": 1752042117, "entity_name": "水", "content": "水\n水是硝酸分解的产物之一，化学式为H₂O。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-a3044e828e36bae4abffcc851d029284", "__created_at__": 1752042117, "entity_name": "硝酸分解反应", "content": "硝酸分解反应\n硝酸在光照或加热条件下分解为二氧化氮、氧气和水，是一种典型的化学分解反应。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-05eed95990366a15fbe452afebe6571c", "__created_at__": 1752042117, "entity_name": "光照条件", "content": "光照条件\n光照是引发硝酸分解反应的重要外部条件之一。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-3423dcbeed57430a92f658b80352b83d", "__created_at__": 1752042117, "entity_name": "加热条件", "content": "加热条件\n加热是引发硝酸分解反应的另一种重要外部条件。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-5694ce8668abbda7a6c7164c38e7df98", "__created_at__": 1752042117, "entity_name": "化学方程式", "content": "化学方程式\n描述硝酸分解反应过程的符号表示：4HNO₃→4NO₂↑+O₂↑+2H₂O。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "ent-84e13277c9299adab2a0ebb7c4450a7e", "__created_at__": 1752042117, "entity_name": "分解反应", "content": "分解反应\n一种化学反应类型，指单一化合物分解为两种或多种较简单物质。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}], "matrix": "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"}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Chemistry/vdb_relationships.json b/dsLightRag/Topic/Chemistry/vdb_relationships.json
new file mode 100644
index 00000000..e7272611
--- /dev/null
+++ b/dsLightRag/Topic/Chemistry/vdb_relationships.json
@@ -0,0 +1 @@
+{"embedding_dim": 1024, "data": [{"__id__": "rel-3553ef062eb947a3f8d47270b471ca82", "__created_at__": 1752042117, "src_id": "硝酸", "tgt_id": "硝酸分解反应", "content": "硝酸\t硝酸分解反应\n化学反应,物质转化\n硝酸是分解反应的反应物，在光照或加热条件下发生分解。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-dd48c5fab81d1ec4c0f82270285f8bfd", "__created_at__": 1752042117, "src_id": "二氧化氮", "tgt_id": "硝酸分解反应", "content": "二氧化氮\t硝酸分解反应\n化学产物,气体释放\n硝酸分解反应生成二氧化氮作为产物之一。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-82eb0feccb2049747fee4373178a7025", "__created_at__": 1752042117, "src_id": "氧气", "tgt_id": "硝酸分解反应", "content": "氧气\t硝酸分解反应\n化学产物,气体释放\n硝酸分解反应生成氧气作为产物之一。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-b7c79e733bc95455eb2857e5c93b0f67", "__created_at__": 1752042117, "src_id": "水", "tgt_id": "硝酸分解反应", "content": "水\t硝酸分解反应\n化学产物,液体生成\n硝酸分解反应生成水作为产物之一。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-6b443b3a80386849e145e184d7723fc2", "__created_at__": 1752042117, "src_id": "二氧化氮", "tgt_id": "硝酸", "content": "二氧化氮\t硝酸\n产物生成,化学反应\n硝酸分解产生二氧化氮作为主要产物。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-5e16b08731bc1c12e2d2e6b6c4db5069", "__created_at__": 1752042117, "src_id": "氧气", "tgt_id": "硝酸", "content": "氧气\t硝酸\n化学反应,气体生成\n硝酸分解产生氧气作为副产物。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-3ff279b0a2ca9afae4202b9865145b2e", "__created_at__": 1752042117, "src_id": "水", "tgt_id": "硝酸", "content": "水\t硝酸\n化学反应,液体生成\n硝酸分解产生水作为副产物。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-b49a2a1b1a28061f37be7040ed71ae2f", "__created_at__": 1752042117, "src_id": "光照条件", "tgt_id": "硝酸", "content": "光照条件\t硝酸\n反应条件,能量输入\n光照是引发硝酸分解的重要条件之一。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-6afe55e56105d7018fbe22c1f5226e18", "__created_at__": 1752042117, "src_id": "加热条件", "tgt_id": "硝酸", "content": "加热条件\t硝酸\n反应条件,能量输入\n加热是引发硝酸分解的另一种重要条件。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-46f63ffdeca52f9591cf12a622f8afd3", "__created_at__": 1752042117, "src_id": "分解反应", "tgt_id": "硝酸", "content": "分解反应\t硝酸\n化学变化,反应类型\n硝酸的分解是典型的分解反应实例。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-02bf4559123fd82153338dd6677d55b7", "__created_at__": 1752042117, "src_id": "化学方程式", "tgt_id": "硝酸分解反应", "content": "化学方程式\t硝酸分解反应\n反应描述,符号表示\n化学方程式准确描述了硝酸分解的反应过程。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-cacd0103bbcde19a505cac8c90f8bd79", "__created_at__": 1752042117, "src_id": "二氧化氮", "tgt_id": "氧气", "content": "二氧化氮\t氧气\n共同产物,气体释放\n两者都是硝酸分解的气态产物。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}, {"__id__": "rel-ada04c2ffdfd9e43ccf0f82f37c0b49c", "__created_at__": 1752042117, "src_id": "光照条件", "tgt_id": "加热条件", "content": "光照条件\t加热条件\n反应条件,能量来源\n两者都是引发硝酸分解的能量输入方式。", "source_id": "chunk-fa4cbbef47ac19e90c1a1de96f1ce2f6", "file_path": "unknown_source"}], "matrix": "NRNyPef1pDwL7QK9vTC7vCIuEr32Ple8Dgz6uiYkdT15+OM86l90vB70Jr1GZe68yGlTvcLFmDwGiUY9MU6wPPFxCDzVcge9fzOMPJjearw80iC7kRDfPKUYwLqOCFK7uHLJPLFKiDuCxyy9/CYavNKaXj2hWs68AsvUu3jphr2LUm29saS9vIFsujyQvXk8QZifvOA2dr3U9VC7ymqQPHQ68jyJvwm9iJT7PA5XUjuY5ve7mTldPKcgTbtbbc+8qHu/vGB+Jr0oJTK884GivKClJj3AOYU8ctCivLz/Gbw2X4e9o9+RvKdzsrwbPsK8DVdSvADlCz07Tho8ICaFvdsWwrzjBhI9u9VIPSEEwTyPrpy8nnSFuwg+bry3EIc9coVKvCjSTLxsXYm8Q01HuhQl3jyXfCi9qimXPH5cID3KceC8z4K3PF7QzrzFKBg7fhHIPFllwjtvwIg8SRNGu+2KgryhrbO84f4EPI0iiTxN0Te9MKjlOjQT8rxMflK9KoAkvbCcMDzGrB474IHOOzCZCD3BvQs9wO6sPDYMory4xS69CpKQvOCBTjnZYF08AnGfPA/UCL2ppRA8zlEWPUT7njzZs0I9iDpGOxTKa7zsYLG8GP0GvK7niDu2OZu8xSiYvJwRhr0yJZw81e4AvAHDRzg3bmS8Kof0O5cpwzyKvwk89YkvvA1XUrytOTG8i/AqvZjeajwYiF07oteEPDrR47yDKe88a68xPbOsSr3ASOI8gRKFPdgN+Dyt7li8ZLgRPT7iur1dbgw805MOvVTyqDxefWk8JLqlvJXOULyHXIo8W8A0PD89rbxzp4491nqUu6S9zTzQ3am9j1s3vK2T5rtvwIg8aJ+XPHLXcryBbLo845n1vAg+7rtEAm89h5R7vWKGs7kA5Ys8aVQ/vTvZ8LwL7YK8oKWmvDss1jwMcQk+iOCQPHOnjjstPha5HvSmvDp+/rxEdxi8fmv9vKMQMz1f0E4967pmvaqDTLyEKqy6bxo+vDokyTugrTO8OiTJu1ldNT3HtCs9Ah66ven9sTxf0M47HGiTvPjsrrstkL482t0TPcZZOTvXehQ7B5FTvKK1wDy2F9e8wb0LvX3YmTry00q90pMOvC3jI71GAyy9sqxKPGtkWbuSvjY9Ez+VvIo7g70XNfi76EgKvUht+7xdddw8vP8ZPCIMTj2Uc1484txAvUkTxjwamHc8lSE2PVldtTu95WK733lBPYMpbz3pUBe93UATPbkYlLmuQT69RbBGPTZfBzwxHQ+9ymoQOrjFLr092i09c9ivPFT5eLsSaCk9XOoFPPxXuzwJmWC9IQRBvVM9AT1vbSM8+/xIvPB42Dw/NSA9oa0zvY+17Ly4lI08VqAAu3Aiy7zccbQ8qotZPfKAZTy69ww873BLPcWzbrsxsPI7RgMsPXPf/zz0kP88G+SMPNizQryYKgC9Q/phPa5BvjwtNom8HqFBPNT1UDzDo9Q9x4MKPelQFzwBcZ+6KXgXPEg1CjyqMGc9pGOYvQ31j7zNSQk8TX7SO5FjxDxsEfS8sykBvRG60TyUc148DHEJvVkK0Dz9uX07jUsdvhqJmjsbkac8wkESPW3pHLxaEl26XW4MvbCcML2VzlC9PeH9vPAlc73uu6O8EQ03PBI3iDwiDM68rkG+PMZZuTxFCvw8OOuaPP9vYrtQA5Y7mNcaPErI7TyH2AO9h9gDvfU2yjwVeEM7/bn9OnAiy7waPkK88y69vVPx67xHsQM8VMGHvKK1wDxkPBg9r2sPvfv9hTuRCQ89VqfQvL+TOj1H2pc96VAXvIBsurv/YAW9RgMsPQJxHz3JvLg8dY3XOk6G3zuXKcM7Qm8LvFoS3bzEUaw8dgoOvQOA/LsMT0U9Il8zPUawxrw4yVY8hHWEPE+ObL09NGM811hQvQmZYL2x9yI7m5xcu5V0GzzBxZg997uNvLZqPDwd7Bk8wDmFPIEShTzUomu91vaNPbQHvb13nfG8iDpGPBENt729i628U/l4vIIakru7guM800CpOjCZiLlIbfu8B7OXvIjv7Twnd1o+ciOIPVldNT3maRG8ZhMEPY9bt7yDfFQ8wEDVPEHrhDzNzQ+8+lb+vBfTtTx3Qzy8COS4vMdhxjrvcEs9pHL1PGYThLsqgCQ9ZqbnOnSvmzyx/vI8W8A0PdWbmzs3FK+8+EZkvErI7bwtNok7bumcOn5cIL02uby7djsvOI4AxTykaui7tK0HPDXbADzP5Pk8T4ccvFxtTzzzWA68l1MUvFldtTvG/4O8vIpwvHhtDbzqJ4M8jlr6vDcUL70/NSA9+pqGvL6S/TrSi4G7veXiu2Hg6DtqXMw70IrEvGZEJb3pslk7Q01HvR5HjDxj6HU8vIpwOyw9WT2xxgG9H6nOvBguqDwjFFs8nZWMvQtHOD23xHE9OW8hO2NDaDyEzzm8RKg5PYYBGD2SGOw8WbCaPABwYj1PLKo7Nm7kOz3h/bxSPES8t8z+u4WMbrvW9g07vjhIvCEukjyqi1m8BqsKPZ73TjsxJZw6+1c7PMcHET3lkiW9pyDNunB1MDzT7UO9fAGuO0+ObL1tPAI9JW9NvFcCwzosPVk8rpvzvBj9hj06dy69O3+7OepYJD3iNzM8TywqPIMpb7wo0kw8JhUYvSh/ZztJZis90T9sPVb6NbuSvrY8Qm+LvKK1QD2Zrga9u4JjPAarCryMS5080N2pPMe0q73bFsI80u3Dus833zxoTDI9gylvPHJ9vbzemwW9Hk7cPJmuBj0zqSI9Dao3PZrntDzxHqM88SYwPWxk2TtL0Po8k8bDuy4+Fr11jVc8A0gLPKJi2zv+sq27reZLPOZpkbso0kw927wMPJG2KT2frPa8OG+hvHXgvDxdboy8RKg5vUOoub3ZBqi77LpmuxPK67smHaW8oKUmPUx2RTtpp6S8ss6OPDOpoj0ZBRQ8QvrhvFA0tztxn4E8QOpHvc0vUrstPhY878Owuz+Ihb1MJB28ps3nOgEWrT22Yi89xCCLvDReyjxS4g48xg5hvPhG5DyjCKa6NgyivGLgaD1uEjG89z8UvOaasj2MUm28PdotvF8jND1L0Hq8QJCSPbH+8rxGuFM8VfIoPIjn4Dw2DKK8k8bDPGYTBDyfrPa8fAj+vLkn8Tw0Ztc8OneuvPWJL7pqXEy8i51FvR3DBb0eocG8TMkqvBBYj7zem4U95ZKlO9kGKLqEzzm9UIecOyYVmLxB8tS88R4jvUVdYbtg0Qs9UJb5vLY5m7x2jhS9fq8FOtlg3bpKbri7S5gJvIQqLLoqLb+7C/RSPWHg6LsTP5U8YVUSvQOA/LwwRiO90bSVvNVyBz3yeZU81vYNvdMPCDvGrJ69flygPNCKxDyblM+7kAGCOq3my7x5ni49f8bvu4aM7rtopyQ889tXvNE4HLwG3Cs8OiTJvEjAYL35wxo9l3woPXDPZTvdQJM7HcMFvQUnBL2onYM8I4kEux5HDL0vwpy8zSfFO5ABgjxst746BSeEvRWah7vKcWC9lksHPXWVZDqpIYq8y3ltvYxLnbyaQeq6nEInvVhVqLxo+Uy8M1a9PIfYAz12leQ7k2QBvX+3kjygpaa83ybcvKvevjycnNw7uJQNPWGGM7vBm0c9ABYtPLH3IjzmT9q7X00FvAg3njyXKUO9VUUOvT2HyLtuEjE7XeqFvAoWlzyQAQK8K1eQuuU/QL1fdpm8J3CKPBYtaz37ohM8ijsDPczFgrz4RuS50xcVPA0E7bxqfpC7b89lvTQLZTuREF+84jczvHdDPD1GVhG9e9CMO8asHrz0Nko81noUvb6S/bvwJfM7BCbHPOH+hL1Hbfs7p9V0vRailD12Ehs6uvcMPderNb15pX49nnQFvPLTyru0WiI8pr4KvVgslDzau8+8KNJMOzdnFD3p/bG822GavPyx8DxrCqS77LMWvQezFz09NOO8qtYxOTElnLuum3O8ShSDuZIRnL0X07W8gSHivDZuZD3Tmt4723B3PdKLAT0NeZa88nmVvMtyHbwJ7EW8KH/nvGem57ylGMC73x+MvE6GXzxB64S8HvSmulwid7wwRqM4z6wIvXv5oDs94f08mIQ1vWU8mDxefek84f4EPTp3Lr3Tkw69UuIOvf4UcDxi4Og8BTbhvZ+sdjyXMVC7tr2hvD+IhbtqCWc6FcuovKS9TTz0Nko8ybw4vafOpDtgfqY7r+8Vu5CFiLyqMSS8kiD5OwxxCTtyKli7n/9bPeyzFj0JDoq8+RaAvGn6ibzbFkK9iugdvPbz/jx3ZYA8nUInPIG/H7xuZZa8HOwZPTcUr7vpV2c8XiM0PHxjcDxx1/K68y69O0zJqrvn/PS8s2HyPLD2ZT39gQy789tXvOpfdLxwIss80JLROs3UX70zBBW9T9nEPHltjbxMJB08gb+fu46tX7y5nJq7ZfG/vL9imTwBw8e9F3mAvfupY73/Z1W8kRDfvHIq2DzuHWa94i+mvK6bczy3zH46y8zSu9WbGz3rWKQ7LT6WOzYMIr3iids88ojyPAR5LDvLzNI8aJ8XvWbxPztXXPi8o98Rvce0K72DfFQ7DPxfOuMGEr1wz+W72P6aPA+yxLyyWeW8reZLPLZiLz1lls27iZU4vVOXtrzGBtQ7MEYjvUnA4LyrAAM8jqYPu4xLnbwIPm68QesEvOn9MT3Lcp28LLICvVhVKD21af87GNvCPPWJrzx58RM9WCyUPTa5vLyWz427tbzkPIUqLL0/Pa08lSG2vIV9kTyzYfK73x8MvReAUDtnpme8bLe+OgUuVL2M+Le8FcsovEUKfDzDnAS9U0RRPQFpEr3V7gC94zezPPPb17x8rki9SMDguvoejTzDnIS77GCxPGDYW7xJG9M8DlACvRiI3byY1xo95mkRvPlHobwo0ky93HG0POH+hLuAbDo7t4wAPC3qczv2swC9g56YvLp6VjyXfCg8LDaJPSJfs7y+kv27N8HJvDCZCL3FKBi9QUU6Pe3C87wXJhu9XMhBOlq4pzsGica80JJRPKLXBL2rAIO7ZOkyvAHDRzxDoKw96bJZPHxjcLt1jVe9afoJPfDLvTwPssQ8h9gDvX6+YjzsDcw7N8HJPD004zyxxgE9X9BOPKyTZjua3yc9ICYFvMpqkDzNSQk9Lj4WPQY24brGrJ67hzK5vIMp7zuTbI48ZhOEvMP2OTyOAEW8bLe+vPv8yDyQvfm7ZZZNPEdlbry93VU8T9nEvPyx8LxQjmy8WCyUu3Y7LztWAkM84i8mvQ1XUrzPgrc8ctdyvBeBjTx5bY29nffOPBENt7pzMuU85pqyuQPTYbpKwR09coXKO8NQbz1bC408mCqAvOhIir0Aw8c86y8QvfmhVjpo+cy8THZFvAJxnzwU0vi7BdvuOYv3+rtEVVS7b20jPNZQwzyedIW6KoAku5uUz7tS6hu5WoeGO2TeGj3UFkg8Pkdlvb30gzt+KaC8QFlPvFCUtLqITpM9EOwFPGHhg7r9h1+9sKbPvGXC1rxAYEA7ctb+PHcBxDw8aBa7ZN6avCMflbs/ZzE8YNiOuiMflTxv0vY8RXYyOxoKiDylj7688GzGvDQi8rxNiTs97n8Vve1ovrxszm69hjW4vWbwBL1Dcio8KRJSPBHSxbyliE29L0aMvCkSUj3/rhy8iFUEOx/t3jytjfS8FPmCPBkIhDwL1pO8zwDWus8A1rzC0Om8cfLCO8YCILyTV0I9oIeuPFe1n7xGhpi8KjeLvYkyT7zjQ0u9iECxvFfDATyVcB09qH5zvHYPJr16KgW852AuPNksOj1Sph49PGgWvUZoUDzUNBA6H+ZtPek9+bzE2+K7V64uuVa6jLt0Cx49/ZXBvKGXFDzNHJo9JhwsvfJ+MLzM/M07D+MQPI0637xv4Ni5/YBuPIwvZj1auac85lW1vF+zVbv3cW27sr+qO4kd/LxixT+8fzmGvbjlgr0uNiY6A4n+O5l9mrzWIUE96UvbPEWLhTx+KSC9wtdavB4Jo7tcy5G6Pk7Wu8cShjxLYn68KQthPE106DxObfe7Z+IiPa2ix7uIR6K8HvTPuUNP9bzhMeG7/66cu7fVHLpgrOS8k1DRPF+6Rjxdmvo81j0FvF+z1TvufxU8aLj8uyEGuriGQ5o8MSVbu5E3dr1Dcio9Gew/Oq2U5TyTQu+8OE03PU2QLD0hGw2962Q2PQ3DRD30iSk96T15ugWwuzyTXjO9X7NVPBCyeb3XP4k8tdOYvMj/truHU4C7GuVOPKuQXTzyfjC9x+ZbPbe5WLqGLse6j18YvV/Bt7yvrcC8YrDsPOA/Qzyyo2a8XZr6OzQp47tGhpi8yupjPUePDb2mc/q8j0zJPP6smLwPx0y9Z81PvBLZtjtYi3k8paaVPbWg/TyGQ5o8VLEXPKuC+zsO6gG90ysbvH//+buEI049U4paPYEfRr3WPQU8lXeOO+hnnzqllq+8giq/vMEBgTx5BUw9HP4pPXDywr34pAg8hUoLO2zjQbxQqws8qpfOPD5HZTyyuDk8vchZPP+unDtGhpg8pnrrO3TvWb2basu7eRqfvG/uurzuTHq9YdoSvaWBXLy02AW995QiPUdlZ7uyvyq9YrBsvMH6D70fGQm8BaJZPY5BUDwuNqY9/ZXBPKqzEr109ko96HWBvLfHujxGWu475WOXPLCRfD3mR1M9jTrfvENyKj1OdGi7ZecPvRz3OD1TtoQ7OE23vIQcXby1tdC8KQthPCMfFbwPwFu71igyPSczgzx6KgU81DQQvcff6rx5Gp88jjPuOwitUjtNkKw8iEeiPQq4S70M3wi8CJh/PBCy+bsZ8zC8aLj8O88AVjx/MpU71gxuO6N9VD0AjGc8V7yQu7rSs7vGAiA9mGbDuvuD1zuliM28jk8yvQWpSj1Xrq48paYVvF2oXDs7Ub88IyaGPbe5WDxAS226KARwvPhqfLxKhTO84EY0PL/TUr3WKDK9fimgvG78nLzJ/zY9Y9A4vScskr2hZPk8nmDxPCUhmbz6mCo9Ql3XOe19Eb5CeRs8ZcLWPPBeZLzra6c6RIIQPG/1K7wf5m292zDCvNY4GL3gWwe9AL8CvZNC77uRPuc7xgKgu6SdoDspGcO6yfhFPaWPvjw+XDi8M1OJukF3F7xSn626+p+bvM4cGr1xB5Y8PWOpPHslGDwNteK5A5DvvIM4ob3UD1e9hjW4PMHsrbzB7K07t84rPST8X7wCs6S8Plw4PbTDsrwX7yg9U3x4PQCT2LzeNMo86FLMvPZt5Txs6jI9hBxdPW3HfbuGPKm78HO3PB4XhbzWOBi8hjW4PNke2LxIbNi8LiHTPLK4OT07UT88uLJnPHz7cbrWKDK9O28HvE17Wb2ciBO9U4rau8XUcTx68Pg76GAuPbW8Qb283aw8jFsQvOh1ATsSvfI87mFNvZtcaT0L3YS9dPZKvRkBk7q50rO9jkjBvLrpijweEJS78owSPKWdILubeC08Q0/1vJNJ4Lxqw/U8gQpzPlqrRT3hXYs8MkqUPA/HTD3ZHli9k1BRO+ZORDxLlZm8S5WZu/BzN72riey8GfMwPXcfDDv7qJC84zzaPIYn1jw2Qj47JwBoPcYCIL1XvJA8XZp6O+lwFD3weig8cPJCvaiTxrzmbAy92TOrvKathrx3+tK8kWqRvOFWmjx079k7QHWTOxC5ajzwXmQ8t8e6PNMkqrs+egA9AJrJvB0OkLzH7cy6fwbrvE2Cyry9uve8Ljamu/ZtZbwkKAq9/ZVBPdtMBr2ZWGG6SZiCPGn0DDsX4UY77HsNPHLW/rx7JZi83kkdvFWqpry0yiO8oHlMuY5IQTvrZDY9Z+KivC4h07xcqNw8iVCXPFqrRb3M/E09/6erPENyKjyFQxo95mwMvcb7Lj08bwc9D9UuPaWmlTzjQ0s9fiKvPCQKQryebtO8d+zwvKSrAj2RPuc8W8mNOwjSCzxouPw84mYAvMrx1Dyomjc9iDlAvPeUojtVldM8IQY6vZVpLD26tu88S3DgO6B5zLyGLse8JBEzPU5td7y9wWi8dOjou5VprLyQYZw95GgEvN9SkjzE8DU9tNgFPQWU9zyTV0K8MDquOj1jKb0b4mW883c/PCwdyzxYxYW8XL0vPF22vrw6bYM9Pk7WvH4iLz2Ye5a81iiyPDM3xTy/6KW9KjeLPDxoFrt/DVw9DMq1PIM4obnlaoi8Yr7OvPBlVT0Fm2g8SHo6PUiInD2gjh89JwdZvMcLFTyNZAW9FNbNPLK/KrtIiJy8ZcJWPAiY/zveJui8Q0/1ux/f/Lt8+3G7/oBuPZtV+LpfukY9cxIPvW/uOjxu/Bw8eCgBvLPPkLw+VUe9jkjBOVWqJrsMw0Q8wgMFvBnzsDx+Iq+8iz3IOwWpSjwuKEQ9RmFfPIhHIr3mR1M8BZtovMP3Jr2ql048+3zmvFOD6bxNkKy9PWoaPJhfUrwU3b492RB2PUuVGTwP1a48zSGHvG3Hfbp2DyY9SpoGvS8T8bzzYmw9SV72vPqfGzx+MJE9V7wQvBz+qbzhVho9DbVivYdTgD02UCC8RmjQPMwDvzte1oo9B9AHuqFkeT21oH05AqVCvaOERb1+KSA8Q0/1PFvEoLguGuI7vbp3POJmALygjp+8Uq0Pvfh4Xr2gjp+8k1fCPVK0gDu9unc8/5lJvThGRjyQUzq91jgYvNQdObj3ogS9iSvePJBhHL0M34i8evfpvCkSUjuRPmc7iyj1uxLL1LrcIuC7SIicvCcHWT2HGfS87W+vPH4pIL3gRjS8kT5nvTtRvzv+ef08r7siPQWb6Lu33A27dAStve5hzTzuWtw7jTrfvOtIcjrcKVG9zAqwPNtFlbspElI8JBEzPfeUIjwkETO8WqvFvE172byql069UHhwPKuQ3TzZEPa7f/95O5iCB73jWB4841gePEqFM7ssQoS7O1G/vGTeGjvuTPo6F9PkvBTWTbsVz1y8taD9vB0OED0P3B+7mmpLvOhZvbzkYZM8bvycvPKTg7ztby+9lWK7vF+6xjwM3wg9Hdv0O2K3Xb0IpuG8PnOPvLW1ULy1p2491xPfPORhEzxCeZs8FcjrPFWVUzyANJk8nIiTvM3n+rvE6UQ895QivYQc3bwKv7y7qrOSO3EHlrxNe9k8M0wYvSEGOrvTMoy9IRuNvFCri7vlagg90ScTPcTbYjyANBm94SpwO+pyGDq3udi8D9wfPKWPPr0+c487/ZyyO/hq/DtYvpQ8YdoSvbjZpDqHU4C8pZ0gOqiaN7ulgVy8B8IlvN4t2Tz/rhy9DMPEO5Bxgr3M/E09xdRxuzlkjjxk0Li8RlpuPYs9yDtXtR88X7rGO3IJmryVW0o88F5kvDEsTLq3zis9W8kNvds+pLxYi/k8PWOpO62wKb2tsKk8VLgIvXLd7zzE2+I85k7EvFWVUzzgRrS9O1gwvRfa1bw2NNw8nmBxPMYCoDy1vEE92TOru0JWZrxasrY89XvHvPabE72dfLW8cxIPPBDsBb2PTEm8cxKPvHIQC72wkfw7ziMLvUFSXr3uU+s8gzihPLrEUb2JHfw8aL/tPLPWAT00KeO88F5kvST1bjvWOBg8S5WZPNcT373TD9c7JzODvE+iFjtdoeu7zyWPvEV9I7x/Bus7qpdOPCs5D70mIx07D9wfuw/AWzsDiX68gS2ovC4hUzwFtyy8WsCYPNg6HD0+R2W8mn8evV/WirzH2Hk8b/Urvft85rzcKdE8wwWJuTw1+zw2O826/66cu49fmDzhXYu8XKhcPEtpbz0hDSs7FOugPNIpl7wxHmo8k0JvvWntGzyIR6I9v9rDOx4JI7zB7K08RmhQPY1kBbxy5GC91iFBvSxChDtLfkI8vN2sPLbVHD2tsKm8A4l+vEB1E71Nl5080zKMvaKZmL3tby+9bPgUuYtSG70FsDs9v9NSvbvimbwHyRY9WJlbPOBUlrx8EEU961ZUvOZVtbmflRC9k0LvPF+zVTy0vEG84TjSPHT9O710C548fhRNvBnzsDvoUky90yQquk+bJTxGWm69i1KbvIYuRzxKk5W83ibovIk5QD3qeQk9Cs2evOBUFrvkYRO9kWwVPIMxML2TQu+8evfpPAvWk7zQICK8k1DRvJFqEb31lws9M0yYvEt+wrxk3ho9V7UfO4Efxjz/rpw8MEgQPG/g2Dxl7oC8fw3cvC02JrzWGlC9Q2u5O1B48LxSrQ88NVeRPBHgJ71Ic0k6zAO/vF2aersZ8zC8TZedvH4wEbyghy48K0AAvRzpVj0eCaO8KQvhO8LJeDyDMTC8tbVQvUBgwLwDkG892jDCO/KMEj1CeRu9k0ngPIdTgL22zqu7XMQgPUFS3rsh+Fe8urbvvNEZMbz1kBo8cQ6HPMz8TTyjdmM8fw3cvJiEC734eN48DeGMPL7vlj2ii7a8Ee4JvWTlC72OQdC85k5EvD5OVjweCaO8V8OBvQKss7uCKr87sc0MvbCR/DwL3QS90QTeukucCrw+TlY8IRuNPU106Dy3wEk7Z9TAvCT83zzE/pc8X9aKPDw87Lxj0Dg9AJPYu5BTOj36mCq8i0squ0V9I7xit107r7QxPZBaK71DXVc8cgkaO4xiAbz7rwE9HOLlPM4cGr0Q7AU8fhTNPONfD72RPuc8SGzYvCD4VzrjSjw9kGgNvRTWTT2tx4C8zQ44vJR1irw5ZA69V7Wfu2rfubu4sme881v7vOtktrzmOXE6lXAdPWzxozrGAiA8B7RDvVe1Hz37dfW82z6kO/ebE7zRJ5O7YdMhPe12ILyyo2Y9YrfdPPiNMbx0/Tu9k2WkPDZJr7tQePA6kGEcveEjfzwzRSe8S3DgO++IirzbPiQ8RIIQvFzSAj39lUE9GwUbPKiFZLyBJjc8Q2s5vFWqJry9rEs9M4BvPGMTOb36JuO8Z7e+vNMmj7wCF4U8b6KdPaJyujxSQj47q7pFvZWGKb11Bb+81mglu7pl8jwyZCc8g1iCOc/ftbtk0lS8Eb1uPLEdZ7x5TBg9XQ3EPDN3jjuhsx49m0b3vKEQS73A5QC9vy/GPPgFWL2wu3e6XzMSvS3Aob2rDhG9sjURvNzQCbdKuU68jrxVvXPks7x5R1U94i7ouzxrTrw+kZw8FboCvNzLxjsRwjG4Hq5CvEM1IjkjVwu92CdBvezYYjxeb7O7LJ8WPWxbxDsHeqa8qw4RvBW6gr2YyL+8p3gvvcywBr0kEeS7m0s6PZWGqbzt/jC9HOpjvIhZtDy73ws9Z7wBPSLw2LzK2UC8GV4Iu2NwZT2jMVa8Kn4LPEVWrTpINtS76PP4PF5vM71Rft88IggDPYp/Ar1svTM8TH2tOyExvToOP7e8uEmqu69jDjvR+/08dEYjuz0hibz2moe8xxXiuz3NvbwjUsi8X4Iau6jaHr30vn69iz6euMXYDryl8PG8qvspPX6vuTwGtsc8Gg8Ava/827xTBh29FWa3uwr9ILxC07I8ZviivCwBhjzcjyU9ibbgPBSi2DwVBEi7APE2vLOgYbs4Kbi87xr5OxhLITt/r7m7P+5IPD9QuDwHeqY8Nqa9PDECOLx6rgc9CvhdOrOlpDxUY8m8W0AEvNZj4ruFF569obOePDYDaroh9Rs8Mf10vCAjGT0RJCE9jVEFvf8xGz3WY2I9tLgLPf3Bh7wMt/k8MyNDvQFOYztwUxW9O6fvPPhsirzx3tc7ZTTEvEzfnDxdDUS6c+QzvcaXqj2+Yoa8i9yuu7F/1ryGM2a8qNXbvI1RhTx3Jso8vg47vIPxTzwswCG8B2yCvJhmUD1+TUq9jfj2vGCVgTymGwO9wDSJvcMP7bu8kIO718qUPMO3gz38rqA8qZT3PHRBYLtaLZ07Sr6RvJhmUDqR9Qq9Y3BlPRG9bj0A8Ta95KiBOuHRuzsE6Ye6FWY3uWFUnbyKdXy7m5+FPXtoYD1+r7m9buMBPJufhTt3epW8dEFgPJYE4TtZaT48sSIqO5XomDwl0H86Ln89PCOvdDlNQQy9EtWYu9Zj4rzHDIG8F9sNveW2Jb3QntG8UwHavDwOIj0UWJO7KRdZvZqH27sCEsK8ctaPO1il3zw9L607PL+ZPbM+cjwq2ze9P+5IPWFUHbwlKQ488p1zPBEfXjws/EI9h5VVPcO3g7zMsAY99eTMu+c5IDz/kwo94W/Mu3Fc9rxUGYS8uKsZvVY6jzznOSA7EGDCvG876zymEf08qZR3PDYILb1zhwe9V0izPCNXi7zcHxK8sjURPeXJjD34Chu91milvHfchDv4uxK7FsPjvKx+pDyRRJM8pmqLvGU5hzydzjQ9a/4Xu3IgVTtm+KI8He8mPVdDcDzmNF08dAB8vLXB7Lztl/489SUxPGndjLzAg5E7gdBEvBeMhT1tgZI8L9xpOyp5SLyM+PY5UwHaO1AhszvcimK94A1dvdFd7bw2A+q8QXHDPAISwry0X329FQkLPfNh0jya7g29eIN2PSgX2Tr9Xxi+BxN0u9ZjYjwaCj28CNfSOow+HjwN3Uc76Pg7vc/acrxk15e8FWY3vTPB07xb3pS8UCEzvBhLobxsuPA7A9FduxYqFj3tnEE9LFCOvO8a+be9sY68M8HTPN0oczrPQSW9umXyPOXJDD0Uoti7QLInvPMXDb01+oi9ER9evevPgTwFkPm7eIP2OwuuGD0v4ay8cVz2uAh14zzxlBK84jMrPfyuID39ymi8PHCRPIAkEL1BdgY9cWE5PdODOz198J28SPqyvIY4qTwSRay8dskdvGWR8DwabCy9A9agOX8RKT0Uolg9REgJu8udnzxr+dQ7sBQGvVHlkTxt0Bq9QRSXvNfF0bzzvv47yBXiPPXkTD36jZW8XatUO0g2VDyWRcU8EGUFPZyoZr0ciHQ9r2OOvcU1O71Asqc8UCGzvdfF0bycCtY6uQjGuzXnoTy/cCo86EwHPIl6v7w3apy804M7PdTgZz776kE9NgPqPIbWOTstXjI9n41QvRleiLuQ4qM88HzovNsHaLzjlRq9mSqvvLNDNT1k15e6zRvXOldDcDxCMF886m2SvJIDLz3meoS80KMUPMA0Cbw15yE9jV8pOzrtlrwRJKG84/cJvU3yg7zfq+07dmLrvJL+a7zcy8Y7vg67POq31zrDD+27xvmZPAINfzwBTmO8/EyxPPgKm7wShhC8Ggq9u2h22rxaLR28jf25vGv51Drcy8a8yjbtvGv5VD0s/MK8hjPmvM/acrt9ji48m0Z3PKEQyzz2Rry8LPxCvawctTvcbpq836ttvLsulDx+Ug28HUxTPRpsLL3Nviq940/zPNEAwTwN4oq9OuhTPcQnFz1KV9+6SldfPRoKvbzjT3M9toVLPajanjxRg6I80QBBPZhrkzzYIv46gHMYvZ1sxbwIdeM8sz5yuso7sDuhZJY5jV+pPPB86Luf6vw8WKoiPdTgZ7u87a88NUROPV/MX702ofo68IGrPLO4C7y734u8phsDveZ1QT3WaKU7CHomu6+ylrymGwM6Kc2TPV1hDzwDdDG75nD+POptkjyN/Tk9nArWu9+wMDzdKPO8dysNvL1PHz3F00s97N2lOxHCsTyplPc61milPd7xFL1/qvY8WKqivJ4wpDx+r7k82gyrvezYYjx7Hpu7A3QxPTah+jxNPMm7Ln89vC/hrDs8DiI9prRQO2TSVD3nOaA9XzOSPP7K6LyRoT88VScovZNlHj0tu147rZ8vvY8jCDxjEzm8egbxvCz3f7x8ys872ImwuxJAaT3NG9e71mNiPWFP2rwvf708SJ0GvCe1abzdgYG8vy/GvJDdYDxitoy8HCtIuyGOabwShpA8wxQwvK6abLusHDU9uQ2JPQDxtjzeogy9mGbQPChTerwZrRC930l+u4UXHr2N/Tm6wgaMvbVpgzuQkxu7QXHDPerPgT2FEls70FSMPGOIDzzRAMG7C1pNPHn9D72gTOy8JXNTPU2QFL2sfiS77mCgPT0vrbsjtLe84i5oPT6RHL0GVFg96Pg7OtnrnzwcMIs7LPxCPRLVmLzt/jA9Sr6RvJe6G71FuJy8I7Q3PXT3Gj3fq228X5A+POIuaDxcSWW75balu2kslbwMt/m8GmdpvO3wjD0PnOM83MvGOw+hJr1CMF888UBHvcuYXLx4iDm8VGPJvF8zEj3P3zW9P+7IvEEUF72l9TQ7vs3Wukza2byL3K47zRvXO35NSruYyD89dQqCvGFPWjwkFie9YOQJvS+EAL0oU/o82CfBPP0LTT2a7o28G8nYOys9p702A+o8ajo5O2//Sby87S88s6UkvQG1FT2R9Qq8kN1gvIUXnjypmbo7G86bvNWkxryneK+7D6EmvdxuGjzjVDY9f6r2uz9LdTik5xC9OuhTOzwOojyn2p67MQK4u34DBb0OOnS63MtGPEOSzrzhJQc7dyuNu0MwX73DtwM9SiABPHZnLr1tfM+87hEYPFuKybxN8gO9fxEpvTarALxr+dQ81mglPZjD/Dzm1zC9SyCBvFgHz7xYB0+7LVlvPK8BHzylV6S6DTGTPGo19jwLEIi4V0PwO3sem7zCVRQ7Y4iPPEbLA73tl368phF9OiIIA7xaikm9V0PwPNmcF7015yE8KnlIvQWQebxygsQ4RVFqPSyfFj10CgI85nD+vLKXADz76kG8HwvvvGNwZbzRYjC9UwYdPCs45LvQo5Q7HDALPbirGb3cjyW8OYsnvcrZQDsmMm+8b0Cuuwy8vLsqecg8OkpDva1Cg7uneC+9FWY3Pcz/jrxxw6g8H3KhvMuYXD1N8oO8a/nUPIhUcTy+Cfi8oRWOO2WRcDujNhk88v9iPM6CibyGOKm8/5MKPRwrSDs/pAO9eOqoPJH1Cr2rvwg9oBBLPCXVwrxI7A48EkWsvfP/Yr1+Uo28REgJPVXA9TwNMRM9ZNJUPYj8B7x9ieu8W4rJu+j4u7xf0SK9bjIKvTGgSLuFEtu82IkwvBHCsby87S+9UX7fut7xlLxRfl+9W94UPad4rzxPv0O91OUqPXVZCj0LEAg92ZwXvXtoYL0D1qC8is4KPDarAD1H1OS9ibZgOx1RFryMm8q75zkgvBYqlruVgWa8YVQdPHPkM7sRwjG9mMP8PKa5k7wRH148/s8rvIm7o7x1o887bjKKvOptkjxb3pQ9Kzhku7KXAL1Czu+8JpkhvHbJHb2zpSS9JBHkPHjqKLzFiYY8/EduvJaicTvWaKU863ZzvP0LTTxjdSg9IY7pPCrbtzyl8HG8fxGpPBpn6bxZab48zn1GPQqbMTuN/Tm7DLd5PLXGLz39ymi82wwrvTGgSL3iLug79MgEu+Zw/jvK3gM9lqc0PPeoK7wjUki8YrHJPFiqor0iCIO9rBfyvOq8GjxWhFS9c9/wPCE2gL22I9y840YSPbVffTtnsvu7X8xfPZjNAjxGdzg8s6UkvXcmSj06T4Y80FSMOiaZIT38qV29EoaQPP3KaLyMm0q6d3oVvUq5zjyV49W2Cv0gvQqbsbvapfg7pJiIvIY4KbybClY9E0DpPOptEr2N+Pa8wZE1vZk9ljylVyS9RVYtvaM2mTyG1jm8xxVivLzobLzwgau8umVyPfNmlbzR+/28AhJCPVQZBLxDNSI9VGNJPBbIpjwzwVM9oEzsvGFPWr2bRnc7gHOYvfMEpjsXh0K94W/Muw6TgjwSRSy9IfUbPH6vubxbjww80WIwvHHDqLsi8Ni7pVLhO7vfC73BjHI9cFMVvYYzZryv/Ns85nVBu5aicb3ltiW8c+QzPfWC3Tu8i0A9O6wyvRC0jTzyoja93qIMvVrLLT02CK27O6yyu+hMB73XyhS8vU+fPK/AOjyFF548gdDEO6wctbzgEiC9LbtePGMTOTyNWuY94/LGvDamPTzM/w69ww/tvKiLFr0oWL06zRvXvFS3lL2gTGy8kOIjO/WHIL0xVgM9YfItvZPHDbvhb8y8eqnEPFxOqD1KvhE9nslxvA172LxxvuU8ZZYzPCXVwjyV6Ji8C18QPTA+2Tuibfc85XXBOzJfZDzQo5S8VcW4vBpsLD3lGBW9U6StPNsMq7pjiI88i9yuu87RkTzLTpe8IqaTOUzfHD2Q4iO8aHbaPPP/4rwNgJs7GQo9PamZurzuERg9WihavByNt7yPgLS8Rne4vPxMsTlcTqi7jyOIOh8Qsrxt0Jq8gpQjvHtoYDw4Kbi7v3CqOmxgB72l9bQ8E975vFUnKLtD7/o7Fsimu6VXJD12yZ28vWKGPYhU8TyoN8s7qvZmvSi6rDwJNH+878KPPL8vRr2cqOa87fAMvBPe+Tv67wS82wfovK+yFju4SSo9z981PUPmmTz0Fw26RPmAPI1fKbyibfe8xdCEPfMqEz3FEyC9JGujvN7TXLweO5S8QUQjvDBReD3AxuA8r9mZu1LxAL3VURO9bklFvUuvILyLtgw8QI/rPFnbQjyRiQK8w+/9uov5J7rH36M8vaiiPF/0hTzXo0281GsRPR31Rrxbp0a9nonVu9WuLD0Cg4S9g3H6OuTsH70ZS269Ry7lvKF+9jiQAJq8C+4BvQQ1ir1bc0q8DI42Pea4I7zbO1W7bLG9PG4DeLzzQV88dxFcPGsO17zGnIi8+RTVvKgdcLxap8Y7X664u+7ghT1FOUQ6l+pbvG9yYjxm8Ji9cvOdu2UkFb0BV7W8YTRvvMKSZD26J2c7qAYkvQ26BTub8c085Y8GPavSpzwC+hu9+DEFO6YoT7x8u7Q90z/CvG9bFjz0EJU7McOUOyQ3pzx9Qeu80EqhO1H2+zzC2DG9AbROPGlFBbrFzdI79IcsvX+w1Ts10rM8+lqivLihsDxSTpq8vWLVOQC3gDyGOIO8W7kXvcFpR7wjJda8GylDveg+2rtlga4766JlvNZ6MD1gwAk84sh9O8RhGr2UIYq8RX+RvArCsjxpGba8D+DwPCyQ07w2QZ48ycLzPJxguLtGBUg9I2ujOWNYkbzXerC8u2WHvMsaEj2RzB065APsu1WjBrzSnw09TJJwO7ECtzzpZ3c7oMRDOwyONjxK+ug8eSOtuUDVuDoB+ps6zrKZvdKfDT2UwT48CmUZPQYYWjy3XpU8DUhpPeEOS7yLs9o8QNU4PXEnmjyFJrK8X644PY6Rr72Rb4Q7YukmvXOWhDwWaB67kobQu7QgdbwcKcM8zib/O6pbkLzfopI9H+2ZvIlhoLwdUmC9XiiCu4AfwLzLoEi8/xtHvA5aurwNoIc77RFQvK6TzDt6TEo9CVNIvdd6sLyKij08c5YEvR2veb2vYgK87C6AvG+m3jwGXqc9AVe1PH3nAz3e09y5DI42vdBKIb2Dt8e8NUEevVWgVD2ZJUo9tZKRvbKI7Ttu7Cs7M48YPDewCDzMoMi8JGujO6v7RD1l3kc9kLrMvQizEzxpK4c89IesvCMOijmcpoU7GhfyPFmVdTwk9As8naYFvPZ8TTxpiCC9m8CDvbdElzuNIsW8pBZ+vCcDK71677C8JDcnupLj6by2MkY9uP7Ju4CwVb01QZ677foDvN1kcrxOAds8X664O698gD18dWc8u5ZRvXGEM7yDSN07GO7UPGcH5TzNDzO8Wu0TPaNK+jyB2fK86FArvF6uuLhm8Bi7wWnHPCk+Gbx9u7S8RNwqvKc6IL39CXY9GUvuOymyfryF4GQ9ZD4TPaCy8jyB2fK8TJJwvFHfLz3hDks8r9kZvHmslTy63B49zKBIveeEp7wx3ZK7yxoSPP8bx7tF8/Y7UpniPKMW/jx+hzg8sS6GPYS3R7w8iHm8gUsPPOZyVj1q5bk8/+dKu5iFFbxfC9K8wPpcPWkrh7xjEkS81WjfO3wYzjxio1k9qcDWPEWWXTwmYMS8VuYhvJHjabzZtZ4816NNvcQBT70rkwW96K3EvNlv0TweIZa8CA17vVI8yTzyGMI81cX4vLfs+Dz23Ji7RksVvhYlgzvlWwo9f7DVO/vg2DsMSGm6f5kJvduBIr0TG9+8p8MIvdHTCb2Dt8e8N8fUOy1fiTwBnQK9GO5UvByG3Lo+xhk9NNIzPQlTSLyIeGy704UPvRbFNz3pZ/e8wnsYvcTqAjv/G8c7vQU8POszezucYLi8HgcYvY1OFL2SKbc8G8wpvM6V6blt2lo9clA3vIcehbyOkS896nlIvT7D5zze1o49+heHu+D8+TsseYe8COTdPDg2Pz16TEo9pW6cvKovQTyGPX48AKL9uxyGXLvsouU81D9CvU9wxbualDQ9FVZNPU+2kjzlW4o7Wu2TPKAKEb2gxEM9L8tBvb9Aqrzgbha9VTHquDck7jwmGnc9pss1vUCP6zx1iyW7cpv/Oa58ADyX04+9bxVJPTBuqL1Hv3q9dYulPJqUtL263B690S3xu04B27ug+D87wPrcu+ZBjDuGOAO9CIdEvYtWQT3OlWk+iGEgPRoX8jy/QKq7otYUPf/nyrzazGq7PqybPDsUFLy099e8o1xLvAgqq7ymKE88xKS1vEAbBr3g/Pk8UgjNPKP/sbu3oTA9plFsPPzJDDxOR6g80WHtPI1OlDyFJrK6UsJ/vH4qH7mPqHu8yQhBvE2S8Lz32eY59faWvFS9hDyFg8u79rDJPGQSxLzJCME8Tdi9u6MzLj0QlSi8SmyFvIxWQbywpR071pF8O9/lrbzUC8Y8qnUOvEqdT71Dsw09TtAQvPSeeDucAx+8E+diu3N8BjyB2fI8q0ESvfs98ryr0qc6ljCpvCFcBLyF4GQ8nc+iuzb7UD3DBAG9IXaCvQtLGz1y8508N5YKvaCycj3QBNQ8HjsUPCSUQDzJNJC83WRyPRCVKD0+Zs48EODwOyMlVj0qrQM9esaTOWzdDL0+Zs68Ud+vPIRarjxbp0Y6IoLvO/bcmDxuScW7tCD1PKpbED2rL0G7oGeqPJnffD0Ih0S9IHaCPLrcHjvTnNu7X1EfvQAuGL3Xo009C+6BvIzFKzjR0wk8wtixvLQ9pT0Vtpi8WdvCPOPaTjzqHK882IwBPSXx2bu37Hg8rcfIvCQl1rsmphE9O19cPbFIBLwqJBs9nGC4O8MEgT0KwjK88QZxPGtUpLz+vq28KiQbPOyLmb2Ivrk8LXkHvHJQNz0g0xs9mciwPO20trwuXFe85OwfPdFKoTyVwT49U9eCPag6oDy0IPW7x9+jPPLS9LzYAOc8/ZWQOwCi/bwQ8kG7K2c2PJ2Mh7xVdze8+KXqPFJlZruONBY9HClDPFstfT3t+gO9hBRhvO20trzMzBe7SsbsvHWLJb3GKmw8+VqiO658ADx1SIq8eTr5PCzWID1677C72W/RPOLDgj0eIZY8WgTgu46RLztQKni8R3Qyvcf2bzyVB4y61jeVvFhsWL1BRKO8xXC5u4bytT27ZYc9CsKyOrTGjTwtM7o8ddZtuwt85TsI5F288JKLvGU7YT0Ohom8BgGOu9Fzvj048PG8qWO9vLbVLD2gmya9ceFMPfQqk7tI/Zo7OPBxvAUbDD03DaK8bxVJPbFxIbzpZ/e8NljqvHhXKTxBRCM9m/HNvBuJjjv/oX28JqaRvCMl1ryxcSG9Ifw4vX1B67yyK1Q9ikRwOzxxrTyAZQ29BZKjPNwKC72uaq+8Rr/6vFIIzbwt7ew7nAMfvK7Zmbo3loq8oJumPDMd/LqjueS7j0viu4yCELyMVkG7QQGIPbqW0bxYyfE78O8kvSvHAb1qK4e9oLJyOgAuGD2AfFk9WqfGvNZRk7q6Obi9QXifPPdLgzsVnBq8VUM7PKMzrrxm8Bg9DDEdO2KmCzy5bbQ8Bhjauy3WILwZvYq8/0eWu4eVHLweZLE8QNW4PJAaGDwBEeg8YummvNKfjbuycaG825juO5RkpTt6Bv28VL0EvC3/PTxZOFw8pCuBvB5kMbyF4GS9phGDPFJlZruDWi67VBoevQLd67sWxbe8AC4YvdwKC70aF/K834gUPT1U/Txym388G4ZcvV6c57sN68+8JcCPvJiFlTyMxas8Qv7Vu6S5ZDwTeHg9vS5Zu0AbhjycYLi7j0viO8lojDs06f+8Le1svUa/+rsT5+K83E0mvUGhPDx7eJm8uW00PEHnib006X+8jdz3PEd0sjyxArc8TXukPHVFWL0ZvQo8qKkKvbxLCb1dP04666UXvQPGnzyFJjK9LisNvMhlWj1CW++85VuKOlvQY7w7FBS6B82ROzb7ULwWaJ45uRAbu0qdT70MjjY8T6RBvQVMVj3evBA7X/SFO8RhGr2VHlg9oCSPvOocrzxBRCM6kW8EvQVMVjx7qWO8JJRAPIavmjyA9qK86fORvCfPrrt7G4A8/CamvBmRuzxBMtK8xUecPKVuHDxUGh69wnsYPAPGn73e1g69FrPmvMnC8zy/V/Y80hYlPZpRmTzAI3q7VL2Eu5i5kbvyXo+8QI9rvBA4D70KwrI8D8kkvTfHVDx44BE8xROgvOGxMTzDYRq8a2twvXe0Qj2GJjI80EohvXmsFTyYuZE7CEH3PA26Bb2dLDy9T+qOvAYYWrseZDE9o+3gvWF6vDzND7M7zzhQO9lv0Tt2ovG74n21Oe0R0Lum9NK8vAU8vagGpDsSBJM8dL8hvDvOxryK0Iq8J4wTPFMITburL0E7PsaZPMzmlTtaSi27CCqrO8Fpx7z2H7S8AvqbvGx9wTw+TwK8ocTDOwL6G7zQBwa8aV8DPbrcnry6ys07Fn9qPHe0wju1Cak8wOMQOrWSkTtg11W9wnsYPd4ZKj19QWs7w5Lku/9E5LxnB2U9k/U6vNHTib0+rBu93E0mPOwUArzM5pW7wMbgPErG7DuTIQo8jBD0vIpEcD2jFv697m5pvTBR+LzFzdK8FVbNvIHZ8jykiBq9KrL+vDqlKT1QKvg7qnUOvBfFt7vPOFC7YB0jvWJyD72jMy49h68aPac6IDuhId08i/knvYl47DyFJjK7O85GvMirJ710HDs8Xq64PHQcu7zevJC8xeoCPADoSrwchly8ekxKPafdBj1gwIm8Zwflu6MW/rwqCh27aV+DvQ2gB71KhgM8LqKkvL50JrxpGbY7sXEhPPxPQz1KbIW7NeQEveTsHz0Uikk8mFnGPGrlOTyF4OQ86QpePbACN7yOkS+9bH1BPOTsn70KZRk9OxSUvVH2ezwZNCK7kBqYvB31RjwOFO28rtmZOri4fLwGGFq85aZSvOVbCjziIBy9l9OPPfVqfLwqVeU7ju7IPLXDWzyA2XK9t4/fO2UkFT0U5+K7ZMz2PHTW7bwzBrA8fF4bvd0KC7ulKE89fBhOvIKOqjs/NQS9oGequ2rlubyjM668W3PKO14OBDzZtR69+Os3vdc047znPlo8aULTPRmRu7xpKwe8K2c2vRlL7rzzuyi9N7CIPF8L0rvvgDq9oH52vNZ6sLqRKTe9McMUPSiJYb1/mYm8CsKyvBZ/6jw6SJA9xbYGusiCijwg0xu9esaTO73RPzzlctY7XJ8Zvct3Kz3jN2g7DDEdPfdlATwWaB49NOn/OtXF+Ds94Jc9yJnWvPdLAzxo02g8At3rOz81BLxHdLI7AIsxvesze7uiMy48cSeaPD36lTyGT8+8pzqguu+AOj26ltG8AiO5PKp1Dr34MQW9OxSUvCXx2bx0vyG8C3zlO1u5l7tUvQS8SNHLvFh+qTs94Bc8R6guvDMd/DzsFAK95OwfPU2S8LuZyLA8oFXZu1nbwru1khE9AiO5vK82sz1xhDM8TtCQOy2QU70s1iA9HgeYvBGs9LvE6gK9bgP4O72oIryxiG26PmmAvETcqrxLOIm86QrePJf8LD09VH087VedvKYozzuikEc8vTGLu6DaYD19Zas8+qh/vQF1tLt6MNe8l5eQvBV7v7wKNog9a8EsuwATKDyB7Vy9qy7HvADiobwmLIa7I4hdPB6PcDzWoDc72WievA3LgbzLW4A7l/c1u3dIgDzI9aU8lmSju02YwTw9KZe8UZEuvK/Fp7xhz1I9FIgHvRpFDb3uP4q9pdPNvQfB/rwklww8wYt9PKgIorz0LRa9kPr6vGy2Sz2Y7FQ8OjKRPJ20uzyOyXS8ELPYPCp2aTxWu6G8KhRdO+AW9bx/KcS8Gta4PBSIhzuIqmI9cOsfOyznpLzlHhG8JCqfvRPZfbxpUPG8+hk7vDeOaDqyKwI9LBgruzQ3Pbx425I7kv5IPGz0GT1aUgI9V4obvalqrjwYsJM7zUFwPXdIAL1feo68dZl2u6yfgryYyJY8tO+avM5y9jt+mJg992ADvXWZ9rvvMsI7Aaa6Nvqo/7wfz6U85HxPPIi5kT3/oWw8shzTvLls6zs/jYq8cBwmPCDRDLy73Sa8nVKvvScfPr2WlxC8vgNMO3+YmLsw4BE93jCFPA4tjjwpslC9++g0vOFWqrx9xze86abCvPlVIrnU/nW7e6GSPJA6sDzlD2K8ZmgaPREVZbsp8oW8QB62O8m5Pr1feg48IKCGu83ukrue5UG8e2FdPRSIhzxQvuY844kXumyFxbrBOKA8jhSLvMLLsjxfq5Q8e2FdPEITVb2xiUA9+7kVPEw2NTydg7W8UP4bPcYxDT2l0828tiIIPbIcUz1FSCk9Nl1iuzPVsDziJ4u9tHN+PGwjOb0MyZo6gfyLvHJCy7pJ34m763kKPVmwwDwOLY68ElUaPV4YgjzOIQC81A0lvRCC0rz6t665dHPRPF+rlDw3v+68VkpmPJL+SLqFtcO8y31XPeei9LxNB5a8FBkzPU2YwbtHDEK9G6eZvATbjjoZdKw8UM2VPUaqtTwGbiE8suvMOw4tjjxswxO9hbVDvDoykbzJVzI96zlVPQ6+ubtqkKa6uKhSu23n0bv063m8w2sNvQ38hzxRMQk9it+2PIOPnr3etGi8fjYMu65U7LsUSrm86zlVO5od2zyJbns8a8GsPFKCfzz0jTs8FXu/OzJ1i73PtJK61T6rO4UkGLxPa4m9MKDcvB+en7xMZzu97W4pPVy0DjxzQku9JOppuc4hAL3QRT665+IpPbusIDw015c9+fMVPT+Nir3D/Dg9Vt34vMEp8TzYxtw8Jn38O1Z7bD0pslA9tfGBvLVz/jzrOVW8mIrIvL7SRT34kQk8IDEyvKjI7DvnovS8cNzwO3wldrwhApO7cq84PT1L7jtmN5Q8lTMdvalb/7wFn6c8Jx++Obz//Tpstss8r8WnPdN6Er1L1Ki8RUipPDGVe7wNjbO8PYsjvKeXZjz97AK7xxf9O3NCSz36hig85Q9iOwZuobxCE1U8BNuOu7QR8jsLieW8LdzDvFSGTT3Bi3082/uwu/bvxzsOXpQ8oq0oPdQNpbuLED08ubeBvHMRRbzvcBC7cX4yOY/J9Lxp/RO9cq+4u4xyybuMo089G5pRvR48k73jiRc9MTPvPIZI1rzfUlw9YJ7MOu9wEL7U3B47mh3bPCYshrxpH2s7UO/su9HY0LtDdWG9/nBmvASqCL2mBFS9z+UYvUO1lrwBdbQ6mfuDu94hVru1Uw68QbFIPQUubDzZaB68niOQvGvBrLypai68O1bPvD/tL70rp+88UWCoPCa9sTy0EXK8UP4bvYqusL3kfE+9B9CtPGXVh7x6/9C7W0NTPUiug7yF85G8PkvuPFD+m7zoRDY9rMFZPaMPtbxJ34k85oAdvQEIRzy8PzM99Vw1PRUbGrzx1AO8FRsaPR7PJTzhR/u7om3zPE+cD73U3J68m3/nPIOPHj0KJ9k7oKnaO3LgPry0EXK9P42KvBHzjb1KxXm834NiuyUqHzwovxg9Mwa3PKkqeb2uY5s8Ho/wvKjXm7zQRb48qWouvSa9MT3UL3y9ZypMvWyFRbvNH5m96/3tvBK3pjyTL8+5JRvwO+ElJLvNQfA7FwPxvJeXEL24qFI8jeOEPhY/WD3Z92I7VOjZPDyHVT1EFyO9ClhfOwqJZTzyJ+G79fyPvGcqTL1yr7i8hhdQPUvUqLo3Ifu8HfxdPRTqkzxDhJC7U/M6PaLeLr1rwaw8WbBAu4NTNz3GIl47nOFzvbGJQL2WZCO9DSunvP3dU7wfwPa7GXQsvJwSejxU6Fm80glXOdYCRDycIak7zK7dPGkumrwVez89kPp6vGnu5LwzaEO6SJ/Uu+9jyLwA4qG8PelhPHfZKzvaivW8j/p6PanZAr2SYFU8thXAPK/2rTvUL/y5ej8GvEvUKL3oE7C7VOjZvOvMZ7zkfM+7v9YTvLh3zDvtX/o81gJEvAM5zbxgPEA8SwUvPehENr0FPZs9F3BePKzyXzxEF6M88QUKvc6j/Dz7iA89Z1tSPa+2+DymNVo94xrDO7vdpjstqz29rfLfvH+8Vjx/KcQ8ALOCPO1uqTyQCxE9BwE0PGPE8Twk+Rg9rmMbvHIejTwUGbM8XQfsvEIihDzppkI8M9UwPLio0rw50AS9/d1TPYyjz7w/jYq805xpuwc/Ar37iI89o02DPFiMgjux+BQ9qjsPPaZmYDzrzOe7aYF3vEToA733gtq6ZipMOwWfJzxqsv27j8l0u10Wm7yQnDw9cOufvK0BDz1DtZa82ffiO19JCD3IlYC9XngnPBoUhzxG2zs9s40OPNDlmLvyNpC8zxQ4vUaqNT3e8E88PosjPSFiuD3tX/o8u53xvOz97bv4RvO8lVV0PKJ8orthANm7S3QDPJY1hDzQdsS7v3QHvJm7zrtuSd66EeRePQfQLbz76DQ9zBDqvNZAkjsT2f07qAiivMLLsruCgO+8AUQuvGkfazxyTxM8IZO+Oz6LIz0Qwoe85K1VPKtfzTotSTE9GqWyO2dqAb3n4qk8CJRGvNn34rx8A588DU1+vPUgzrxfq5S9Fj/YOwqJ5bp32as94uk8Pc0fmTxHn9Q8P7ypvKj58rotejc9DU3+vCL1yrxA75Y9KnbpvBiwEzxY7Kc9Rdu7OXXVXbzhJSQ9CDI6vUvUKD1Xipu8oHjUPHuS4zvBB5o93Cy3ukvFeT15DJk7OWEwvZI8F70QgtK8SnIcPc9ShjuMcsk81nGYPEU5+rsIoY68gfwLvUifVL3JKBO81P51PT2tery7P7M7YDxAvSL1yjwZdCy9XWl4vG+6mbuZLAq9AeSIPJlOYbxmyD87NyH7vCImUbt0c9E79fwPvEO1FruVJG68BHmCvKRxQT3F8de8VOjZPBK3prySPBe8Hi1kvTPVsDz+Dto8EILSPH+8Vrz4wo88UP6bvbwOLT0gxEQ8CvbSvHAN9zsypCq9iQxvPCUb8LrjGkM7PMcKPZCphLuJHQW8WuHGvHUVE73gwxe9cD79PHZo8Dsfnh+7qsy6vG+6Gb0YEqA8s37fO7YiCLyskFO7D4+avDXKTzsUGTO6JRvwvGQEJ7s48HS8gl4YvQcBtDxE1+27KL8YvOaAHb2ulKE6g48eu60yFbybvxy9wMfkvNv7MDzlcW49gk9pPMJpJr1ZHxW9HKmAvGn9E7x3ynw9SnIcPTFzpLvJiDi74uk8PaCHAzy9cDk8sFg6vDnQBLzuDgQ8BwE0vdu7+7zHtfA7DPqgO7Ic07ubsG08eg4AvWqQJryl0029apAmvN7wT7yJDG89FXs/PeZPFzybv5y8MqQqPLYiiDsxQh68rfLfOkujIr2VM507uWzrO+h1PDwgoIY7o3FBvK6Uoby1Uae8v2XYureEFDxD1+28ROacvKdmYD07Vk+9VejZO8yuXb3bu3s9Xpp+u3BNrDz1IM68I4hdPfEFCrzEzZk8y65du/kVbbzMjIY8J+63u/gV7brtbik97g4EvE9ribzzyaI8cX4yPJwhKb2jD7U85LwEvbONDj3qals8V6zyvAF1tDzCaaa9zxQ4vclXMr1fq5Q8tUJ4PM5ydroypCo9lVX0O1PzOrzeIdY8cX6yvLOv5bzFzwC9SRCQPD0a6LxL1Ci8I4hdvC2rvbwYQyY8a2EHvc3ukr2QCao8eGw+PKHpj71YjAI9zN9jPH1WfDwzBre8WB0uvdB2xDv2IM46v9aTusZT5L3D/Dg8iNvovCwYKzzlQGi8ElWavCOI3brqats7MXMkPCnj1rzuATw8fjYMPGIPiDzg9J28FLkNvT3pYTzYpIW5BMxfPNgo6TxV9wi8XqktvQwceLyvJzS80gnXvBCRgbzaivU8fcc3vPvoND1PXFo5TStUujEz7zzKuT67xmKTO8UAhz3kvIS7UP4bPXJPk7xllzm8rfJfvaC4iTzNUJ89h3ncOyCghrw3bJE8NixcPQEVD7sNKye92pkkvdgo6buZ+4M87NsWPYPxKj1cpd+7UC+iuzcwKr21IKE8Dl6UvQDkiL3NH5m8e5Lju9xdPb39rE09DSsnvQUMFb1E5hw9TGe7PKZm4Lyv5/48loZ6vKC4ibzXM0q8N50XPP4/4DylBFS8TQcWPRqlsrzF8dc8yYg4vM7jsTuGF1C9Pu0vvGQEpzwQs1i9qps0uz2LIzx0goC82or1vLIrAj27rCA9z+WYvFPzujpGShC9S9QoO7NciL1dFhu9sisCPYPCC71NB5a7DU3+vJPC4byqbBU9jEHDvB5tmby1U448dnefO4PxqjtKMuc7/38VOhTqkzxa4ca8D1FMu7azs7zkrVW9Q9ftumP1d7y7nXE8tUL4uwoFgr1k9fc6H2+AvMReRbyTb4S8NgoFvNnVC7sAswI9UyRBvRjS6jztX3q8bRhYPIC8VjtwTay8OZK2vdNr47wEzF89gcsFO8Xx1zx3yvy82/uwPAU9m71Xihu8Pa36PIwFXDtadFm8ROacvKkq+TsUGbM6A2rTO9+06DvPg4w8XNblvEToA7105Aw9CJRGPIhuez2dUq+7ABOovER5L70M+qC8L2/Wuy2rvTzFz4C8V4qbvcYxDbzq18g7EeTevIpOCz3NH5m8A2pTO6k5KLzhVqq7yfeMPQ9RTLqjD7U7I4jdvCT5GD2uYxs9qVv/PKPP/7yrkFM9Du8/vKdmYD3M32O8qWquvPiz4LvSCdc8eDs4PY+Ybrz+To87TGc7PC5LmLyyHNM8ylkZPWJADr2Hedw64PSdPGwjubyYWcI8kDqwvOei9DnYpAU9FaxFvTlhMD0+Wp28SJ9UvCSXjLtnW1K93vBPvHOCADzx9tq8Q1OKvBs4xbzJiLi6SdBaPdQNpbtBRFu6LdxDvQM5TT0hMxm96XW8PI4Ui7vamaQ78ifhPATMX7y1USc99r7BPNTcnrwE/eW8cOufPGDeATwogco7eKoMvcUABz0njpK8xWITPCNXV7qIuZE8dkaZvLkK3zwQs1g9QbFIuzVdYrn3gto8CjYIOpwS+rww1TU9/W3RPDbEMr0Onke94ojfvEGg8bsR4+g77WiUPbb2jzxstxQ8/k9zvQH8Cb2n/oa8GLZCOv7Sizwym7Q7NeBVOzux9LsfCL+86dpbPKaMmLwnPhg9Gv0ePVJvoztpjNs85M+7vOKI37zFF/C8pgu7PAoSSr1MAYS79ZwyveKZib1xUgG970q2u7Lnebux6bS8MrdXvXVq1bwbXmM9m64ePENoq7wSV5I83JsdvPW41Tq8ZK+7WiQfvNQEADzDNc68bG59vT74UDw6ULC64NMKPbi8DrtZv+S8xd8pvPNmgL2hnRu9aEc6vWzRfLwxK4G8tK8zPaxdt7yrigS9u4INvH8DLj1BBSw9BSUIPSSHiLwb30C816plPMM1Tj1AsZu7g3OIO38DLry1kxC8hHFNPLfYsby+qdA8tnUyPQaIh7yn7dw8m6xjPD74UDuRlqO83KqMOxp8QbxzJTQ9LvFYvE5iSLxT0qK8bjR8Ox9rvryJfqi85M87vDiKMb0nPhi9sud5O+q8fTu9q4u8zwYUPQ8fJTyavY07Drwlvda7D73qPxa9q3nauwGXz7y3vI480h5ovERMCD3rvjg9bjT8PPRXkTze4D66nfM/vOpOhblwfZO8wVFxPHmVDrtttVm8XyILPQfcFz2uswI8CDCoPAsSyrzkX4g85iUHuWvv2jsIToa8PJeMu6uXuDucEZ69csK0PIKemjvJFxe7xd+pvCewBj20rfg8H4mcvFREET05bo49cPw1PWD1PbxpjNs8q5V9vUTnzTsxuRK9qjL+PNw4nryo0bm6CE6GvP3urjzQdse7ALPyvNVJoT17W428IhUavMbfKb2MpWu8CpOnuy9ytjyjYd88hHFNvEEFrDzDNc68s0y0vJjoHz1pjFu9iuGnvAH8CT18Pa+8wWIbve9KtjsZmh87OlCwPAzLlD11hng89Td4PIxCbLxBPfK7NUPVvC0CgzpHj269dIgzPYMqcT3CxRq95TI7vBOp57vIJgY7nXSdugF7rLzUgWe6vWJ0PQPccD0GeZi9aMgXPGtufbxAP628V/nlOoDYmztb6h08C3eEO40IazzDmog7f3UcPCMVmrti2Rq9qjJ+PKqzW7y1EjO60h7ovFuFY71bhx69EeUjvb1GUT0Jy+07d81UvRADgjxlgbu8cHvYu0XJbzxalg08hNaHPTZFED3Wu4+9GLZCPXZqVby4ulO88C4TPcHwrLpT0Gc96XdcPeIJvby4vA49WgbBvFaYoTu6njA9A96ru8HwrLw0/jO8b/r6vGsLfjoymzQ8AfwJvQfclzud8788zS/rPHFfNb1O4eq8bbXZPCX3u7z7JvW7EIIkPTXgVT1T0Oe8Z9cGvc2wyLuRpZK7yQbtvI0Iazxi1988Oev1vDs0jTzWSSE9powYulHuxbpmgTs7HNKMPJ7VYTzwydg8WN3CursBMLzCUyw9c6RWO/nhU7zxDno8N6bUu5IXgT0663U8F9SgOm42t7sEP3A8V3rDPPwKUjzEixm9F9QgvQsSyrxDaKu8cqaRPN7gvryn/oa9rrMCPfzs8zwZGUK9ChSFPf8z0DuddB2+oBw+u+KI3zwUDqK8RcuqugNdTjuSFcY7HcMdvfDJWLs9lVE8+ygwvcxNybzHQG67z/XpOrSvs7wR9JK5SVcovOra2zyImks9J7CGvJGlkrw7TvW8vauLPB+H4bu/jS29xXyqPLdZDz0W4w88x0DuvBDlo7zfYZy9U9IivQaGTDx8voy8y2nsO8SYTT2Y6J+8+yZ1PF+u4TzaVEG8gOXPPG+ZNj3RzJK83/zhO5KWI73VZcQ8aSncPCw8BD2Y9w69pKg7vBqY5DxGLG+7mr2NvMilqDxDdxq9enV1OI2LAz0RgOk8ckOSO46JSDwnvbq7tZHVvMZ6bzxJ2IW9BoiHvPTWs7zgQz48DVkmPQzaAz25HdO8fSGMOyh2BTzhwuA8ntccPSc8Xb3XqmU9Dx+lvdw2Y729Kq48lb+hvQZ5mLzzVVY7n7k+PDs0DTzYquU710dmurNMtLz1N/i87y6TPMV6bz7Kh0o9kTOkPJW/IbsKr0o93n0/vZIVxjuVzpA8O071vORfiLyvpBO94gm9vFnBHz3SoQC87uc2u1PQ5zyZZ8K6ZuS6u9SDIj0NWaa8yggoOw4ulLvf4D49j0KTvEKGCb1JyRa9+ygwvencFr3JiYU8dk6yvBFII7wwOLU7U1MAPeTr3rvP9em8iybJPCvZhDx/5wq9NV94PIBkcrxxXfo4+eFTPNlyn7viihq8yReXvKjEhTw9+ou8FI3EvNiOQj1TUwC8dkz3vIrhpzppKdw2i0QnPFPhET1zGAC95Gw8vbxG0bpSCum86euFuwaIhzy+q4s7qdE5PcM1Tr2e1xy9c6RWPKuXOD24OXa9/W+MPb3HLj2HGyk80cwSPQNdzrzJiYU9T7gTPdeq5TywhrU8hNaHPXFSATwW0mW7+eHTvANdzrxYXqA8FtJlvGfXBjw4ijE8JtuYPHOkVjyImks9OAnUPBSNRLz0V5E8WqNBPb1IDL1zI/m8OGxTPNE+AbxkOt+8yt0VvRUMZz14lQ68fL6MvNOfRbzAcYo7EWaBPRQqxTx/A667UYvGPMD/mzyRMyQ9BmopPFaYobruZtm8hHFNPLPNET0+6xw955N/PA68JTxRi0Y8rVt8PdOSEb2AZi08awt+vOeTfzyt+Pw8aSlcvRO6kTv+NQu8duuyPG+X+zzk6945059FvNG76LyHKhg9Q3eaPBdTQz3La6c9OIj2OxHlI72t3pS7KB7/vH2eczwGByq6SPLtvBADAjyBLKw7aEc6vL3Hrrz3/XY8GLZCO+sffT0bYJ68FtJlPUDACr2ql7g8U23oO3brMrxUUcW8QQWsvDA4tbut3Fm8AYqbOw68pbwEou87mOifvDE2+ru7ATA9vquLPUj0qDye1xy9SPLtPHHeV7zlwge9HqU/PHDvgbx4MFQ8lb+hvdG9IzwafEG88hC1PfwKUj1xX7U8m66ePF8vPzx9oC46ckFXPA8BR7w4irG8zTEmPYvFBL1XXOU6p266PUlVbbt1bJC8+yZ1PUAjiryGtm49e1uNvCbbmDyzSnk8AfwJPbV1MrwGeRg9OlCwu/disbyRlqO81ALFPIOPKz1Gj+68kTOkPI9PRzztaJS7GKmOvIVkmbzUg6K8y2nsu8xPhD3F/Yc8poyYulUXRL1VM+c82XIfvWSfmbsnu3+8vw6LvNG9ozySeEW9WiSfu6uXOL30uNW7OIj2uiggOryvvvu7pEU8PKqXOLxJVyg9HMMdvC9ytjx/dZy8AYobvdVlxLuXIGY9K0f9PElXKD3lz7s5vsXzPFQ1or3/tC09O7F0ORLj6Dqnit08XxOcvFWWZj1HA5g77KIVvItC7Ds2JXe87CG4vPhgdrwhzr28rd4UvRtvjTxi2Ro9FuOPvFmjQbz7KDC9V3rDPMdCKT0jJAk8Jz6YvGdF/7y3WQ88y84mPHbPD72rFtu7i7aVOAt3hL2jOAg9CMttPFvqHb0pgzm9vo2tukjWSrySliO9wlMsvdBaJLzL6sk74UM+PcXfqTyGxxi9Z8bcvOXCh7wiTWA8WgZBPGSfmTypJwU5eZNTufU5Mz3EGau8GRlCPDVfeLzmlTq7dYb4O7Jo17yP7Me8CqKWPPEQNbwh6mC9xXyqPJyDDL14sTG7nJBAvZyQwLykRby7OlCwPXMlND231vY5lFwivIRxzTtuNje8XU2dvJT357wTuhG9rsA2O90awDsym7S6ZnSHPMrsBL3xDnq8KCA6vTBWkzmMKAS8xl5Mu3tbjbw3J7I8zi9rvQt1Sbtalg29IepgPSFNYLstrLc8Al8JvZaFoD1stxS9fSEMPWI8Gju+KPO8CM0oPPKPVzuMJkk881VWPEcDmLzA/5u8sCM2PI4I67u19g+9CcvtPMywSL2uwDY9/sOcPDluDr2GN8w8YBOcvckkS73YDyC9TBvsPFAoxzziCb08rfj8PEA/LTt8O/S8vqlQvD74UDvsohW9U+GRvDXC97ukxpm8bjY3u0q6p7zJFxe94+tevCV4mbzSn0W96U4FPVdeIDyuwDa9Um8jPdZJIT18Pa880TzGvNeqZb10iLO8HZgLPJIIEj0/2vK9JIeIO+Yyu7wiFRo8/yacvJaFILxzJbS7OAuPPF4vP7vB8Cy9iBnuPEaRqbxQqSQ8BgeqvCe9ursBFnI8QSFPvNcPIDwjJIk9thD4u7SvM73mJYe8z/ekvJ7mC71ZMw69tC7WPPj99rxju7w7zS/ru4/fkzygOGE816plvFyFY7sM9iY99NazPP7DHD1eL7+6FtQgvGYA3rwOvKU8gMdxPY5tJTwSSKO7/sOcOxQOIj2MKAS8v5wcvYVkGb0hsho8x7QXvFAqAj0fXgo9Y7u8PNB2x7sbfEG7mPcOPYcqmL0MaBW9OAuPvOlbuTo7sXS9xBmrPCX3O72whPq88Ej7PMHwLDzrPVu86BRdPewDWrwbYB67qicFva8/WT39Ua48ygiou3MlND3u5za9nuaLPNlyH7t1hvi7KuY4vdtUwTzpWX66b5f7vGCSvjo14NU7zhUDvUfybbugDwo9HofhPO1oFL3mMru8Z8bcvNSDIjzPeIK9gxAJvR/7Cj2XhaC7viouvPL0kbwPHeq8agCFPQx1ybyKYMq8/tILPTKZebzrITg9p4pdPJDQpDzqPVs93/zhvMtrJ70syFq8hjmHvax5WrxiWD29n1Y/vCgTBjzkzzu9yupJPBr9nrrpd1w7loWgvIYqGLmDcwi87dqCPN5wC71MgCY9BCNNvV8ii7x6WdI8Jfc7vENoq72BLKy7P9ytPPEQNTyRMyQ9NycyvZsgjTxIdYa9gOXPvFLuRT02Q9W71AQAPO0FFb0nPhg81ruPPJBCEzwLEso8u4DSO0nYBb3SvSO9kmuRPG4Y2bu2dbI9ds+PvNOSkTzUgyK9xIuZvNvVHr25OzG4UCjHvIIsrL0Izai7ARZyvMqHSr1ao0E91VgQvepOhTokh4i8G2CePH2grj1ZJJ88enewvJehw7x9nvM80FqkPOo/Fj0m25i8wfAsPRbjjzqSaxE9L/OTuxUOojqy3AC8cd5XvCggOj0klDy8elnSPA3YSDwDwgg79/+xPPuJ9DtsVBW8wzXOu4MQCT0trLc7/VGuPBtvDb3QaRO7MTb6PMdCKb1JyRY9Vpihu4Bk8rxZo0G8Z9eGvPlGjrxKuqc4UQwkPORQmbxrcLi8DFdrvPeAjzwQgOm7zE+EvKPVCL3cmWI8W4cevRD0kjqbII070pIRPOPrXj3OBhS8HTWMPVd6wzyif707RSxvvTKZeTyqJ4W8wVMsPEKETr1Mj5W827fAu/1tUTyWIiG8cO8BvfunUjwEwE09ozgIPRAd6jtg9T08EAHHPHWGeLw+3C29hn9KPUBhOD3NuTS9rQwHvZWam7zJLS68YziqvPoRhT2Gf8o8uIbWt5NNIr2EHYi8G80evbLJrrsmhpQ7Y03zPBT0njx6qhW8aCaMvN0oXDu4voY8jonrPGpsDz0rPEa6ieibPK89KLzjAdy8vC41vFoSMT2beni9ueG7ureiLr3Sdly9ZxGqvMVpkLrpzIi8jXQivW//i728LrW8es1KPStfezsfmDK8YkaWPGWa7LzojWI8mldDPDg7v7zugjq8IghhvAg0s7wyVFM625xVukPfUj31mke6EGiYvN4TEzwo0429L+uavLrvJ70jCOG74wHcvDpsYD3550C8wfnIvMgRVjtlxDA9ZxEqPW4byzxqc+y8neNJO46zrzrfUqA9JpSAvCMI4Ts94x278fJoOxO8bjx6sfK7wMgnPIB1KT3Zh4y84IPBPCkSmzsb/r87qrgXvYm+VzzDOFY8tDldvOGRLTzDRkK8O4g4u4CY3jz1foi8q8YDvWJbX7yP1uS88KXvvPHklTsINLM8+PUsu5NiBD3lKyC87BKMvMtsO734xIu89E1OvEKusTzCHBe9cov5PEFvpLyX7go9yAPqPJ7V3bs7liQ9+zQ6uVjhj7w++Ga8RQmXvBmxRj3JQve65TKWvDzHxTzugjo9JEeHuysghzwdSzm8LGYKvAlzwDzlK6A832dpPMyPiTwBHCY89rafvf7OLD1dgl88eGQSPWpeozt6sXI8er9ePclCd7vika08FBdUPYjMwzzlD0i8Tm4dPSRjxr2wn2o8fkQIvSaGezwfmLK7T3WTvLeUwru2apc8YN1EuMM41rv3vZU9UJ++vPxl27xqgVi9eY69u2SFo7t/gxW8WdMjvMH5yLyy3nc831KgvDlJK7w96vo8+SZOvbnTT7yZCso8VDmxvNhP3Lye/yE79X6IvJp6+DyTTaI9y2y7PNzpzjxuG8u7WzVmvV/rML2EHQi9Q8qJvRT0Hj2X9YA9qpVJvXhkkrtv+BW848JOPCMWzTqf8bW8r1mAO+snVT3i0Do9yS2uvRrw0zvw3Z+7F0h1vN0FJ7xJeUW7pzMHPbiwmjzhg0E8x68TvKEwwzrlD0i9JoaUvePeJjwbzR68tUdJOvfL6Lw1vSS9PeMdvDuWJL2Ion89+PWsO698Nb1u/4s8HmAbvPWax7y+kJA8c4QcPLVHST0QdgQ9C52EvXhk+bvojWI6ueG7O6zwLj1IecW8Nb0kPVonEz0AHCa9y4/wu2Ic0rw/Iiu86cwIPQzjhzrqC328ZIUjvNAbEL3zMfY8O6ttO9AbkLzFd+M8fj0SPTllAz1SARq9VXi+vHwaRD2bgYe64YNBvAhJlTx6sYs8d08wvfpX77xE7T685B00Ou1DLTl9Nhw8sJEXPUh5xTz2mkc8NKFMPWbnZbtJqua8mjtrvIsnqTwLwLk8alA3PJNihDuccxu8wipqPfkmzrzP3Om7PuqTPItK3jzCOFY9LIm/PGJb3zs6iLi8Bb31uUvwgrfbuK08kQ4VvZWhEb1KuNK8vEOXvKmVSTzws1u8YQeJvcfE3DxOdfo8V4YqvY/PBz1NE7g6KMwXvr6Xhjys8C49pKcAvCnTjbmOpcO76xnpvOMB3Lxdgt+8ZvXRu/EA1bwwB9q8YltfPJo76zzV3y29MOSkvI/PB7wDfgE9N+5FPUYsTLwo70y8zKtIvQYDEj1SARq9D1osvSQkObz5EQU8Itc/PKOgcbxLxj67UK0qvWpeo7zSaIk88euLvNqA/TpBhIY9LtY4vKviwrsDmkA9kiNevR0vYTyYLX89whz+uxK1kbvA69y84Fl9PHTfAT0Dfug8YlvfvO6CujyhPq88VXi+O7nTT7yBpso8XF8qvfHkFbvsQy09oD4vPQ4bnzyYJqI73zZIPFxRvrwNDTM9pyyRvW8pt7wmlAC9r2DdO23qKT13ZPk8NeBZvY17GD0NDTO806eWOjurhjw5ZYO9DQ0zPSHlq72gFIS9Wy4JPTRwq72K7xG9amUZvDWhTDww+Qa8GyH1uwYK77uLPAu9vEqNvZtXwzzipnY+V8U3PS7WuDy3oq67E+YyPZbLvLw5ZYM8A36BPJf1ALzYQfC8qZVJvMfuoLzQGxA8gdCOvCCt+7wPWiw9BL0OPG/4FTwOKQs9y2w7PPpCpjvKQhA98zH2PKYJwzqKGT28BcQEvfHy6LsyVNO8Dz7Uu5DIeLwCcPw77VGZvMH5yDzyMfa7YPmcO6viwrwyYr883jbIvHTY8jxztb27coQcu6l58TvlD8g8l+cUOmSMGb08x8U8vDyhu57/Ib2YLf88ddGVuiaUgLu/kBC82EHwu8WTuztObh09swg8vUiHsbwZ1Hs6mBi2vOBZfbbQIgY8UK0qPHddHD1jdze92o6Cvf7cmDzV3608kiPevG83oz0Qbw49qWSoPLw8IbzJ/Iy8mTuEPfj1rDwPMOg8PeMdu9JoiT0guwA9YRxSu5Ij3rxNRNm8+PUsPEY6ODxFEA08q6O1PCo8xjxeuo883MYZPaX71jxv+BW8sJ9qPHwaRD2UfsO8tTIAvHXRlbuxrda71hBPved4Gb0KV4E90BuQvM7OfbzKSYY8E9jGvIMPnD0ffNq7mUnXPGD5HDxAYbg89738PB+KRjtiTYy7LrrgvC/57TtvNyM9cXYwPS/kJDtswOU8QX2QPMI4Vj1jacu5XF8qvCQkubzmaq28tVU1PEwhJL2YLX88ByZHvIsL0TxqZRk9Rjq4PGXEsLxzwym9iu/4PC6XKz1dnjc9Pz6DPQhXaDwMzqW8b/gVPKzU1ry6BAo7bLKSu7sgybyNQ4G6VU76PFsSsboXcrm8aCYMPYMWEjxuG0s9mCYiOw8ifD1Obh290CljvEmjibsxOPu7OB8AvbZjIb2plcm7k1sOPF1tFjwffNq8UcKMPDD5Bj1rsnm8c6fRPIiwhD1+PXk8GvDTu5NUGLoDfgG9H4pGvVCfvjw+FD88d08wu2fZkr3Ozpa8m3ObvMx6pz1ltkQ9QYSGPDAVxjxOYLE86H/2O4VOKTy64Ts8wiMNvPaoMz3nhoW8V6KCO2DP2D3Nq8i8O52avJR+Qz3fUqC8CqRhPUhWELxKuFI7pco1vAyyzTxVatK7sbtCPR5uBzxXhqq8gcn/vE+RUrwQaBg9k00ivQhJlTyNWEq8AU3HvIsL0bxS+iO9anPsvPe9/LzxAFU9iycpO6ANjjwbDCy93NQFPaOu3byl7YO8UgEavRZIjrx78Jg69rafvMIq6jtAYbi82U9cPA8+1LrhtOI7R10GvHX0SrosbWe8WfZYPWpQN7x6sYs8ZGnLvEPKCb2OpUO94+ySPDSvOD0PTEA9IvMXvOroxzyBwqK9ylDjPGuB2LqFYws78cHHPIHCIjqe1V09ILuAPILlVzwZvzI8dPTKvOPQOrxRyQK8oloHvPRbOrtBktk8cVrYO1jTIzt2JYU8lr3QvPM/Yjzx5Hy76bcmPBQCi7x4ZBK9hnHeO8WhpztAReA7O52avI/W5LpuBoK9om/QPAzjbjr+3Jg798tovb6XhryGjTa7VE4TvTAVxryTVBi9IvqNPLxD/jwxMZ47kjFKvdlPXLzrBKC8H6YeuwzckTwebu48l+cUu1HeS7xBhIY9hCRlvAbnuTysxgO7phevu0wTuLtcdIy8M4V0vdOnFjxGHuC8o4sovU02bTuNdCK8fkQIO6Fah727IMm8w2n3PDExHj3V9A89GwysPBsMLL3pqTo8E8ravCIBhLw/Iiu8CDSzvEiHMTz4Cva8yANqvC2s9DzZgP28ZIUjvHu/3rwG9aW7TCGkO69uSbxpULe7hU4pOon9ZL20K3E8MTgUvYiifz1wRQ88EYvNO7Z4ar3c1IU9GJUHvffLAT3MnVy8bhvLvO+liDwb4me8TAVMPPR+bzxgDua8gw+cvBrw07xcQ9I726rBvD0G0zx78Bi9AjEIPVjTozygMEO9GIClPJk7hL3Ozv28bMBlvYsL0Tzajuk86ujHPNA3Tzp8/us7AU1HvOLQurvP3Ok7erGLvEKSWby54bs8tTIAvd33ujyTP7Y8Qq6xvMIjjbuQ8ry7if1kvfs0Oj1UOTE7+Ar2vC/57TuNiYQ7tmqXPGuyebw1vSS9bbmIvBOuG7yW2Sg9yPX9vQOM1DwqC6W7v6zPPCogbrrA3XC7ADHvOyr9uDqnSNC8J7A/vfCz2zsSmTk8x+A0vGJb37yk7Wq7ivaHPHqOPTtIa9m7sq1WPDk7v7tHVpC8om9QPG7/C73+3Ji8RReDvFs15jzjws68bcBluzE/CrliHFI8kiPePDAH2ry9bUK7WzVmPDAVxrtxdjA9eo49PKFTkbx09Eq9tmr+PIPzQz3aqkE8yjuau+GmD70Lsk099XcSuy2sdL3qC/283NtiPMV3Y7xoA748OVcXPSWUZzyaO2s88zGPvEYQjT3W+wW+yfUWvftlW7ykvMm8BybHvCr9uDxzw6m8Q8MTveUy/TxPkVI8hUC9vL1RarskMqW8JZRnvX49+bys4kI9WNMjPVHQ37uGf8o831kWvRBMwDw9BtM7es3KvC7WOL0BMYg7YSq+PIB1qby0Fii8GaNaPDOFjby4lMK6h7DrPKFT+DzO3Gm81LXpu+UdNLxg+Zy8baucvUTR5rybgYc8NxGUvAqkYTsDcHw5Xqwju/HPMz1Bdhq8FAnovEq40jzFoac6zurVPL+6uzwVJcA8H3xaPRGLzbtFFwO9mBg2vOnMiL3H4LQ8xGmQvaN9PDwhyVO848JOvCRAkTyyya67RixMvJyW0LwU+/u7zJ1cvBGLTTzKSQa9fAxYPYw88rwlY8Y7guXXPBq/sjpBb6S9f3WpO5IxyjxAN3Q7W0PSPL6XBr2ZCso80WhwvbG7Qjx/inI94GeCvAJbszwWTwS9o6AKPOVAAr0T2Ma8diWFOkvwgrnfRDS9sZ8DvVn22Lye8TW8mCaiPYoZPbwo2gO7BwpvvcDr3Lx6sQu99CqZPJEAKbxVVYm9nJbQu5uBh7yQ5FC9NKFMPVCtKr2vWYC8H4pGvOF11TyvUoo9Xqwju7QWqDu1VTW9uv0TO5NNojzx8mg8UgEavamAgD3SaPC7jqVDPRKLTTkpC6U8EsraO7LekDx2F5k9YPmcOgXEBDyKGb08GIClu4G0tjx+WdG7M34XvalylLw4LVM6j9bkPGfSnDxBfRC9PMfFu5NiBD1/gxW9Ki7aPEmq5ryLJym9IclTvKTKtbxsztG89718PFfFtzulyjW8mjvrvO+zW7ripnY8p1Y8vDXLkDwasca8nccKPdJ2XLyfFOs85SugvHUQIzwqLlo9V8U3vM3HoD11Are7gaZKu7G7Qr2LNRU9v7q7vEBhuLxcbRa9TCGkPBT7+7tbNWY8DQ2zvAOM1LyCwiK87EMtPRQJ6DwCcHw8AlszvEBhODxzhBw849A6vJBcIz2uXQE9Q2AbvdocOb20+za9EQnUu7NKFTxDgWc9pgvuPPk+47vXsRO92oxjvV6eE73RK0g6cBHsPA5mGTxiSrA8EZmpvAqR7zzTPYw7+B2XvKshDz1rRIM841cDvMlagjxQdrW7FlcKvW+4Cr3w1OU8i2YtvL/H97xh0SO9t/YxvWury7vzz+A88a4UvF/firwXCCy9bf6GvAZ+Cj3cfny70z2MvTBLqTzr59G6xs8xvHXmFTtU8x48sQC8vLphV71w+QG9/JoAvaWS4bsEg4872aMsvDArfryRPPi8WM5uvbGQEbzoc0q71qgxva0TqLwg4lM9K14VvDHENb3x5im7n7wWPNX3jzwZau86gYOjvP6Mmbslz2e8aqLpPKmfoDuOQf27hIcAvR6AEDmulRY9h2LQvIHzzTyaNss8vLQSvfnOuDtzDOe7GWrvPG02HD01CQo92hy5PEvw6Twc/iE6WNfQvCLUbLxkM+c7snlIvSLU7LoN7Qy8uHggvSYwCr0EK088sQA8O8hRoDyTN3M8QwhbPaWbQz1V/IA8QJRTvaUrGbzERGE8wGCvPD8kKbqt8/y8jtq0OphEsjwIOI48vm4WPbEAPDuZvT69LEfMO0P/+LyjEPO6dIXzvChauLz9SyK9DmYZPcHZu7wf+Zw8Kdymux3e9jz0qY88xjb6vGJBzrvCwnK6JmgfvG2mRr1VbKs8Ies1vLmBAj3eYQ28GnNRPTAr/jzv6y69a0SDPHgiCD1ltdU83xKvvLMSAD0jbaS9LVCuu+s/krwNJaI790zKvPLvC7ycwZs8Sf5QPHkLPz1Y19C8BLskPTgc77z9E427J+ErvHKT2rxRRwK9mcYgPYzoGzyzShW8h9L6PLs7Brwuybq7MLtTPW4fU71U6jy7ECAdPSA6FLyjEHO7gvyvvLJ5SL11J408kk68Pbzspzzjhja81CZDPHiJ0LwWV4q8oDUjO3SlHr1pKV09u+NFPYGDIzuEZ1W8Zk4NPDOHG7nPAZq6DQX3vGoyv7scxgw9g3U8PVFHgr2STrw8XGuDu/XqhryXyyW9By+sPG6vqDwEgw+8+Z8FvMtMG7tlrHM85oExvY7R0rwl75I88u+LvbPy1Dj8Od683YfevOr+mrq4bz68ufEsPXEazrwYEY69Z6duu8ulfLzND4G8PqucPPA1CDzoDII8pmyQPMHZO71gT7U8XSUHPYq1izx4iVC8rw6jvMBgrzzJMfU88sb+vLr6Dj2joMi8KlWzvGhAJj30UU88sfdZvY3I8Lzk0A+9NL8wPVblNz0JGOO7CpFvu2UNlrtrRAM9ojAevbXMg70zRqQ8l6t6PK2DUr2RnZo8WyqMPCncJr3CUsi8jtHSPF3EZLq4eCC9kzfzO07rZD1rtC09U3qSPE5MBz05JdG8qhitPE70Rj2ksgw8Z8cZPcNbqjz+jJm8MBOUvN2QQD0Onq48GgOnO7IJnjzIUaC80YOIPWWsczyolr46S4A/vBLjgjuaPy080vwUPRR0+byZxiC9QygGOza6q7txqqO7pIn/vDisxLpU6jw9wNBZvCDi07ygFXg9wsJyvEZbFr4SguC8h9L6u6cdsj287Ce7r9YNOpwoZLwayxG9ozmAvZBcI73S/JS9b7gKvWPDPD1qO6G88eYpvXAxlzyTN3M8MVQLPRAgnTzEROG7zzBNPGHRI7wp3CY9vFxSvFFf7LyI+wc9FYa9vBQNsTtdxOS8qJY+PKwKxr3gGxG9V+4ZPHFyjrw2IfQ7sIevPPHdR70CqWA8TGn2ukiFxDu99Qk9dBVJPcUekLzV9w88FYY9vR0/mTqgFfg8TPnLu13E5LzBSea7EhuYO8VNw7tV3FW9Dp4uPZUahL3VD3o8px0yPRQNMT20iwy9V1XiPLs7hrrp9bi9zI0SPUYjgb3ORxa9ASdyvGwturtyswU9bZ1kPQ/oB7yI+wc7zsAivPPPYDwlXz08mESyvG53kz0iZEK9HT8ZvE70RruWUpm925XFu5Yy7jsb7N07KaQRPVxrgzowSym9VdPzvKInvLt+UBM9kzdzPoZBhD2STrw8EGEUva6MND1TepK8DZXMOrB+zTv4VSw844Y2vH0PnLu8XNI8Y7paOwI5trwv0hy8K84/PIPl5jtWdQ29hIeAPUOYsDtco5g7UvijPEj17jzYKqA8stEIvWKx+Lu15G28Qo9OPJhEMj2YRDK9oXYavVVjSTyNWEY8ZMweO6yam7wQIB09lUk3PDmV+zyNYSg9CSHFuwoqJzwTXI88KdPEvEQRPbvPME28GPHiu+nsVr1ltVW9IHIpPTZKAb3S/BQ8AYgUvUMIW7zSpFQ7WeCyOrhAi7z9SyK9vWW0u+/rLr1cawM9+c44PVDm3zvphY48LEdMvc6IDb2cMUa7Y8M8PHSlnr1h0aM9qQ9LPf7ELjxudxM9QwjbvIj7Bz0/i/E8EXn+PIFj+DzlEYc9GBEOvEuJIb0KKie9OSVRvJRA1bo0vzC7rw6jPHfhkLwoWrg8Qh+kOlFHAj1EEb28y7xFPO35FTx/cd88ZbXVvMk6V7xF+vM8oR5avfHdRzzBSWa9TutkOkYD1jzA8AQ8Dp6uPAqjs7ycKGQ9Ue/BvPq377tYLxE8Q5iwudI0qjyoBum8wuIdPbV0w7wrJoA7XNutPNmjLD1ZcIg8JHaGPPMwA73oc0o8FRaTvKWSYTzGxk8863enPDU4vbugFXi9VnWNvAwcQLyIazI9mb0+PdeRaDuD5Wa8CSFFvDI9wjzKQ7k8hunDPDa6Kz1lrHO6aqJpPPFNcj0+q5w88NRlvBlq77vcpwm9hPcqPLjf6LvFVqW8crOFvN6ZIrsxNOA86HwsPbRrYTx2l7c9niNfvO46DTzH2BM9n4QBO0hWEb20a2G94xYMO5VJNzqFcLc8h/IlvQg4Dj0CoH48PLAhPDWoZ7oJIUU9MZWCu4Dqa7zx5ik8LeADPQTEBr2Xq/o74g2qPIB6wTvMrl69ajshu6SyjDzp7NY9t/YxPef6PTzVL6U8VTSWPAMi7TutHIq6v1fNvE9k8bxI9W49eInQu2UNFrz/Pbs91LaYOoHEmrwGrT09q5E5u6iWvj2Pq4G8PqK6PI1Yxjw98Rg9r3VrvT4SZTwcZeo6ytOOOpSYFb2mpKU8f3pBPPHmKbz2Q2i8D+gHu+35Fb2K7SC8BybKvKWbwzxGW5a8Jc9nPQU9Ez1xco68SY4mvYfypTxoIHs6zc6JvAl5Bb1V/IA8X0bTPG4WcbzyVlS8E5SkvLy0Ervu4sy4NipWvFhnpjwPF7u7JmifORQETz33vPQ7t/8TPWiwUL0c/iE8JmifvUOBZ7zk/0I8W0L2u3cQRL0maJ87ItTsvABHnT19f0Y9LJ8MvLLRCL1qMr+8deaVPNYY3LwDIu06XEtYPLhvPr3Utpi7PfGYvPHmqbyaNsu8Xp6TPF/WKD1dxOS8DBzAvFpZP70rJoC8i9bXPIrtoDuXq/q84BuRvOmFDjz16gY8MTTguwOyQr0K8pE6jE9kOq916zz4xdY81Q/6vI9KX708sKE8/82QPIHzzbyM37m72JrKvKl/dbzGNvo87cEAO1lwCLzIUSA8u3ObvJmOi7wQIJ072aMsPJTQqjupZ4u8A0KYPN5hjbs+q5w8HT+ZvDczOLwd3vY8U3EwvQ6eLryz6fK8U3EwvHGqozywhy8771vZO4OHALyEXvO882iYvGJBzjsoK4U9SW77O5GdGj17VZi8bZ1kPAMi7TlqMj+8/NKVPB/5HL2cwZu8AgoDvN0glrsJGOM8cYr4unYH4jtJbvs85RGHu2oyP7xgT7W8XGuDvMDwhD2vdWu9vOynPIT3Kr3XsZM9WM7uO5LeET1TORu93xKvPbRrYbxgv9+6+OWBPMbPsbyWUpm7eJKyO7dmXDz16gY9T8UTvAMKg7xDYJs897z0uWNTkrsAt0c9YcjBulpZPzuXq/o7iXSUvDU4vTyyeUi9ByZKvEj17rz7wFE9B7+BPGy9Dz1iQc48RiMBvI+rgbzp7Na8G00AvQS7JLw2sUm99EhtvIB6wbwc/qE6YcjBvCLUbDxHfGK8WUf7u7Jw5rxeXRw8+8DRPEj17rxI9e48wCgaPc8BGj1y6xq9tn0lvR7n2LzwZDs7T2RxvGen7r1VNJY7n5zrO8jByrtiSrC6RgNWvMTUNr1ZcIg8fdeGvAC3x7xO6+Q8mjZLPAcvLDzEpQO8hXA3vR/BhzxdJYc8nrO0PLZdej3uUvc80qTUvOhzyrzw1GW8t/Yxvd6ZIr2pf/U8B5Z0u/1CQLzlEYe8ex2DO9CpWT2aP608NTi9O5JOvDtur6g8NUEfvNWfTzwMHEC7c5w8PAioOD08eAw97uLMu3iJ0LyCBZK8lGAAPVRaZz2NyPC8UvgjvRjx4jvMjRK9YhKbvA+nkDxNCxC9gOpru9wXtLzxTfI8FYY9vTm1pr3OJ2u9mb0+u9uVxbzxrpQ8xb1tvSRWW7yrkTm8eQu/OW02nL31WjE9aAgRu8FJ5jqZjou8lJgVPOAbEbxosFA7Wlm/PHXmFbz1yts76ESXvBR0eb0n4au8/sSuPMkxdToi1Gy85XhPvHqESz15Cz+8snnIvGTMHjtxqqM6ZMyevIN1PL2mC+68OSXRO7jfaDuiMB69w8tUPDywIby2hoe8w1sqOz2ZWLy740U9Fo8fvd9597zOiI0852rovIN1PLs7N5U7nyxBPZaTkD0xVAu9QJTTO0IfpDy3Zly87WlAPeTQD73ofKw8x9gTPEwCrrwkdga9/sSuvA8XuztGIwG9IXuLvC0YGbyKtYu8MEspvYzfuTwFNDG9d+EQvcyl/Dwg4tO8iu0gvWen7rz7UKc86mXju3wGOj1yIzC91S8lPRoDp7ysCsa8XNstPatiBr0NJaK7Q2AbvDHENTzQqdk8ycosPbxT8LokVts8yVqCvO3Z6jtIhcQ8Z8eZPLzspz0T++w8ubmXvAHAKb3rd6e8UsCOOzq+iD2M6Bu9McQ1vYXXf7xcS1i82wXwvLlh17u5gQK95I+Yuwx0ALxW5Tc8k9CqPQI5tjwP6Ie7s/JUvQsT3jwXCCw8fdeGPAoqJ73i7f48pmwQPLxc0jzqbsU8yTH1PLNKlTxX11A8QueOPeJ91DxwoUG7g+5IPaYUUDx1jlW8t/YxvKM5AL2x91k8YhIbO8Nbqrt15hU9rpWWvCZon7zY8go8NL+wPBP77LyapnW83YfeO+Lt/rx++FK9ZMwePJfLpTuLZq28rNuSPDywIb2MT+S8U+HaO1TTc7yNYag8N8ONvYrtoDwkVtu7UUcCPDkl0TvGNno8Rww4PClD7zzjV4M9Dxc7PL42gbzwbZ29+1AnPKOpKrz7MPw6H/kcvSpM0by0a2G7acIUvSw+6jxoSQi922aSuy+aB7uaBxg9zQ8BPT3xGLs2scm8yBkLOxdv9LxOrE09kAWtPAAsbr3/UMq84EwCvVftALxpMY88Ly0RPfBOpjzFe7869NwRvSQjH70dzj29kUcXvHFj3TyJ1Sc8mNfLPEiru7tv8LY8GRv2O4RHvLuR1jk9xVZjPLwwdbyWBr88/qQZvLQtGr1Hht+8+4cLPTMlw7vqytG7Zfk7vZbreb23APC81XPMPPSSWTz+04y8kUcXvSdnUrxJfEg9cGEUvC6XV70peIA8oJ0KPGt9kLxwnOc7hCx3vOr5xLzyHzO9HNhUvWuHp7zH+Hy8tXmbPLZUPzyFYoG8DkcOPF/JNr097Uo8kHYKveACSrxl1N+8XvgpPUzlV7ydEWi9Op+AOxBJ1zvnfIc8ZhSBPFejSLzuJ4G8scZTuaLErzy8JJU7K9BhvCbFOLyxoXc8JnFpPaf+y7yq6p08weO8PIwZW70Eulk8IVypu1M6uTzhJ6Y8GRHfPMVxqDzxBO48G/2wu8VW47ySPQC8Ly2RPNY6Qr2ZnkG7VBVdvG/mH727af+85kZ9PBrWizyl/AI8FfwePUB7Nj3ZoQg9MvQGvNzILb3kmsy8lt8Zu4MWgDwEBJK6fEYqvUEbh7v3NPM8YwEKOzTRcz0R6/A5w88Ovc/v9zuGroK76u8tvLU5+rzfAIG86+WWvIRsGD2W4WK8bR+qPI0+tzsl6hQ8qP7LO8xX9bzkmsw7sesvPK8aI7tqApy8f7nQO+vvrbpu+s07knjTvMmzkj3kvyg93woYvReUoTtHkHY931YZPehXq7wHFwk9b5CHvaq7qjuolAW9hfNsu/Oc8LxNqoS8x/h8PESziTwnQvY86d5/vOS/KD3qytG8hEc8PEooebwpUyS7GwfIvJjyED0yJcM8+gyXvFpgJz0pLsi8RrXSOtRO8DxvnGe9tYOyvI0+Nz3uJ4G8+EWhuzMbrLy54iq9kAWtPCz1vT34dJQ8EiuSvD3tSru40fy8I1ISPBospDxaaj69TdtAPcKDjTzVc8y8V6NIvHQgPDvehYw6x0K1u+AM4bwwXs05/mR4PfdZTz0ZW5e9eqQQPW36TbyG8+y8YZrDvLmMEj2If488/N2jvE97ETzwc4K888vjOyexCr20OXq7MagFPd+FjL08vI67M8UTvbGLgL3eFvg6indBvEseYj1UFV28BlCTvRzYVDvTfWO8VTAivOS/KD0HUty6kLHdPCCLHDwM1jC93HTePPZ+Kz08Eic9Bnc4u4n6g7wV/B49bxUTPfkWLr1iRvQ8vibeO9S9BLwnsQo9QkxDvKnPWLzMq8S868A6vVwMWD2SPQA9+CBFu7OypTy1Ofo5GiwkPUUJIr0Npz29UE7nPEL4czxFCaK9Y2G5PE3A+zy8qSC9wr7gvIp3wTwyJUO8y4bovPZjZjyyl2A9HNhUPFXcUjweug89RQmivK4kOrzmPOY8iaa0PJyKEz3Sh3o8zVf1u+TkBL03sy492q3oPLJcDTwSK5I87mLUugzWsD26mPI8yeTOPDT2zzw6eiQ8HalhPF4dBj3rylG9majYvIGK3bzGTMy7vXAWOlFzQ723bwS8H3BXPW3VcbzFGxC92OZyPQ6dpjloahm+4N1tvHt1nbvCVJo9D0lXvPrAFTzDqjK92SYUvZFHF73oDXO8F5QhvTwSJ72pZRI9tGjtOvG/A722L+M8H3DXO9K27TxIoaQ7GG/FuxAk+zueB9G8kj0APboHh7wgixy9WztLPfZj5ryWBj88luHivIVigTxkDeq93MitvEzlVzz0ktm8Ux/0Omd2eTzI5E69t9F8vNkmFDtjVyI6R7XSPEInZz3WH3281EKQPDw3A7305ig868A6PZmDfDxSaay81mk1O0W/aTxv8La71h99va5TLT0iEnG9bMmRPNx0XjzHQrU8wr7gvHt1HTqVNbK7vuuKvXbM7Dwkz0+9rv9dvWelbDw1EZU7Fc2rPCraeD3ykBC8fujDOonVJzlyKIo80Qo9PZf8p7wyeZI94q56vUSzCb2O3oe8m8OdvRydgbvyFZy73Jm6O5xvzjy0IwO7dwwOveaGnrygzka8OZ8APatxcj71rR49NtgKPaDzoryKRgU9yOROvZfXS7u2L+M7i1LlPKuxk7vxv4M8HZ9KOivaeLv4+2i8YJpDvMRg+jzuJ4E8lyEEvXN+oj0oNpa8LlyEPGX5uzybSvI8+EWhvBdvxbw7QZq8YmE5vcR7v7ngTAI906I/vS8tkbzWCYY8bA78PD6+17y2L+O8idWnPMkuBz1+twc9AulMPNzILbznMk88wb5gPGdqmbw59Zi8b8vavOrvLbzwc4K9+CrcvOLT1jz9idS8GiykvDz34bySgmq8h+nVu2aZjLvq1Gi8L7KcvGaZjDuxxlO9tIMyPV3RhDzuPfg61Wm1PN8MYbs+2Zy8hEe8PJ2KEzt2kZm9pTdWPRAkez2qlk47TrZkPa0J9bwnNhY9ca2VPI40oLgzQIg8F5ShPdK2bbx7f7S8hfNsvNZE2byeW6C8xzieOxJahTzOlxa8frcHPQhtITuCIBc9VQvGvFo7y7u0sqU53WpHPSMtNrx/DaA8GtYLPXGSUL1DZ4g7PYMEvV+ucbwTvH080tvJPN5qxzyZg/y8+8JePc85sLx98to6AFFKPF0nnbt7dR08OfUYvABHszxyfqK8ZhSBu/9a4TzZJhQ9bR+qPB6VszwISEW8TdtAPeS/qLxl3vY8dvFIPJHMojxCQiw82txbvfggRTqp9LS7t/ZYPW0pwTzDzw48ngfRvHcMDr1C7JM74+6bPCr9CzzFloQ9AGyPPNHl4DuXpo89majYPOd8B73q+cS7Rv+KvPZZTzsnQva7k5OYvN2Po7w1EZW8C4AYPQAsbj3HOJ48uYySPRd53Lw8NwM7xx1ZPaVSG7yl/AK9/bhHvUInZ7tGtdK6TO/uPG1EBr30ktk87TEYPHbMbDuV35k7NNFzPa2CILyUDg29C+DHu/cokzzB4zy9X6RavNpyFTyE5ww87j14vVB92rozSp88YmvQPaRBbT3wKcq7NOw4PHmT4jy8qSA7wRIwPBPhWbwXedy8Qh1QPfTBzLxu8Da8hEe8PV3RhLtnapm8HJ2BPGqHJzt0KtM9X2mHO+EnpjwLgBg9XALBPBO8/bzJCSs8tSODPKmq/LxpMQ+9PBInPbxV0TpihpW8ga+5vMvQoDvj7pu8H2bAvDTH3Lz2Y2Y8OksxvX0hTj2Sp8Y8WUXivO6HsLzdakc9J2dSO3BhFLu3bwS9bUSGPJqeQbxaO8u6N45SvLOyJb0uoW689W39uuzAurzwKUq75ZC1O84ea7sGXHM9yeROvBIGNj3yFRy9U0TQu77rir0Gpis8PLwOPCn9Cztk0ha9D50mPLONSb2rjLc97WxrPZNJYDvRqg29HLP4vEExfjzoTZS8Z8pIPJ5boDx5rie9S+OOu4JPCrxO0am8SSj5vKqg5TsSBjY9x+KFvN47VLtwwUO9v7yXvPoMlzxGtdI5RLOJvMc4Hryjupg6giCXPLNcjbwL4Ee8jd6Hu9x0XjrQ7/c8n+J0POACSrwjzYa9ETUpPCNSEj1YmbG8KV27vCNSEr24ER47YXVnPePJP7pG5EW86d5/PAyx1LsySp+6xXGoPF9pBzxWJos8DYz4u31GqjxLQz47jWOTPDdpdrxPh/G8vDD1OqnqHb0mcem8pi2/O7uOW7yPKgk8fUYquSJcKTxBVlo8NREVvdOiP7zUfeM8lElgPQk+rjyWEFY9weO8vKj+SzxUFV28MVS2vNr3IDw87Uq9h+lVPFCitrwr0OG7OIQ7PKDzIrwZZS48qaDlPMizkjxw3Ai9NPZPvJ8H0bvL0KA8i1JlvcPPDjzQ5WC9mahYPSZlibuPKgk888tjvdWYqD1DEzm7U2ksvVbSuzzfYDC9VvcXPKHEr7ueNsQ8K/W9PH3wEbwEBJK8GTY7PA7Cgrt/3iy9lgY/PTv3YboLu2s8f5T0O6jZb7zswLo86Cg4vdPRMrz8WBi9+sz1PHX73zyjNQ09ynoIPYCIlLw+mXu809GyvMc4nrwaB0g7pyMovXquJzvJkH+8tXmbOhv9sLwNjHg6edODvEwUy7wXPgk8PDeDO6RBbTyg2F28OF9fuuql9TwDBBI93woYvbqzN71W9xe8RtquvEeGXzwpeAC+No5Su8A3DDsizYa8az3vusc4nrtEswm9aJG+PK39lLyTU/e8BqYrPLHrLztv5p88pGbJO8f4fL0E1R4991lPvM5oo7pMwHs9ZE2LPOql9bxzfiK9Ux/0vEfQF7219A+9jg/EPGh2+TqyvDy88tV6vI3eBzydEWg9NtgKPBzOvTtt1XE84ALKPMyrxLwqLkg8YWtQOxosJDyPD0Q93wCBPfG/g7tmmQy8JBmIvDNAiDxaO8s8tkqovIfpVb0ZEd88QUxDvX/erLxsWDQ87oewvNOsVrroV6u8WxbvPOdXK72FPaW9LrwzvfLwv7t88BG9cWPdOxsHSL3A92q8/bjHOz+FTbsHF4m9GwfIPJiyb7vfAAG80rbtvDazLjvC/gG7TaqEO2iRvjxxrRW9+sz1O8EImTyblCq9QGDxvOdXKztqApw7j+DQuy68M7zNoa08MVQ2vFETFL3HOJ48Fc2rPJf8p7x/DaC8R0sMvfj76LvS0bK7hg6yvHhYjzyzaO27dxYlvT3jszofcNe8e380PXJ+orymCOO8JJ4TPInLkLwslY48Trbku1MfdD3B7VM9MI3AvHDcCLbcdN48sBAMvSQZiDwxL1q92F8eu1BO5zzqytG7c1nGvBAaZLwmcek5icsQvYt3wbp504O89q2evMGyAL3WRFk8bMkRvUh8yLyCIBc9HcQmvY7qZ70V/B69CwUkPdRxg7zfYLA8ryQ6vS6XVz1Vt3a8GUDSvH4XNz0vjUC9DLFUvABHs7y40Xw75oYePNAU1DwQP8C7/n89PPj76LzS0bI78E6mO+gyzzzY2pI9u19oPLq9Trs9CBC9HNhUvMm/8rzbo1E9fRe3vHFtdL1NAB06EevwvPApyrxIxoC8icuQvP5/vbpkKK+8HcQmPJf8pz2w6687DLFUvBeUIb2W63k809EyPOzAujyDW2q95gGTPePumzyWENY8ZQPTPNx+9TylN9Y7g4DGPEWEFj3TrNY7vHotOiZx6TycQFs8K9p4u1YmC7xQQge9q2fbPKOLJT0NdoG8ZCivPGXedryq6p285OQEPAPE8Lu57ME7EA4EuzBeTTwk/kK97JtevQvqXjp2zGy8IIscvWusAz1c53u9NNFzvFejyDx3DI68h8R5PML+gb0CDqk8kOBQvaRmSTx6ric7rEJ/O5iy7zx357E86E0UPbqOWzkPbrO6kj2AvUSziTyHBJu7nG/OvDURFb1KKHm8/tMMPG7L2jvJ5M48CyoAvdvtiTxWrd+7y4boPPApyjwwaOQ6kp0vOzpwjTxQTue8wsIsPfYkzDwJc8S8lYc4vFR2JL15MIs7gjnAPKiggD3AjSs9FbHLvA2olrw2rji9wI0rvY4kITu67ic9USPcPCc7sLytzpa8uAzNuzhUp7tEdGe81RAlPXoSlTzujIS8XJ1PvK3OFjjd5Km8gSIGvbGpNT3LeAy8ZgAJOVKUSbzBUT+9JZXBu50mDT3rqlg8/HCpuiVCm70Uz3C81tQ4PRzBPLu210u890KTPN3kKbtt8oO8SDidPHlH9LybJry8NZBxOzauuLwgutG6xtL7vGyYfz3e5Ck8TirHvGjbVryDOZG9D92XvD9G0bwJc8S8tRM4vJU0kj0nHWk8USNcvWvU67wZquA8D90XPd+/9zy19XC8poJoO5Idh7xEsFM9e2WMO/hZTbzLloK7/RZ2vI4koTyBday8QNUFPTYB3zy+WCq9qrcLPWTLh7waOZU85imcvCC6UTx0AiQ98aMPPCz42Ly6lPS8GlcLPbYTCbu/OgW9PWR2vA2oFrwt2jO9HKP1vNPbozzVECW8b+tHvFJBozxBCmU9QdUFPB7Y9rxhy2W8xIYRvYsrDLxS5288UAwiPMYsr7yiNq08OOM5PK3Oljxij3k9vucNPE59bbw4NmA6x/BCvAUJwrtpNYq8BJjUO45CF73HLIA9OafNuwUJwrsALlK7VjoJPKrs6jz1s9672wJPu+zIH7xsmP+87qPtvNuvKD0fZyu8s22aPH58F7xLhFg9cSBJPfkdYb2j+sA8pb5UPe9QGD3q5sS8HxQFPRH0or35HeG64IoYvBTP8DxGdIk8WG8KvWYACbwNv3+8NZDxPCulsrvOjxc9qSjXO7gMTTwEmFS9OjaCvOdA1jrkR0G8WG+KO/ScJL09vik7braXvK3OFj2NYA09h8GJvVzZjLqIhZ088g3wvL7nDb3SFxC9o6eavMGk5TrTgfA9R8evPMbSezxDA3o5+QYnvCrhnrzMWha6vCMpvYzvHz0fZys9m/GLvSZZVbwxJu87SU/XuvO6STyP6DS9jkKXPL5YKj1gWvg8qIKKvW62RjzfqD08MICivKhkwzy1hCU9T5u0PMCNq7xACmW6DjBtvFWN3jy/b+S8oXIZvTTqJLx5MIu9t0g5vD/zKr1NuVm9yPCTPCc7MDraPjs9RnSJvKlklL2FjIi8PImovO6MhLtLMbI8brbGvM/ERz1zVco7uu4nvcrp1zsQvyE9GDlzPQtzlTzUn7c6KR0LPYf2aD1ykba89bNePTdyTDxqvTG95QtVPYEEED1IxwC9mZ6UvMo8fr0WIjk9zq2NvFCy7ryfH9E7g4xmPOZ8wjyXaRO9BlxovVrCATwajLs7rbAgvGxF2TpM9UU9dk5fvUF70rtVBQg866rYOxK4Nr1L3os8nESDPROa77pNZjM8yjz+PIjYwzw/gj08S9d+PTdyzDw9vik9I36HOncZAL23m1+8iSvqPP2H4zu210u8MtMZOsPZ5jxwr9s9TKIfPaqZRDxsmP+7hMFnPGmfarz36N88ouOGvbmbAb3fGas73vvjupA72zv36N+8BJjUvGuBRT2/OgU9ZHFUvTNEBz0ndxy74xIRvqcvE7xVjV48LEt/POODrTuikA88j+g0vUR0Z7yYLSe9JCTUvHtljL3PAAW9dsYIPctaxTyAsRi6Yo/5O+mxFLxp+R09FyI5PPL2hrwJVX28HoVQuxOabzzoBOq8ODbgvDKXXDxUyco8/2m+O9OBcLsTC128EDCPvev9/rwVXqW6VjqJvEfHLz3bXII9Wrv0vKl7fTs6a+E8ko4jvUWSLj3lXns9SItDuwAuUjzaIHS9QZmZut03UD2sP7M8ByD8PMa7kjyVNBK87xTbvJP/kLwZqmA9UdA1vVCy7rsjfgc9upR0PbLAb7zpddc7p0b8PJnTc73XRaY7Bev6vAAuUr3+NA68AyfnOzLTGbx0xjc9dAKkvEg4HTuqCrK8qpnEO9+ojjzEnXq9yQd9PS5pl71Btw+8SaJ9vN3kqb1QX8i8afmdvMDg0bwNGTM9MdNIvLgqFD0gK7+8rZJZvNhc4DzSvVw+Qc54PSWzCD0fZ6s8ShNrPQzGjLyceWK8e9aoPGTLhzwd3wO9sFYPvYLmGTuQWSK9CsZqvG/rRzxYbwo9k/8QPQxs2bxCP2Y9CpELvDsYjDxBt488gXWsPOBs0Tzivxm9wsKsvFoVqLy3m987JpWSvLGptbwVQN47pb7UujCemDySHYc7zMsyO808IDqIhZ08FV4lvR9nqzqIhR08KuGevEfHrzv8HYO9uwXiPDauuLx1N6U7kHcYvYEEEL2Go0I9YAdSvEBGUbwE1BG8EwvdO/ScJDwJrwG909ujvJCsSL3Saja838YEvUBGUbxM9UW8LBaguggC1zzsG8a8gFflu32aDT1qvbE8yPCTvAo3WD2wdIU9ocU/O6RN5zzHnRy8M1twPKDjZD2MfoM8VecRPMcsAD1yc+875bguu5EdNr2//na8Wrv0vAZcaDsc32E8SItDvB3fA7uhchm73TfQPBAwDz20oko6tKJKO8cOCj3u/SC9afmdPDjjuTyLfrK861eyO76rUL0IXIo8XtJQOe3f2TtLhFg8MJ4YvfAyoj0Smu+8C+QCu7gqFD2JnNc7PRHQOrwjqToaG848nSYNvcdDabxDXa08aC59PRbPkrr078o7AydnvDoYOz320SW9Kf/DPGsuH7zmz2g866pYPEmLlL2HhXs8Nh+mPOqTHj1At748yzz+Ot+ojrz2d/K80y7KPNnNzTwKN1g93HM8PazsDDxBmRk9O/oVPUyiH7y+5w09Buv6uvnKurzwhUg8gLEYPOxXgzxiPNO7MA81PNTyXTwIrzA9YLQrvPQrCD1e0tC80MQYPJHKjzxm+Xu8kzRwvNaBkr00ebe7UpRJvFgzTbrdN9C7amoLPctaxbu6X5W85JrnPAzGjD1BKKw855N8vCwWoDsfSWQ6ypYxvfDBhTxtCe08toQlvBNlEL1hJZm8TtegPGlMxD2ybUk9iIUdvUI/ZjzpsRS8/HCpO324Az2/OoW8Dt3GuwuKfj0VXqW7ypaxvDAPtT12Tt+8MICivBvfYT3dc429w9lmPRobTr2ZnhQ9lWnxO3U3JT2SHTa7x52cPAcg/LuIFIG9j+i0vMOGQDxpF5Q7g4xmvPQrCL0vnkc5Ca8BvVn34LzgMGW8D04FvXb7uLvbVXU97d/Zu+ftr7ymoK+8I9GtOzMmkbvLlgK8KVLqvI4kobzPxEc8y3gMvPAyorwG63q96bFDu9o+O7vvbo68oa6FuwZc6Lq7QU68hoV7PeJl5jtau/Q8XtJQvdl6pzqwdIW96pOeOjxNvDyK730955oJvX+T0bv74XS9TEhsPElPVz3LeIw74mXmPBgiCr3bPow8/0t3vDTM3btnxJw8lMOkvOT0mjs7+hW744OtvNIXEL1I3mk8x50cPOK/GTwhnCy8zY9GvZb4Jb2DVwc950DWuWBaeLxhJZm8nSYNO8taRTyo1bA7rc4WvfqOTrvBUT+9ay6fPGam1TywdDS7Pk2NvRd1XzzS+Zk7sRojvf740LzoBOq8zwAFPcSGET0ehdA8DMYMvT1NDTzd5Km8cK/bvHtljDzg3T48cOsYPRyMjDyv5aE9wVE/vABqDzwy05k7WIZzvKOJ0zw6NgK9c5EHvY2VbLpL3gs893dyvER0Zz3CaPm8pb7Uuwbrer0e2Pa4PE28PAW2Gz3VY0u8fO1iPdVjy7wXkyY7iSvqvFxKKb2IhZ28Yo95vUQDejxZ4Ka66+aVO+nI/TyCjOa8/HCpvL0FhLwNGQS8iBSwux0yKrygASw7uu6nPII5QL0nOzA7jA0WvVzZDD3LB5+8LdqzOmjbVr0llUE9Rc6au0z1RTz+NI488DIivSrhnjx3bCa8Ap8QuSFJhjx6Zbu8V2+5vPMrtzzqk548EL8hvSRgkTvMHtm7qNWwPN5VF7tj6ay8XtJQvMuWgr1EPwi99ELxvAmvAT1K/IE9xywvPWBhBT0vvA69M0QHvRYE8jxPm7S8VlFyu1KUybz5d5Q8HaN1vOuq2LuHwYm8Rc4avCcGgLyHo5M5TirHvJVp8bpqvbE8IkL5vClSarxHGtY8+ugBPDvcTr0Cn5C7yGGwvABqDz39FnY8/lIEvodQHDyezCo8TblZvH+TUbwtpQO7hFB6vLhICjw0ebe8KOF8vUvX/ruka648MA+1PMuWMbwJIJ68xtJ7PJee8juhVNI7FM/wPJb4Jbv2JMy7LBagvKPFEDyvdDS9OmthPCk7AT1qY348wsKsPB6jl7v0fl28IZwsPW22xjupe308P0bRPB0yKjz5yro7KXAxvCisHbzdiva8tYQlPV/wFz2iGGa7h2dWPCtwAr1awgE9x52cvOH7Bb2xqTW9dMa3PMo8fruT/5C7ytKdPNK9XLxKbR68GcgnvOZ8wjyhxb+9VqulvWyBFr03xXI6qXv9vGJ4ED1EdGe9efRNvQd6AD2JSTG8CpELvTEm77pYbwo8PE08vJU0Er2vIQ49VxwTPW22xjv8cKk7k/8QvdonATx7ZQw7QLe+vK2wIL1c2Qy86ATqPEQhwbwQgzU74d0+utqR4bzpyP28/Rb2PCJgwDpq+Z27DFUfvAXyB71YM827NHk3vWPpLL0/RtE8724OPPz/DL38HQO8QNWFu/eVOTzJB/27sHQFvZP/ED1zkQc9F3VfPQ2oljtZpDo94vuFPe3f2by4X3O8vliqO2RxVL1Gqeg8Xg4OvaRNZzxc9wI8WIZzvK/loTxsmH+85s9oOxobzrzLlrG7MdPIvAzGjDvI8BO97BtGPV8sBLxpiAG9pRH7PLruJ7zHQ2m8poLovIzvHz1V5xE8l57yuTygYr13bKY8e9aovDdyTLwHzdU8emW7vHe/zLxQmwW9waRlPMYsrzzYCbq7eUf0O1LnbzwPTgW9btSNvMZ/1TzgMGU8ig3FPUEorLy03ge6N8XyvGC0K73j1tO8MfEPPMollbw2H6a8kh02O+zInztj6ay8yGEwPAgC17wnBoA8q13YvC/ahDuXh4k9qgqyPFAMIjyyqbW9r+UhPbmbgTsSuDY853yTve2Mszz5Bie8rbCgPG7UDT3GuxI9GargO7gMTTzIYbA8WOCmvK4DxzuBBJA8gAQ/PX9AK7weoxc7I7PmvFHQNTzJeOo8hTLVOlhvijxtY6A7rbAgvJNSNz3K0h29efTNu7PeNjwLin67iysMvRK4Nr0iYMC86cj9u903ULwZdYE7G/2ou1dvuTvdkQM8DFUfPAZ6rztEzpq9idhDPPScpLvHLC89sIvuO5b4pbv4WU09jrOEPD1k9jzuUEc8f0Cru/v/O73QiNu78fa1vCs0xbyrXVi9nsyquRo5FT15R/S7/2k+vPINcDwXdd+8AxAtPCZ3HD1wCQ88E0cavUC3PrwK5LG7hYwIvINVp7iauYE7g7j8vK2b8LwoGtK8mPhLvYSyCjzsGxc9OwQtPeyw1bqYXB696vcLvXzSW7zmSyM9BxeNPFKMEj09jIo6MGTFu7MziTuSPaW8jDvIvFiN8juBcOY8fu93PBQ+VTrlLgc8t5+qvAaPL7ztFCg95rzWvGJmMrwgXyu9dVCNvaFCvzzl9S49SRclPGDX5bsqN+689Agnu5OTGT0jGHU85SApvUTc7zzUKPC8Ny1KPIiP3zykilW8Bx3/vPy1b7wEZDW9XxC+Oy3xtLw0rFs9zIKWPEufAr0n79e8gA2RvZY/ArzpBG29q+ImvcIGOrxbOds8jGZCvCy4XL225eO8XfOhPJV33TyJ5dO6IDSxvBnc3zrfyFe89cFwPavpFb1Qp9G7wLDFuwuRjDvtsFU8kW8OvZyktDvL7Fo9hFUnvS85Sz2Zjoc8XY9PPADxpDw39PE7yToAPSzGOrvi3wG8WRy/vGuiRzxDhns8WzlbvIuse7z3e7e84PNRvX6+C717p2E7N8MFvOtaYbyKUJU87zFEPBEvFz1szUG8vBK7u/TPTr2Zv/M8NOUzO3jDHT0sVYe8+1KaPLRegzwaayw8cc+ePbAc3zzfATC8X0mWvDwvJ7yLrHs6SwlHvNap3jyY+Eu9G5amO+ZSkrvB2787AqpuvOnMETyMn5o8J4yCO2S8JryMn5q8bk6wvDs2Fr1tXA49KtQYvT2FGz3Ahcs8CBCePbefKj0i7Xq9akxTPViNcj0pqZ68BoFRvAy1Fz1m2cK9mVwePMVOUL3unIU80UQsPeAsKr0gXys7flPKvIWAITwFyAe8lzGkPfGyMr23EN479V6bvT1aobumGaK8NBAuOfRlCj02kZy8puBJPCzGOr2M0YM80FKKPWqiR70jp8G6FyMWvCQSg7sIEB699cFwvC1VB7zEwIA75ZHcPd6d3TyYXB498MAQu+3bz7xLmBO809L7OwuRDL2a6u08RaQUPaOYM71yLAK9XiULPErQ7ry5yqQ5kQTNvHdtqTsGuik9lFrBPPRrfL0DTgg9EMvEu+nMkbwqcMa8BWS1PD1MwzwUdy088zqQPMekxLxkGYo8zgMFvT+iN72Tmoi7YljUvZ4lI70BHJ+8hd0EvQjlIz2fgoY8f+IWPQjXxbwsjWK9tkk2vMvsWr1okwm8lj+CPPZeG7wxVuc8dd7cPLKrK73irRi8ZtlCPRSpljz7Uho8EfY+u8FM8zyeVww9TxITvT2FGz0n79e8vT21u+jZ8jxHJQM95ksjvYw7yLz0ZYq9JTaOPX+3nLwWW/G8DIMuPKVLCz3bgME8xuSLvcCFS71lEps8NQJQusWHqLw79s47uS16PbfYArzGuRE8M0mGvB3evLx7p2G8ZOcgPavpFT31kIQ8daaBPP82Xj2Lpgk6ufyNPF2PTz10UA09Bx1/PZKaCD31JUO8qowyvHP6mDziSca7q6lOvI6DXrtU2xc8uDvYPasUED1VqS49VOIGvZXpjbyomhC92WMlPVJTur0vRym99TMhvLMzibyCm2A87dtPvLoniLtbnS09q6lOPD3ocLxVcFY8NpGcPIumCb6YXB69T+ApPJFvDj0BHB88hON2PDdYxLy2rQi8kQTNvC6q/ruAfkS9e28Gveb1LjsBf3S8Mh4MvarplTxnLze8KmLoO7/2/jwI5SO8tbppPDp1YLwQBB09V8bKvGUSG720XgM9+/wlOxoyVDxP4Cm8ztGbvAjlo72Xole9BlZXPFJhmDzlJ5g8xFwuPeHl87wCR5m77zFEPaP8Bb3lkVw9mk5APcWHqLscwaC7GpYmvTnZMj3idEA9LbjcPJ5d/rvdcuO7yGtsvA8Enbx67he8jpE8PRtdTr2LEE47oW25O1Cn0TvJXgu9LFUHPU8LpDp3ygy86NOAPJxrXL2DuPy8GjJUPM3YCj3WG4+89omVPUJVD7yZv/M5ES8XPWdaMT3oPUW8dFANvZQhaT3kyrS81qnevNqOHz0aa6y927kZvbW66bue+qg7/qgOPR3evLy32AI9lJOZvJHZ0rz3tA89RTJkPu3bzzy3n6o8fZORvGiTiT0BjdK85ZFcO84DhTwLZpK8vQTdvKtFfLy2SbY7SwnHO4EUgLtxz548aSFZPPHAED3HeUq70zZOPcC+ozz87sc8TnzXPB566jyIARC7X6zrvKcLRLwvcqO72NTYO8Ki57xnL7e84VckPE21Lz06dWA8PC8nvNT3Azxz7Do7n1AdPKPDLb1hOzg8Pne9vHHPHr3alQ68LhwvvQN5grxbz5Y775wFOmODTrxGMmS99pCEPVDSy7yPvDa9EYWLvIANEbzPX+u83p1dPMlei7wN5wC9eJgjPEIqFb3iScY8SnSIvHdtKbw0EC49An90O2sGGr1Gazw98nlaO/9hWL2dMwE9tfNBPT3ocDzypNQ8SIjYuwEcHz30a/w8KX6kuyRD7zyx3RS8r1W3u58lI7pIiFi9Rs8OO9I2zrpg1+W7br/jupRaQbs9vfY7hqsbPBMTWzxmBL08nQEYvAwfXLk2wwU98Ic4vQwfXDzJluY87EYRvRQ+1btnBD29Dq4oPe1xCzvAviM8WwEAvIp7D73O0Zs9pgtEvSQSAz2H1pU8uS36u+UgKbxmaA+9D8vEPP82XryFq5s8Oz2FPCpiaD1iZjK8wqLnPKLRC7z+qI49vS/XvDVmIj1zwcA6Cy06PYL/sjzTzIm9aqLHPF5QhbvK+jg8biO2PDthkLp5wx28ibrZO9DDvTygs3K6kmgfPWItWj1xz548yKTEO1xWdzwJbQE8VXDWPGV1cDztcQu9OK64OrYevDwxVuc81hsPvexNADtQ0su5gyotPb5orzzq9ws9QfirvFvWhTxL0O65sgiPvHUXtbqRb469uJ8qOvKysrxT72e8ZgS9PLCAsTxXYni8riq9vNDuNz1Zh4A9YcqEPN4BsLxRKMA7XxA+uyRDb71CI6Y8OwQtPFE2HrxHlja9qDa+vKp+1DvsTYA9KBpSPUTc77xKdAg7th68PNvrgjy6IBk9haubPAPVaLw7oFo97mocu4umiTsvcqM9eVFtvf/TCL1Js1I9ztiKvWmwJT3UxZq8f+mFPD8+ZbprzUE9ekQMPEBp3zy8Ejs8Ff8KvcGwxbwSsAU9LFWHO9kqzbxfSRY8YTs4PN4BML1vqxO9GE4QvD8+5bz3tI+8HYjIPe5xCzxKF6W88E5gvcIGOrzIz768AJswvf3gabwY6j290bVfPQnXRb1Y8cS8DzYGu6zipjyx1qW7M0mGPDwhSbxtlGk8+dGrvHEBCD3Z/1K8tMjHPCLnCL3s6S29W9YFvMbkC730z0470UQsPaPDLb11CVc8tUm2vMolM72NAvA8RQfqvGrijrxc1gW97dvPPJn4S7rSNk68iR6sO/Vem7w+6HA7O/ZOu5ESK737w029FobrPPRlCj1eukk85654vMLN4bwLyee81CjwvBQ+VbzuP6K8IJgDvb/2fjztcYs8GzJUuTQ7KL3t2887Pnc9vVm47LwOdVA8QSoVvMzefL17b4Y8+W1ZvHun4bv3F+W8sdYlPNvrAj1WDYE7Bx1/uq1qBL2Vhbs7RWs8vAy1l7yOkTw9vD21urmRzDwJEJ68Wg5hPSK1H7tEeZo7An/0uUVAwrwn71e7rNRIvI5Y5LzXfuQ7r/HkPLfYAr0gmIM8W9aFvAEcnzox8xG9xYeovPqY0zxiLVo9gtQ4PHrgOT1ylsa772qcPOGCnjtxzx6972qcvKg2Pr292eK66D3FvKGmkTul4Ek9JEPvvEBpX7yZv3M8KLb/Oy85y7xf5cO8/282Pd4PjrzlICm9MfoAPCGKpb3sTYA9VUXcvBSiJz1iwxW9JmEIPXJdbrzB6Z08Pz7lPMlei7z2Xhu8fZORvNpjpbwUoic9W2RVudxyY7q6WPQ8pbVPO7ifqjq0j+8705ogPEUH6jxA2488PC+nua+5ibuqtyy9DbyGvJSTmbxB+Ks8XbpJPYFwZj3/xao8A+PGvE58V71jg848f+KWO56W1rxNX7u8HOwaOwMOQb3irRi9KgYCu0LqTbzVKHA75ksjOv4L5LylIBE7DecAPUsJR73qL2e7t9iCPF4lizw6dWC9ESE5vWt3Tbz1+si7Q4b7ukSrA759xP08Dzx4vEw0wbwxj7+77j+iPIpJJr3xhzi80m8muw5ncr1R0ku6QAaKvFgqHbolbmm8r1W3O9uOnzyfJaM71hsPPCCYAz3KweC7LzlLvOX1LrzlJxg8ZOegvELqTbyRPSU9/zZePO9qnLwdiMi8lXdduCZhiDydz666ExPbPG/q3TtSKEA9j0sDPZawtTsD1ei8lwYqvXfQ/jx4mCM9CEj5u1CnUTunC8S7cQf6PPUlw7wvRym8JsTdvBFaETxXKp28mhXouyzGOrwuqn681lNqPE98V7s9TMM8ff3Vvc0J97zo04C9Xh6cPKp+1LztFCg9p6dxvUjBML24O1g7wbDFvMHbP7vy3Sw9xer9OxlrrDiAFAC9+8NNPTIeDLwPBJ28R8EwvBC95roJbQE8nlcMPIPGWrw52bK8n+zKvMVO0DzJ+ji9BY8vPQTVaDrQwz29hasbvbogmTzoqAa8MM+GO7MBIL1DFci8QfirvFYxjLxNUd28om05PFab0DyAFIA8sdYlOyga0rwPPPg849gSvP5EvLwrm0A9+ELfO//TCD0njAI9moeYPOKtmD0wnR07fmGovGhasTxPCyS9KLb/PKmMMr3Eagw8jQJwvFpyM71ziOi7za0QPOUgKbzyDxa9wekdvblm0rqVTGM8CjuYvOtaYT3AsMW7rOKmvGJY1Dyq6RU8KtQYvfaJlbtL+2g8v4VLPBkVuDvjnzq80zbOPDxaIb1naI+8JmEIPVzWBb2fUB28k2ifvP/FKj0jp8G84knGulXihrtnLze8yDMRvQIOQTuCm2A87gZKPFcqnT3UjEK9Ci26PK4qPb3KJTO9FWlPvYumCT1MNMG82HEDve6idzymGSI9km8OOimpHrvsTYC8r1W3PDz2TrrQJ5A7lXddPeg9RTtoL7c6wIVLve0GSj30a/y70FIKPdyru7wgkZQ8Eb3mO5j4yzyx3ZQ87E0APQNOCD2KEE48i9f1PDy9drzKweC86cyRO7VJNj2bpDS8JdI7u/Ok1LujmLM8xMAAPUiIWDtjWNQ7kdnSO4/nsLybFWg9g7j8vGz4uzyznc28JmEIO/Vem7wWlEm8q7csO7HdFL1aDuG8GjJUvLAcX7wWzSG7gH7EO0lCHzwn71c8t9iCvZCu2DyDxto84oIePRweBL19/dU73gGwPAN5gjziSUY9ltuvvMVcLrtkSna99uxqPEp0iDzlICm86KEXvU/gqbyDXJY8vT21vPOkVLsS6GA8Hgk3vJzPLjyWDZk89Zb2uTMQLjye7Mo7rNRIPOihF7xuSTk8SrWeO0u1nr19d5W8KXaLvMyZWLyIiwo8WquOPR1k4DvBEI08D95IvUlFxrw0N0M8kofiO2RR9TwwyNQ869lVO+iFuLz46wC9Qb3aPNxUqLzmwFg9e7R/PGqFwzxwSM880LJVvMC9z7xXdAy94/qYPMK6m7wQTqG8c5zsvIVxo71fGRO9oCjLvC4Ddbumls+8wRLXvEwKJr1ALh09XVQzvKoE1Dzg+wI9VwGAvUJIhDylXJm7ChrTvKEnYbyWESK9t1C1uxkrFDyh0tm8FfdFPV05Yjzrn5+8u00BvdiQsr3djl69vxPBvHvPULxuSbm7HNUiPfq09Lxf/sG8oXsIvTprET0cKio9WzgCPT4UNr2qBFQ8l54VutkAizzF1AK86fUQu5W8Gry9o+i8S5gDPcMR7bwMbRA9rq14PdJamrzg+wK9qcuHPMScFryDAjW9t1C1O8jwszuLiqA93hkIPWKn5rwLwwG9QYMkvZCGgjzBEte89rXeO2JSX72urXi98JsBPe6eNTtoavK8NIxKPYrgETzk+3g8ZjEmvTI4Lb2DHQa6otCPvMDYILwimK466i9Hu/Zg1zxAEQI9PRQ2O3JFmzwimK68ZjEmvEp/fDsrWAa9OvgEPCZcpDtOJI086L/uu4lwOT0x46U8ZMHNuVqP07z9eOq7sOOavDyk3bo3NI88KrDBPEhhAT2Kb0+9o5e5PJCjnTwbKio7v033vKewNj1dOeI8bfSxvLByWDyKiqA8U1xvPRzVIrw4UEA7yPAzvf546jyo6uy8BVfHO+RsO73Ml4676DCxvNr/oDyJGsg8BxynvBsNDz3ugvo7V8mTuTIdXLsc1aK8BB0RvUjVbTzdjl49fOohvV1UMzyxcti8rq34vFcBAD3Gm6y8xdZMvcjwMz20p5C70bLVvACRhzxyDa8828n+PDbfhz1kMhA90iKuPDsVIDzTBvM8mWU/vFJbDzxjUXU7U+iCPX/oTT2BOwu9ZBc/PDPiOzyle348if/2vH949bw+FDY8R4BmPUVHmjwZ1oy9ADyAvIgbsryhmCO9ApJnvP2TO7yVvBo89GHBPAoaUzz7edQ7U80xvKmUe7wnsSu9MHNNOvUmITzeUz68aYVDve5IRL3I8DO9wWdevZCGAj1XdIw8YhgpvWgwPDwaK5S880ZwPBllSj2y4jA8EE6hPUmbNz3BEI28wKJ+PcRHD72ksoo713XhOw2Kqzp+r4E9+UCIPcyZ2Ls0N0M9L+SPvKB90rwUMXw9uYrrOzNwGb0OpBK8ADwAvUARAr214UY6aNs0vCN88zy9abI8gjxru7tPy7xqhcO8C8MBPU2ZYzvbqpm8Hu8JPeBtpT2buVy88Q2kPH3OZjxkbMa8vfhvvISRcjrjMoU8s3HuOvWbdzweY/Y8ILh9OnklQrwqP/+8SCmVPMjTmLzDZnQ7QhLivPRhQb3ZdPc8x34RPax0LLsXS+O7oyb3O3zOZj3mwFg8bJ8qPCwfsLzgUlS658DYuuYxG7zjFzS9zl44vT+EDrsnlBC9T84bPYepD73I1WK9KQVJPSJ7Ez2F/wC9LB8wPTDjJTwIqRq+RtZXPMPXNj3lhiK93410vJK9hLpH8ag8YlAVvS0EX7tUzEe9UXiqvKJCMr3KtRO9p7C2vP6uDDyZEDg7z13Ou/0+ND1ZH/s8uTR6vHw/qbx564u7+OuAPFN3wLxvnsC8G4AbPYDmAzyBOws8i2/POSrqd7wKNo699iYhvYqKIDzx8tK8o0IyOkYrXzwRoyi8V5EnvFgeGz2JGsi85MFCPaewNj1LtR69+yIDuyiV8LxYynM67oL6PI00Lz0mXKQ8/eksOwWsTj06FaC8q62CvCN88ztPJA29l9aBu8ItqDyh7So9Q4I6PfS2yDwIxjW8BlbdvDHjJTsEkX29im9PvK10rLx1fB089QtQPJO9BD1Dgjq9DG/aPBZKA7yeRAY8zeyVPB25Z73B2CA9TV8tvVFdWb3naue8qJObvRVnHjwT3PQ7ZKb8PPVg1znkhww8B/+LPPl6PjvYdeG8Qb3aPEJIhD6FxxQ9qOrsvDBxgzzI1eI8oNJZvWYxJj3tLJM8RpwhveaGortDgjq9Kup3u3jQOj1Z5UQ8Q7zwu6VBSD2tdCw8D6SSO4s1mT3PCEe9snCOOmOIgbxFfwY9UniqOzdRKr07FSC9gpLcvAHoWDyK4JE8w9e2vKutAr150Do8LQKVuSFDpztM71S8IwiHPJ1jazyBO4u8YlLfPNxUqDovOZe8Nt8HPLeJC73eGYi7MMjUvNXJCL07+IS7WzgCPKTRbz2oWy+9kTLbO8rvSTyDHQY83m6PuXhemDvjFzS9rzkMvcEQDbwtApU7tBt9vJURortGK188KlrQPNGy1bzIKuq8fXnfPG0u6DtKYJe9f838PLtNgTz3Xg09dPFzPQCT0bzdOG09q8odPcC9Tz0lspW6zl44PZShyTwh7h+6aYVDvX13Fb2RMJE8KrBBPHKcbDzGKQo7Vh8FPbAd0TysH6U8uKW8PMPXNruAAx89CsXLPL1MF732JiE90c2mPPPSA7ywOCK9BQFWvEATTD1j/O27j217vNNcZLxPJI27CFVzPesuXT1Lms08K3UhPfRhQT340C89hMcUvCgGMzyFVtK87i3zOvV8kjv/Ivk7DDUkvCKYLryyxZU7ZxSLPXdg4rz+zfE8XxkTvVNc7zv08P663ONlvW5kijs2Nlm6IJkYPUUsybjA2KC8MY4evGz0Mblkpvw81pGcOt5TvjwRo6g9jxj0PAVXR71GgdC7wL1PvZe7MD1MCqa8E2iIvJkQODsjXY48cJ3WvDtP1jt5QBO9oZijPFCzSj1X5i68DBgJPT73Gr0mBx08GYGFu9nlubyvjpO8tFIJvfezFDldVLM7E023ueaGojtNX6086Wn9vBGjqDwnlBA9Aa6iPP0+NDwl7Mu8bIIPPYDmA70msau8xivUOyeUEL1Bvdo5WDu2vRllyjyGq1m8WMrzPdQhRD0GVt08kdsJPfCbAbxKRUY6zLQpPSnq97yycA699yU3PUXyEr2nW686gOjNPXZ8nbtv80e8LK/XPHwk2LzBuwU9s1IJPNfKaDyT97q7SppNPVeRJzwS25Q9lEzCvLn6Q70k0fq87i3zu/3pLDzPIxg7InsTvAbHnzvsLl28+gn8ubLH37zrgoS9N1GqvDEbkj1exAs8WMrzu2qgFL3zRvA8MeMlvcq1kzub1Rc83+L7vCEoVjyaKh+9VTygvE0JPL1WHwU7w50AOyzKqLx9eV88tt4SOpWhSTxXdAw94W0lvKwCCj18Ig69D97IO80JsbyAA588vBQrPIHnYz2fDfo6f5NGPA76g72I/pY8RUeaOkiAZrzWO6s8vaPovG7Y9jvGmyy8ZPxtPEpFRj23ULU7qnUWPO1JLr0z4ru8Xo7pvCMn7Dyh0tk7tzVkOhtjAL3s9Ca9koWYPMFnXjwJ4Ya7nn68OlyqJL2AAx+8es0GPI3evbx08fM82Y/IOytYhrwCAyo9MHNNvM9bhLwzN0O7Y8I3PGXBTbxKKvW7WuVEvYrgkbzz0oM8X/7BPII86zuEVzy9ra7ivENn6bxy8BM82JAyPaxZWzyvOYw7h1XoOyFDpzzJf3E6ItLkOhlKebwH/ws7dPFzvE/OG72mBii8LFlmvIpU/ruVocm7MnLjPHdg4ryFAcs61Ft6vc7tdTwKcMS8+Qn8PO1JLj2Vock7HbnnvFN3wDzG1IK86hR2vDxNjDx4CvG89GHBPJ6ZjTw/E0w8jhh0PHYmrLxkbEa8vdkKvEu1Hjourm07UV3ZvOOmcbyCrS09ItLkvJFNLLxaj9O8sDgiPV03mLygJgG7ndQtvHCdVj1ZVge8vb65PF03mDzReB88EE6hPOnaPzt7zYY8gzxrPOGlkbyTEoy8Lo+IPNvihTqaD069HGRgPaPsQL3hGJ49Ie4fPcq1E7zOXji7aYXDvTn7OL2LbYW89mBXPEjwvjtXO7Y7IidsPfULUDwLwwG8FmcePTmlx7w7pN28cvATvRS9DzylXBm9c2I2vCNdjrxO7mq8X/7BuwhxLr0xHVy9VwEAPVKyYDwh7h+92XT3PDc22TzRBZM8QkgEPM2Ybr3DZvS752pnO6fpDDu+hAO+dSeWO9J3tbyXZik8d2DivKDulLyTMXG8lfZQPBL4L7wiexO9KJXwOnzqIb1wSM88O999vCbqAby5+kM5Uz0KPCghBDwGAVY9fj6/vBdL47zZ5bm8oe0qPYarWbwWZ568KCEEPNh1Ybsc1aI8pHt+usEQDT1/eHU81pGcvCoFSTxQCFI9LARfPEwKJj29vrm8e5UaPVPNMb2ZK4k8A+duPQNzAruEAcu89QvQPGqglDzlFIC7WzrMvH/oTb2rWdu7f3j1PMnU+DwIGz09VFxvO+xJLrsR3d68r8hJPDbfB71zKIC9FRIXvWMXvzzXOyu9rljxPPq09Lze/ja9jd69PP4i+TzMCTG9YhgpPYxuZbw7+IQ8dWHMvGJQFT1UsXY8WlWdulbL3TwKcMS8KCEEPUG7kLsNNLo6FUxNvdvkz7qefrw8bIIPvf3prLxDEBi6NvyivEDZlbwNbvA8PfeaPEoLELyrrYK6GUr5vJf1ZrzWHhC9f64XvTvAGD1t9LG8L8m+uzHjpbzipRG9EBh/PM6Ybry6pNK8atpKPGgwPLwolfA86RT2O6aWT7wycuM8lvSGvKmUe72Y1gG94PuCvTDI1Lrfbg+9fek3O80JsTsJcES9MOMlvPyUpTsbKqq8kzHxO3Cd1jtd43C8SZu3PBoQw7yqP/Q8oXsIvVIH6DoTTTc8QhJiO2m/eb07FSC9Cap6PUMQGDzl3BM9xIFFvXVhzDzDZnS9ZmmSvO7zPD3ohTi82/+guzGOnrw6FaC8ORaKPG/zRzxBg6Q8MY4ePFmQPbz18P68kU0sPTDIVDzjpnE9hsaqvGa/A71oMLy7mfT8vH4+P7wmBx28LK9XvAf/i70uyb68AJGHvG2Db71ZVgc9DjS6vFPNMbwV90W8hsYqPF/+QT30YUE9NXH5uoKSXLy14UY80FsEu6eTmzxzR+W7kYdiPQrgnLxSeCo9hXEjO8K8ZbzTzDy8z86QvGUWVT3f4vu8zJnYu4bGqroWEa281cvSPJ5j6zyCPGu9ZtweOjI4LT3OeQm9l0vYPDQ3Q71qhUM8IydsPJkQOL3t2Gs9/njqvN9TPjpcVLO8YlAVvTn7OLx6tH+7qcsHvVl1bLyX9ea8cEYFPMDYoDy0pxA8MsfqOfcInLxJYJc8ssUVvXW207tXdIy7t4kLvJZmqTzG1AK9qFsvPUfW1zxfqFA7jN8nvekU9rvCLag8E6I+vAyKq7w5Foo8hKzDvCWyFT1lwU280+cNvNJc5DuBOws95YYiPefbKTi0jD+7KlrQPOIXNLzCLSi8u9AkPR03gDxKmzq91v3YvN9aJL23Jri81RDaPN2KNT0ouyc9dWYSO5dZJr3W6le9wl0BvXHiJ7yV3q08Y2iPPKut+TudMoe8CFYNPc9wfLz73E67AmorPbNWSTxDY1S7P2TxPGGZejtj22+80YzvvJuRDD1uErm7sPjgvK5EZb2OUVG9LqeJvPso0zvVSd27c6mkvK+/Xby0fMu8KteaPN/fq7x3B429QBjtPAVzHbxjJ/S6RJzXOow1XjodlgW9K56XvRhf+by1q7+8K8SZvIsP3DwZ7fK6JINBvObnALwsLJG9IHrPvCIbyrz8tsy8umgtvNee0zz3pGi8C+QGvfceh7wjSr48SnU4PN0+sTzW/di83T4xvEukLLwY/5k8K8QZPEP7XLxLt6289t1ru0lPNj0iG0q9JwesPLuEoDyYmxu9Y3uQuiBnzrz0iPU8HpffPJLCujy646U8AJq8PC6UiDthrPu8+awAvSYtLjwAYTm995FnvAVzHby92Ra9jivPvKyiED2G/fc7TeYhPEGT5TyrFBc9GkEPPfa2D7oel1+9J/QqvN/MqrovW4U8uXuuvD38+bz/rD08rh0JPbuXoTzUNQI9Qw7eu1BOGb3jKhM8aBPWvPYp8Dv9V0e8GmhrvAe1Er3USAM9txO3vBsIjDyJp2S8u5ehPEFHYTxDDt689inwO03moTvRnpY8Au8yvP2jy7uMDgK8cVQuPIngZ7yOK089TR8lPXZAEL2Gipc7iuDnPJZ/KD2I8+i8iIvxO/ceh72t7246KAcsvdexVDoozqi80GUTvSdTMDzTbgU9UQIVPQKjLryHURQ9P1CWvKvA+rv28Oy6kEfCvNmnRb3BcAI92yK+PDyvG7y6L6o89Ij1vNo1v7sBFTU9AzEovXEurLyOZFI9Ge1yvExYqDr3pOi5asdRvbW+wDz9tsw9iBgRPD0ifLwcHOc7dCSdvIbWm7xPThk70Z/wvLWrPz2V3q08+2HWvG2XQDvSzuQ8lD2zPIX9d7yrh/e8R5JIOuYNgz1wCCo9GBKbvTxb/zwZoBQ8ln8ovSt4Fb2Nd1M8024FPd7MKr3Zusa6bTg7vMGWhDzUgmC9ShazvNU23DwjqUO91z/OOt0FLr30YRm94fuevAvkBrwczwg9h2Xvuhpnkb1uS7w8UmqMvN0rsLzaW0E93Rivu0EzBj0XmPw8sgFTvdJ57jzQEfc8t4U9PZcgo7tjaA+83Py7PK1DCz1wGyu9PZwaPUnUvbxIIMK8QLnnPIshgzz9o0u9ADs3vdVJXb1THog84cIbPWscyLusopA8uKEwPBtC6TyGnRi9Zl6AvbCG2jwfxlM790SJvSWfNDxwerA8BQumvGwJxzqHnvI8+DJivLD44LwCfaw8eG+EPdCxFz2Vfyg8QBjtPJQEML0pgqQ6/6y9PPIgfjs9dpg82FLPPGITGb3TgQa9ncAAPbFN1zxsvUI8+9zOOx2DBLy6HKk94A6gPGUJCj0Kq4M5rh0Ju/+/vjy+jRI9hVz9vLr2prwdSoE8mRYUumnt07s/8RC9dLKWOtItaj091ve8P/EQvT4Xkz2V3q28vV4evgULpry6aC07aABVPQT4JLz1FRW7QsLZvAJqK70lxTa94JOnvEaSSL2Qk0a9HTcAPWFg97wnLa680YzvPAK2LzyuCgg9rLZrPJBHQrqPk8Y8JrK1uGRCDT35+d68tGlKvT2cGj36mtm8F9F/u9jNR7xARoc8JbK1vR03AL0oqCY8wXACvft0V7xwerA8RVBTvWNoDzxi7Ra80uCLOoz82jy37TQ9GnqSvK8dCTxhrPu8+sBbPGOOET1tcT68LBkQvEDLDj0CkK08a+NEOxracb2JLOw8PopzvU+HnDwkcMA8ksI6PXJwobywhlo8GBIbPGb3Yr08whw9KUkhvRmzFb2rOpm8aF/aPP8exDxrCUc9bSU6PGy9QjxyvKW62ZTEPLKizTwBFTW9mreOPUxYKL0jqcO8vEsdvJLCur0C3DE7uY6vunfOCTy6Qqs8Rn9Hu2W9Bb1iTfa8eG+EO00yJj3UNYI+l0YlPZWSKTyukOm8hz4TPRzPCL35rdo7iQWQPEBGB7z1iPW73He0O1PSAz1DdtW7u72jvIU2+7rOqf883SswvGz2xbxN5qE9YwHyO5L7PbyZiBo8vF6ePHVTEbz5+V685N6OvM/Y87zkF5I8rh0JPRkmdr3Rn3C92qfFOrK1zjy10UE8JkCvvLW+QD3Azwc91DWCPbPb0DyH1hu8KLunPInNZjyzVsm8CR2KPC66Cr3y+nu8IVRNvdFA67yKRwU92LpGvQv3hzz/0r+8PDV9vHJwIbxF8U08/VfHvC9uBr1PYZo8eFwDvQKjLj2PGM483VEyPFMeiDuvv928TfkivEDLDjz73E64tGnKvR/ZVD0vW4U93SswPPYWbz3dGK+8tl+7PK/RBD210cE7QZPlPIVvfj1Af4q8F5j8vIaKl7zgRyO8h3hwvIsP3LpvoLI8iRlrvG0lujw+UXC8HyXZPGI69bxFUFO8ahzIPMAuDT08wpy8hz4TPc/Y8zwgxlO9kfu9u1EVFr1SfQ29C/cHPZTLrDw+nXQ80T+RvG5ePT1CM4a8Yjr1uz/faTmWM6S7jt9KPNpIQLxLKTQ9/VfHvAKjrjsaoBQ9BicZPf8Lwzz4MmI84TQivGa+Xz0ajZO8ZMhuuotu4TwatG88aDlYuZukDb0ByTC9LBmQvB294Txkte08UaOPPL3sl7xpx9G8uceyuR1KAT34Hgc8Q3bVPK4KiDvmIIS7sqJNPeMXEj1zqSQ8b6CyvFPlBL1KFjM8IuLGu2SP67v2ymq8uuOlO9CLlTxAbIk9vF6ePALJsD1ws7O8/6y9O3JdID2XICO8uLQxvdGycb2KSF+7+L+BPPgLBj3PXfu81nhRPAWZHzsL0QU8kz0zPGmOTj3VIgE8cfWovCEIyTklJDy8TR8lvazc7bv1AhQ8jvJLPCuLlr0uuoq6/cnNugICtD34RWM9s8hPPBj/mTxT5QQ9dwcNPNm6xjyuHYm8wkoAvVSZAD2IURS8hsMaPECA5D0Cfay8ukIrvPek6DwiLks8z/2bPU90GzxqtFA9vrOUPEgNQT3fgCa8JlOwPK5EZTwd4+M5/wtDva+/XTyGEHm7C9GFvK++A71yXaA7GdrxvIv7gLy7l6G8KjagPPyjy7z4+IQ95KULPYbWm7xGbMa8S92vPIdkFToXcvq7adrSvI8YTjwulAg8sIZavJxYCbzdKzC9LyICvEGTZTo7Nf28iRiRPHJdIDz0m/Y8dBGcPSWytTkqEB49cc8mvfUVFTsXhXu9rE50vJC5SLv4+IQ8/6w9vZrwkTyG6Ry9932MPb9nkD1SMYk7jPzavLFNV7tqx1E8ZKLsvB2DBDyw5V88bL1CvZCAxTv3pGi8G6HuvCO8xLxPwJ883J02PWFz+LwAmry8sidVvdLOZLzeuak8cqmku5lPl7xmCmS8t4W9uft01zwLcoC8BawgvXQ3HjwjvMQ7acfRPIuUYzxCR+G8teRCvXFULj0baOs8GQB0vEoptLrUIgG9PK+bOxgSGz3+5cC61JXhOhiFezloOVi8z137u3H1qLodcIM83gUuOyjhKbz6rdo8UwsHu4s13jxB+gK8HTeAvNLOZDxoOVi99MH4vNgGS7wfxtO89E/yPK2j6jqQgMU7kDTBO535g7zc/Lu79K53vHQkHT377088Pdb3PHV5E70FrKA8jPxavGNoD7z++ME8IvXHvEjBvLvc/Lu8HM8Iu3ODojx4goW706jiO4s1Xj0/8ZA6Pa+bvEgzw7yFXP27SnU4PWUwZr0u4Iw8r79dvcD1CT2d5oI6BhSYPIz8Wr1LFrM9s3xLO/9zuruYdZk8uO20vEUXUDvbIj48l8GdPCTruDyXDSK7r6uCvK4diTzUlAc83qaovMDPhz0l2Lc8tArFPJf6ID2ZT5e7tUPIPN7MKr1KFjM8sZlbvZalKj3ACAs8iFGUPJdGpTw7SH46hVz9vKzIEr1SMYm8KjYgvNF4FL2xmVs7LzUDvU7ToDo9Ivy7TH4qPOH7nrz7Yda8+AuGvJNQNLurwPo7KhCevPa3aTwcHGc9q2H1PD9Qlrz0hxu90nluvPRPcrzfbSU8CQoJvrD44Lu/VA882jW/vE0fpbtjjpG7is3mvL3ZFjz73M68POl4vIshgzxnqoQ8l+efPP1ExjtAbAm9QMsOPP2QyjuOUVE8CHyPPdsPvTzZgcO8uuMlvXLiJzpLFjO9qzqZvEa4SjzOlv681urXvPmtWrzP/Rs9cc8mPdOoYjyUPTO7rLbrPNjNxzzap0W8BdKiOd/yrLwbG408keg8Pbl7Lj1kQg26+tNcvEf6v7y2hb08i1oGPay267xp7VO9d86JPImnZL3+0j+84JOnPN13tLz6wFu82fPJvLEBUzysohC9ui+qvYdRlL1FKlG8I4NBvYsiXTxC1dq8ZDDmvGOhkjwuBg+8ceKnvfQ7Fz2TY7W83Na5OlGQjrr4DGC7mYiaOkSv2DsjNz085UYGvf2jSzz2fQw8TJErvYYjerzQ/nW6VL+CPPn53rvgRyO8ibkLPRsIjDu97Be9+yhTOwT4pDvfgKa8GsfwvLFz2bwh9Ue8wYMDPOLoHb1L8LA8GmcRO+AOILxU0gM8QfqCvGgTVj0BybC8d7sIvUC4jTwcLg69PXYYPNzDuLxCR2E9eSOAPRz1irzir5q8Yu7wOwcnmbxqVcs8R/q/vLnaMzxHbMY7YdL9u4k/bbyvv128dOuZu/3JzbxKA7K7CTCLvPe3abvUleG8m6QNPPhFY733RWO82M3HPNQjW7xLyi69HzjavGOOET3m5wA7Y7QTPR03AL2IGWs9ukIrvL0lm7xSRAo9l1kmvfYDbrzfWiS8qfl9PElitzz0Oxc9aF/au/jSgju3E7e8Q9VavPwC0TzYZdA89K53PUUqUTwATri7qtP7vGfR4LwmLS48QjRgPdEsEL1raEy94EejvI7fyrxLKTS9rChyvCB6z7z2PHG8Jy2uvHJwIbwugYc9SU+2PGJz+Dtnq968TgykPLCGWrspuyc80VISvf1ERj1vxjQ7tdHBPEcgQj20Q0g9/jHFu9hSzzyuMWQ9TgykPIexc7z5H2E9q8B6vJf6IDzPN3m80SwQvdAR9zwln7Q8I5bCvHB6sDx02Bi85ucAvS9bhTwsnpc8i+nZOWZxAb1qVUs8+QxgvQS/Ib0Fcx28HUoBvW2EP70Y/xk92YFDvbPIz7xp7dO6ZQkKu4z82jyJ3429+07VOyuLlrytAvC75mwIvLxenjyr7hQ6vhKau7eFPT29/5g7+L+BvK58jr3ZbsI7YxRzPCcHrLy098O89Ij1vGtCSrzVDwC8sTrWPAZznbyJP+080CR4O0optDwoqKY8Ax4nvN9apLxwZ688Jdi3vA=="}
\ No newline at end of file
diff --git a/dsLightRag/Topic/Math/kv_store_llm_response_cache.json b/dsLightRag/Topic/Math/kv_store_llm_response_cache.json
index 6aedc28d..e1c3d863 100644
--- a/dsLightRag/Topic/Math/kv_store_llm_response_cache.json
+++ b/dsLightRag/Topic/Math/kv_store_llm_response_cache.json
@@ -9,6 +9,36 @@
"embedding_min": null,
"embedding_max": null,
"original_prompt": "小学数学中有哪些常见模型？"
+ },
+ "9b37cd625bfa223f5c83501990ad6be1": {
+ "return": "{\"high_level_keywords\": [\"\\u82cf\\u8f7c\", \"\\u5bb6\\u4eba\", \"\\u5bb6\\u5ead\\u5173\\u7cfb\"], \"low_level_keywords\": [\"\\u82cf\\u6d35\", \"\\u82cf\\u8f99\", \"\\u738b\\u5f17\", \"\\u738b\\u671d\\u4e91\", \"\\u82cf\\u8fc7\"]}",
+ "cache_type": "keywords",
+ "chunk_id": null,
+ "embedding": null,
+ "embedding_shape": null,
+ "embedding_min": null,
+ "embedding_max": null,
+ "original_prompt": "苏轼的家人都有谁?"
+ },
+ "39927327159cfd7cca859e211cc6e357": {
+ "return": "{\"high_level_keywords\": [\"\\u6559\\u5b66\\u8bbe\\u8ba1\", \"\\u51e0\\u4f55\\u6982\\u5ff5\", \"\\u6570\\u5b66\\u6559\\u5b66\"], \"low_level_keywords\": [\"\\u70b9\", \"\\u7ebf\", \"\\u9762\", \"\\u4f53\", \"\\u89d2\"]}",
+ "cache_type": "keywords",
+ "chunk_id": null,
+ "embedding": null,
+ "embedding_shape": null,
+ "embedding_min": null,
+ "embedding_max": null,
+ "original_prompt": "帮我写一下 如何理解点、线、面、体、角 的教学设计"
+ },
+ "15cecdac0531563df69e6105968db51c": {
+ "return": "{\"high_level_keywords\": [\"\\u5fae\\u79ef\\u5206\", \"\\u57fa\\u672c\\u5b9a\\u7406\", \"\\u6570\\u5b66\\u7406\\u8bba\"], \"low_level_keywords\": [\"\\u5bfc\\u6570\", \"\\u79ef\\u5206\", \"\\u725b\\u987f-\\u83b1\\u5e03\\u5c3c\\u5179\\u516c\\u5f0f\", \"\\u8fde\\u7eed\\u51fd\\u6570\", \"\\u5fae\\u5206\"]}",
+ "cache_type": "keywords",
+ "chunk_id": null,
+ "embedding": null,
+ "embedding_shape": null,
+ "embedding_min": null,
+ "embedding_max": null,
+ "original_prompt": "微积分的基本定理是什么?"
}
},
"default": {
diff --git a/dsLightRag/static/ai.html b/dsLightRag/static/ai.html
index e6701ed8..f31eb240 100644
--- a/dsLightRag/static/ai.html
+++ b/dsLightRag/static/ai.html
@@ -199,8 +199,8 @@
苏轼的好朋友都有谁?
苏轼的家人都有谁?
苏轼有哪些有名的诗句?
-
- 氧化铁和硝酸的反应方程式?
+
+ 硝酸的分解反应?