From 1f42a541b6e606a99314a7755c0df1bf760d4c24 Mon Sep 17 00:00:00 2001
From: Riskey <36894937+RiskeyL@users.noreply.github.com>
Date: Mon, 9 Mar 2026 17:49:41 +0800
Subject: [PATCH] Update 30 min tutorial (#701)
* update based on user feedback
* update zh and ja docs
* modify based on feedback
* correct typos
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
en/use-dify/getting-started/quick-start.mdx | 730 ++++++++++----------
images/deeper_dive_doc_extractor.png | Bin 0 -> 226655 bytes
images/deeper_dive_if.png | Bin 110415 -> 174329 bytes
images/deeper_dive_import_from_json.png | Bin 0 -> 50341 bytes
images/deeper_dive_info_integrate.png | Bin 152563 -> 540982 bytes
images/deeper_dive_iteration.png | Bin 0 -> 89487 bytes
images/deeper_dive_iteration_config.png | Bin 0 -> 256698 bytes
images/deeper_dive_list_operator.png | Bin 190896 -> 240414 bytes
images/deeper_dive_paramater_extractor.png | Bin 198289 -> 304470 bytes
images/deeper_dive_start.png | Bin 146556 -> 193456 bytes
images/deeper_dive_structured_output.png | Bin 61874 -> 75166 bytes
images/deeper_dive_template.png | Bin 83523 -> 221811 bytes
images/deeper_dive_test_output.png | Bin 0 -> 264896 bytes
images/deeper_dive_user_message.png | Bin 0 -> 29034 bytes
images/deeper_dive_workflow_overview.png | Bin 192666 -> 291991 bytes
ja/use-dify/getting-started/quick-start.mdx | 674 +++++++++---------
zh/use-dify/getting-started/quick-start.mdx | 678 +++++++++---------
17 files changed, 1098 insertions(+), 984 deletions(-)
create mode 100644 images/deeper_dive_doc_extractor.png
create mode 100644 images/deeper_dive_import_from_json.png
create mode 100644 images/deeper_dive_iteration.png
create mode 100644 images/deeper_dive_iteration_config.png
create mode 100644 images/deeper_dive_test_output.png
create mode 100644 images/deeper_dive_user_message.png
diff --git a/en/use-dify/getting-started/quick-start.mdx b/en/use-dify/getting-started/quick-start.mdx
index f9318806..d8e3036d 100644
--- a/en/use-dify/getting-started/quick-start.mdx
+++ b/en/use-dify/getting-started/quick-start.mdx
@@ -12,44 +12,67 @@ By the end of this tutorial, you'll have a workflow that takes whatever content
The complete workflow is shown below. Feel free to refer back to this as you build to stay on track and see how all the nodes work together.
-
+
+ 
+
+
+## Before You Start
+
+
+
+
+ Go to [Dify Cloud](https://cloud.dify.ai) and sign up for free.
+
+ New accounts on the Sandbox plan include 200 message credits for calling models from providers like OpenAI, Anthropic, and Gemini.
+
+
+ Message credits are a one-time allocation and don't renew monthly.
+
+
+
+
+
+ Go to **Settings** > **Model Provider** and install the OpenAI plugin. This tutorial uses `gpt-5.2` for the examples.
+
+ If you're using Sandbox credits, no API key is required—the plugin is ready to use once installed. You can also configure your own API key and use it instead.
+
+
+
+
+
+ 1. In the top-right corner of the **Model Provider** page, click **System Model Settings**.
+
+ 2. Set the **System Reasoning Model** to `gpt-5.2`. This becomes the default model in the workflow.
+
+
+
## Step 1: Create a New Workflow
-1. Go to **Studio**, then select **Create from blank** \> **Workflow**.
+1. Go to **Studio**, then select **Create from blank** > **Workflow**.
+
2. Name the workflow `Multi-platform content generator` and click **Create**. You'll automatically land on the workflow canvas to start building.
-## Step 2: Add and Configure Workflow Nodes
+3. Select the User Input node to start our workflow.
+
+## Step 2: Orchestrate & Configure
Keep any unmentioned settings at their default values.
- Give nodes and variables clear, descriptive names to make them easier to identify and reference in the workflow.
+ Give nodes and variables clear, descriptive names to make them easier to identify and reference.
-### 1. User Input Node: Collect User Inputs
+### 1. Collect User Inputs: User Input Node
- First, we need to define what information to gather from users, such as the draft text, target platforms, desired tone, and any reference materials.
+ First, we need to define what information to gather from users for running our content generator, such as the draft text, target platforms, desired tone, and any reference materials.
The User Input node is where we can easily set this up. Each input field we add here becomes a variable that all downstream nodes can reference and use.
-
-
Click the User Input node to open its configuration panel, then add the following input fields.
@@ -57,7 +80,7 @@ Click the User Input node to open its configuration panel, then add the followin
- Variable Name: `draft`
- Label Name: `Draft`
- Max length: `2048`
- - Required: `No`
+ - Required: `Yes`
@@ -94,62 +117,70 @@ Click the User Input node to open its configuration panel, then add the followin
- `English`
- `日本語`
- `简体中文`
- - Default value: `English`
- Required: `Yes`
-### 2. Parameter Extractor Node: Identify Target Platforms
+
+ 
+
+
+### 2. Identify Target Platforms: Parameter Extractor Node
- Since our platform field accepts free-form text input, users might type in various ways: `x and linkedIn`, `post on Twitter and LinkedIn`, or even `Twitter + LinkedIn please`. However, we need a clean and structured list, like `["Twitter", "LinkedIn"]`, that downstream nodes can work with reliably.
+ Since our platform field accepts free-form text input, users might type in various ways: `x and linkedIn`, `post on Twitter and LinkedIn`, or even `Twitter + LinkedIn please`.
+
+ However, we need a clean and structured list, like `["Twitter", "LinkedIn"]`, that downstream nodes can work with reliably.
- This is the perfect job for the Parameter Extractor node. It uses an LLM to analyze users' natural language, recognize all these variations, and output a standardized array.
+ This is the perfect job for the Parameter Extractor node. In our case, it uses the gpt-5.2 model to analyze users' natural language, recognize all these variations, and output a standardized array.
-
-
After the User Input node, add a Parameter Extractor node and configure it:
-1. Choose a model.
-2. Set `User Input/platform` as the input variable.
-3. Add an extract parameter:
- 1. Name: `platform`
- 2. Type: `Array[String]`
- 3. Description: `Identify and extract the platform(s) for which the user wants to create tailored content.`
- 4. Required: `Yes`
-4. In the instruction field, paste the following to guide the LLM in parameter extraction:
+1. In the **Input Variable** field, select `User Input/platform`.
- ```markdown INSTRUCTION
- # TASK DESCRIPTION
- Parse platform names from input and output as a JSON array.
-
- ## PROCESSING RULES
- - Support multiple delimiters: commas, semicolons, spaces, line breaks, "and", "&", "|", etc.
- - Standardize common platform name variants (twitter/X→Twitter, insta→Instagram, etc.)
- - Remove duplicates and invalid entries
- - Preserve unknown but reasonable platform names
-
- ## OUTPUT REQUIREMENTS
- - Success: ["Platform1", "Platform2"]
- - No platforms found: [No platforms identified. Please enter a valid platform name.]
-
- ## EXAMPLES
- - Input: "twitter, linkedin" → ["Twitter", "LinkedIn"]
- - Input: "x and insta" → ["Twitter", "Instagram"]
- - Input: "invalid content" → [No platforms identified. Please enter a valid platform name.]
- ```
+2. Add an extract parameter:
-
- Note that we've instructed the LLM to output a specific error message for invalid inputs, which will serve as the end trigger for our workflow in the next step.
-
+ - Name: `platform`
-### 3. IF/ELSE Node: Validate Platform Extraction Results
+ - Type: `Array[String]`
+
+ - Description: `The platform(s) for which the user wants to create tailored content.`
+
+ - Required: `Yes`
+
+3. In the **Instruction** field, paste the following to guide the LLM in parameter extraction:
+
+ ```markdown INSTRUCTION
+ # TASK DESCRIPTION
+ Parse platform names from input and output as a JSON array.
+
+ ## PROCESSING RULES
+ - Support multiple delimiters: commas, semicolons, spaces, line breaks, "and", "&", "|", etc.
+ - Standardize common platform name variants (twitter/X→Twitter, insta→Instagram, etc.)
+ - Remove duplicates and invalid entries
+ - Preserve unknown but reasonable platform names
+ - Preserve the original language of platform names
+
+ ## OUTPUT REQUIREMENTS
+ - Success: ["Platform1", "Platform2"]
+ - No platforms found: [No platforms identified. Please enter a valid platform name.]
+
+ ## EXAMPLES
+ - Input: "twitter, linkedin" → ["Twitter", "LinkedIn"]
+ - Input: "x and insta" → ["Twitter", "Instagram"]
+ - Input: "invalid content" → [No platforms identified. Please enter a valid platform name.]
+ ```
+
+
+ Note that we've instructed the LLM to output a specific error message for invalid inputs, which will serve as the end trigger for our workflow in the next step.
+
+
+
+
+ 
+
+
+### 3. Validate Platform Extraction Results: IF/ELSE Node
What if a user enters an invalid platform name, like `ohhhhhh` or `BookFace`? We don't want to waste time and tokens generating useless content.
@@ -157,58 +188,64 @@ After the User Input node, add a Parameter Extractor node and configure it:
In such cases, we can use an IF/ELSE node to create a branch that stops the workflow early. We'll set a condition that checks for the error message from the Parameter Extractor node; if that message is detected, the workflow will route directly to an Output node and end.
-
+
+ 
+
1. After the Parameter Extractor node, add an IF/ELSE node.
-2. On the IF/ELSE node's panel, define the IF condition:
- **IF** `Parameter Extractor/platform` `contains` `No platforms identified. Please enter a valid platform name.`
+2. On the IF/ELSE node's panel, define the **IF** condition:
+
+ **IF** `Parameter Extractor/platform` **contains** `No platforms identified. Please enter a valid platform name.`
+
3. After the IF/ELSE node, add an Output node to the IF branch.
+
4. On the Output node's panel, set `Parameter Extractor/platform` as the output variable.
-### 4. List Operator Node: Separate Uploaded Files by Type
+### 4. Separate Uploaded Files by Type: List Operator Node
- Our users can upload both images and documents as reference materials, but these two types require different handling: images can be interpreted directly by vision-enabled models, while documents must first be converted to text for an LLM to understand their content.
+
+ Our users can upload both images and documents as reference materials, but these two types require different handling with `gpt-5.2`: images can be interpreted directly via its vision capability, while documents must first be converted to text before the model can process them.
To manage this, we'll use two List Operator nodes to filter and split the uploaded files into separate branches—one for images and one for documents.
-
+
+ 
+
+
+1. After the IF/ELSE node, add **two** parallel List Operator nodes to the ELSE branch.
-1. After the IF/ELSE node, add two List Operator nodes to the ELSE branch.
2. Rename one node to `Image` and the other to `Document`.
-3. Configure the Image node:
- 1. Set `User Input/user_file` as the input variable.
- 2. Enable the filter condition: `{x}type` `in` `Image`
-4. Configure the Document node:
- 1. Set `User Input/user_file` as the input variable.
- 2. Enable the filter condition: `{x}type` `in` `Doc`.
-### 5. Doc Extractor Node: Extract Text from Documents
+3. Configure the Image node:
+ 1. Set `User Input/user_file` as the input variable.
+
+ 2. Enable **Filter Condition**: `{x}type` **in** `Image`.
+
+4. Configure the Document node:
+ 1. Set `User Input/user_file` as the input variable.
+
+ 2. Enable **Filter Condition**: `{x}type` **in** `Doc`.
+
+### 5. Extract Text from Documents: Doc Extractor Node
- LLMs can't directly read uploaded files like PDF or DOCX. To use the information in these documents, we must first convert them into plain text that LLMs can process.
+ `gpt-5.2` cannot directly read uploaded documents like PDF or DOCX, so we must first convert them into plain text.
This is exactly what a Doc Extractor node does. It takes document files as input and outputs clean, usable text for the next steps.
+
+ 
+
+
1. After the Document node, add a Doc Extractor node.
+
2. On the Doc Extractor node's panel, set `Document/result` as the input variable.
-### 6. LLM Node: Integrate All Reference Materials
+### 6. Integrate All Reference Materials: LLM Node
When users provide multiple reference types—draft text, documents, and images—simultaneously, we need to consolidate them into a single, coherent summary.
@@ -216,86 +253,81 @@ After the User Input node, add a Parameter Extractor node and configure it:
An LLM node will handle this task by analyzing all the scattered pieces to create a comprehensive context that guides subsequent content generation.
-
+
+ 
+
1. After the Doc Extractor node, add an LLM node.
+
2. Connect the Image node to this LLM node as well.
+
3. Click the LLM node to configure it:
- 1. Rename it to `Integrate Info`.
- 2. Choose a model that supports vision (indicated by an eye icon).
- 3. Enable **VISION** and set `Image/result` as the vision variable.
- 4. In the system prompt field, paste the following:
-
- In the prompt, to reference the `Doc Extractor/text` and `User Input/draft` variables in _PROVIDED MATERIALS_, type `{` or `/` and select from the list.
+ 1. Rename it to `Integrate Info`.
- 
-
- ```markdown SYSTEM {2,3}
- # PROVIDED MATERIALS
- Doc Extractor/text
- User Input/draft
-
- # ROLE & TASK
- You are a content strategist. Analyze the provided materials and create a comprehensive content foundation for multi-platform social media optimization.
-
- # ANALYSIS PRINCIPLES
- - Work exclusively with provided information—no external assumptions
- - Focus on extraction, synthesis, and strategic interpretation
- - Identify compelling and actionable elements
- - Prepare insights adaptable across different platforms
-
- # REQUIRED ANALYSIS
- Deliver structured analysis with:
-
- ## 1. CORE MESSAGE
- - Central theme, purpose, objective
- - Key value or benefit being communicated
-
- ## 2. ESSENTIAL CONTENT ELEMENTS
- - Primary topics, facts, statistics, data points
- - Notable quotes, testimonials, key statements
- - Features, benefits, characteristics mentioned
- - Dates, locations, contextual details
-
- ## 3. STRATEGIC INSIGHTS
- - What makes content compelling/unique
- - Emotional/rational appeals present
- - Credibility factors, proof points
- - Competitive advantages highlighted
-
- ## 4. ENGAGEMENT OPPORTUNITIES
- - Discussion points, questions emerging
- - Calls-to-action, next steps suggested
- - Interactive/participation opportunities
- - Trending themes touched upon
-
- ## 5. PLATFORM OPTIMIZATION FOUNDATION
- - High-impact: Quick, shareable formats
- - Professional: Business-focused discussions
- - Community: Interaction and sharing
- - Visual: Enhanced with strong visuals
-
- ## 6. SUPPORTING DETAILS
- - Metrics, numbers, quantifiable results
- - Direct quotes, testimonials
- - Technical details, specifications
- - Background context available
- ```
+ 2. Enable **VISION** and set `Image/result` as the vision variable.
-### 7. Iteration Node: Create Customized Content for Each Platform
+ 3. In the system instruction field, paste the following:
+
+ ```markdown wrap
+ # ROLE & TASK
+ You are a content strategist. Analyze the provided draft and reference materials (if any), then create a comprehensive content foundation for multi-platform social media optimization.
+
+ # ANALYSIS PRINCIPLES
+ - Work exclusively with provided information—no external assumptions
+ - Focus on extraction, synthesis, and strategic interpretation
+ - Identify compelling and actionable elements
+ - Prepare insights adaptable across different platforms
+
+ # REQUIRED ANALYSIS
+ Deliver structured analysis with:
+
+ ## 1. CORE MESSAGE
+ - Central theme, purpose, objective
+ - Key value or benefit being communicated
+
+ ## 2. ESSENTIAL CONTENT ELEMENTS
+ - Primary topics, facts, statistics, data points
+ - Notable quotes, testimonials, key statements
+ - Features, benefits, characteristics mentioned
+ - Dates, locations, contextual details
+
+ ## 3. STRATEGIC INSIGHTS
+ - What makes content compelling/unique
+ - Emotional/rational appeals present
+ - Credibility factors, proof points
+ - Competitive advantages highlighted
+
+ ## 4. ENGAGEMENT OPPORTUNITIES
+ - Discussion points, questions emerging
+ - Calls-to-action, next steps suggested
+ - Interactive/participation opportunities
+ - Trending themes touched upon
+
+ ## 5. PLATFORM OPTIMIZATION FOUNDATION
+ - High-impact: Quick, shareable formats
+ - Professional: Business-focused discussions
+ - Community: Interaction and sharing
+ - Visual: Enhanced with strong visuals
+
+ ## 6. SUPPORTING DETAILS
+ - Metrics, numbers, quantifiable results
+ - Direct quotes, testimonials
+ - Technical details, specifications
+ - Background context available
+ ```
+ 5. Click **Add Message** to add a user message, then paste the following. Type `{` or `/` to replace `Doc Extractor/text` and `User Input/draft` with the corresponding variables from the list.
+
+ ```markdown USER
+ Draft: User Input/draft
+ Reference material: Doc Extractor/text
+ ```
+
+
+ 
+
+
+### 7. Create Customized Content for Each Platform: Iteration Node
Now that the integrated references and target platforms are ready, let's generate a tailored post for each platform using an Iteration node.
@@ -303,218 +335,228 @@ After the User Input node, add a Parameter Extractor node and configure it:
The node will loop through the list of platforms and run a sub-workflow for each: first analyze the specific platform's style guidelines and best practices, then generate optimized content based on all available information.
-
+
+ 
+
1. After the Integrate Info node, add an Iteration node.
+
2. Inside the Iteration node, add an LLM node and configure it:
- 1. Rename it to `Identify Style`.
- 2. Choose a model.
- 3. In the system prompt field, paste the following:
-
- In the prompt, to reference the `Current Iteration/item` variable in _ROLE & TASK_ and _OUTPUT FORMAT EXAMPLES_, type `{` or `/` and select from the list.
-
- ````markdown SYSTEM {2,40}
- # ROLE & TASK
- You are a social media expert. Analyze the platform "Current Iteration/item" and provide content creation guidelines.
-
- # ANALYSIS REQUIRED
- For the given platform, provide:
-
- ## 1. PLATFORM PROFILE
- - Platform type and category
- - Target audience characteristics
-
- ## 2. CONTENT GUIDELINES
- - Optimal content length (characters/words)
- - Recommended tone (professional/casual/conversational)
- - Formatting best practices (line breaks, emojis, etc.)
-
- ## 3. ENGAGEMENT STRATEGY
- - Hashtag recommendations (quantity and style)
- - Call-to-action best practices
- - Algorithm optimization tips
-
- ## 4. TECHNICAL SPECS
- - Character/word limits
- - Visual content requirements
- - Special formatting needs
-
- ## 5. PLATFORM-SPECIFIC NOTES
- - Unique features or recent changes
- - Industry-specific considerations
- - Community engagement approaches
-
- # OUTPUT REQUIREMENTS
- - For recognized platforms: Provide specific guidelines
- - For unknown platforms: Base recommendations on similar platforms
- - Focus on actionable, practical advice
- - Be concise but comprehensive
-
- # OUTPUT FORMAT EXAMPLES
- ```json
- {
- "platform_name": "Current Iteration/item",
- "platform_type": "social_media/professional_network/visual_platform/microblogging",
- "content_guidelines": {
- "max_length": "character/word limit",
- "optimal_length": "recommended range",
- "tone": "professional/casual/conversational/authoritative",
- "hashtag_strategy": "quantity and placement guidelines",
- "formatting": "line breaks, emojis, mentions guidelines",
- "engagement_focus": "comments/shares/likes/retweets",
- "call_to_action": "appropriate CTA style"
- },
- "special_considerations": "Any unique platform requirements or recent changes",
- "confidence_level": "high/medium/low based on platform recognition"
- }
- ````
-3. After the Identity Style node, add another LLM node and configure it:
- 1. Rename it to `Create Content`.
- 2. Choose a model.
- 3. In the system prompt field, paste the following:
+ 1. Rename it to `Identify Style`.
-
- In the prompt, to reference the following variables, type `{` or `/` and select from the list.
- - `Identify Style/text` in _PLATFORM GUIDELINES_
- - `Integrate Info/text` in _SOURCE INFORMATION_
- - `User Input/voice_and_tone` in _VOICE & TONE (OPTIONAL)_
- - `User Input/language` in _LANGUAGE REQUIREMENT_
-
- ```markdown SYSTEM {6,9,12,15}
- # ROLE & TASK
- You are an expert social media content creator. Generate publication-ready content that matches platform guidelines, incorporates source information, and follows specified voice/tone and language requirements.
-
- # INPUT MATERIALS
- ## 1. PLATFORM GUIDELINES
- Identify Style/text
-
- ## 2. SOURCE INFORMATION
- Integrate Info/text
-
- ## 3. VOICE & TONE (OPTIONAL)
- User Input/voice_and_tone
-
- ## 4. LANGUAGE REQUIREMENT
- - Generate ALL content exclusively in: User Input/language
- - No mixing of languages whatsoever
- - Adapt platform terminology to the specified language
-
- # CONTENT REQUIREMENTS
- - Follow platform guidelines exactly (format, length, tone, hashtags)
- - Integrate source information effectively (key messages, data, value props)
- - Apply voice & tone consistently (if provided)
- - Optimize for platform-specific engagement
- - Ensure cultural appropriateness for the specified language
-
- # OUTPUT FORMAT
- - Generate ONLY the final social media post content. No explanations or meta-commentary. Content must be immediately copy-paste ready.
- - Maximum heading level: ## (H2) - never use # (H1)
- - No horizontal dividers: avoid ---
-
- # QUALITY CHECKLIST
- ✅ Platform guidelines followed
- ✅ Source information integrated
- ✅ Voice/tone consistent (when provided)
- ✅ Language consistency maintained
- ✅ Engagement optimized
- ✅ Publication ready
- ```
- 4. Enable structured output.
+ 2. In the system instruction field, paste the following:
- 
- 1. Next to **OUTPUT VARIABLES**, toggle **STRUCTURED** on. The structured_output variable will appear below.
- 2. Next to **structured_output**, click **Configure**.
- 3. In the pop-up schema editor, click **Import From JSON** in the top-right corner, and paste the following:
+ ```markdown wrap
+ # ROLE & TASK
+ You are a social media expert. Analyze the platform and provide content creation guidelines.
+
+ # ANALYSIS REQUIRED
+ For the given platform, provide:
+
+ ## 1. PLATFORM PROFILE
+ - Platform type and category
+ - Target audience characteristics
+
+ ## 2. CONTENT GUIDELINES
+ - Optimal content length (characters/words)
+ - Recommended tone (professional/casual/conversational)
+ - Formatting best practices (line breaks, emojis, etc.)
+
+ ## 3. ENGAGEMENT STRATEGY
+ - Hashtag recommendations (quantity and style)
+ - Call-to-action best practices
+ - Algorithm optimization tips
+
+ ## 4. TECHNICAL SPECS
+ - Character/word limits
+ - Visual content requirements
+ - Special formatting needs
+
+ ## 5. PLATFORM-SPECIFIC NOTES
+ - Unique features or recent changes
+ - Industry-specific considerations
+ - Community engagement approaches
+
+ # OUTPUT REQUIREMENTS
+ - For recognized platforms: Provide specific guidelines
+ - For unknown platforms: Base recommendations on similar platforms
+ - Focus on actionable, practical advice
+ - Be concise but comprehensive
+ ```
+ 3. Click **Add Message** to add a user message, then paste the following. Type `{` or `/` to replace `Current Iteration/item` with the corresponding variable from the list.
+
+ ```markdown USER
+ Platform: Current Iteration/item
+ ```
+3. After the Identify Style node, add another LLM node and configure it:
+
+ 1. Rename it to `Create Content`.
+
+ 2. In the system instruction field, paste the following:
+
+ ```markdown wrap
+ # ROLE & TASK
+ You are an expert social media content creator. Generate publication-ready content that matches platform guidelines, incorporates source information, and follows specified voice/tone and language requirements.
+
+ # LANGUAGE REQUIREMENT
+ - Generate ALL content exclusively in the target language specified in the user message. You MUST write the entire post in that language, regardless of the language of any source materials.
+ - No mixing of languages whatsoever
+ - Adapt platform terminology to the target language
+
+ # CONTENT REQUIREMENTS
+ - Follow platform guidelines exactly (format, length, tone, hashtags)
+ - Integrate source information effectively (key messages, data, value props)
+ - Apply voice & tone consistently (if provided)
+ - Optimize for platform-specific engagement
+ - Ensure cultural appropriateness for the specified language
+
+ # OUTPUT FORMAT
+ - Generate ONLY the final social media post content. No explanations or meta-commentary. Content must be immediately copy-paste ready.
+ - Maximum heading level: ## (H2) - never use # (H1)
+ - No horizontal dividers: avoid ---
+
+ # QUALITY CHECKLIST
+ ✅ Platform guidelines followed
+ ✅ Source information integrated
+ ✅ Voice/tone consistent (when provided)
+ ✅ Language consistency maintained
+ ✅ Engagement optimized
+ ✅ Publication ready
+ ```
+ 3. Click **Add Message** to add a user message, then paste the following. Type `{` or `/` to replace all inputs with the corresponding variable from the list.
+
+ ```markdown USER
+ Platform Name: Current Iteration/item
+ Target Language: User Input/language
+ Platform Guidelines: Identify Style/text
+ Source Information: Integrate Info/text
+ Voice & Tone: User Input/voice_and_tone
+ ```
+
+ 4. Enable structured output.
+
+
+ This allows us to extract specific pieces of information from the LLM's response in a more reliable way, which is crucial for the next step where we format the final output.
+
+
+
+ 
+
+
+ 1. Next to **Output Variables**, toggle **Structured** on. The `structured_output` variable will appear below. Click **Configure**.
+
+ 2. In the pop-up schema editor, click **Import From JSON** in the top-right corner, and paste the following:
+
+ ```json
+ {
+ "platform_name": "string",
+ "post_content": "string"
+ }
+ ```
+
+ 
+
- ```json
- {
- "platform_name": "string",
- "post_content": "string"
- }
- ```
4. Click the Iteration node to configure it:
- 1. Set `Parameter Extractor/platform` as the input variable.
- 2. Set `Create Content/structured_output` as the output variable.
- 3. Enable **PARALLEL MODE** and set the maximum parallelism to `10`.
-
- This is why we included `(≤10)` in the label name for the target platform field back in the User Input node.
-
+ 1. Set `Parameter Extractor/platform` as the input variable.
-### 8. Template Node: Format the Final Output
+ 2. Set `Create Content/structured_output` as the output variable.
+
+ 3. Enable **Parallel Mode** and set the maximum parallelism to `10`.
+
+
+ This is why we included `(≤10)` in the label name for the target platform field back in the User Input node.
+
+
+
+ 
+
+
+### 8. Format the Final Output: Template Node
The Iteration node generates a post for each platform, but its output is a raw array of data (e.g., `[{"platform_name": "Twitter", "post_content": "..."}]`) that isn't very readable. We need to present the results in a clearer format.
- That's where the Template node comes in—it allows us to format this raw data into well-organized text using [Jinja2](https://jinja.palletsprojects.com/en/stable/) templating, ensuring the final output is user-friendly and easy to understand.
+ That's where the Template node comes in—it allows us to format this raw data into well-organized text using [Jinja2](https://jinja.palletsprojects.com/en/stable/) templating, ensuring the final output is user-friendly and easy to read.
-
+
+ 
+
1. After the Iteration node, add a Template node.
-2. On the Template node's panel, set `Iteration/output` as the input variable.
-3. Paste the following Jinja2 code (**remember to delete the comments**).
- ```
- {% for item in output %} # Loop through each platform-content pair in the input array
- # 📱 {{ item.platform_name }} # Display the platform name as an H1 heading with a phone emoji
- {{ item.post_content }} # Display the generated content for this platform
- # Add a blank line between platforms for better readability
- {% endfor %} # End the loop
- ```
+2. On the Template node's panel, set `Iteration/output` as the input variable and name it `output`.
-
- While LLMs can handle output formatting as well, their outputs can be inconsistent and unpredictable. For rule-based formatting that requires no reasoning, the Template node gets things done in a more stable and reliable way at zero token cost.
+3. Paste the following Jinja2 code:
- LLMs are incredibly powerful, but knowing when to use the right tool is key to building more reliable and cost-effective AI applications.
-
+ ```
+ {% for item in output %}
+ # 📱 {{ item.platform_name }}
+ {{ item.post_content }}
-### 9. Output Node: Return the Results to Users
+ {% endfor %}
+ ```
+
+ - `{% for item in output %}` / `{% endfor %}`: Loops through each platform-content pair in the input array.
+ - `{{ item.platform_name }}`: Displays the platform name as an H1 heading with a phone emoji.
+ - `{{ item.post_content }}`: Displays the generated content for that platform.
+ - The blank line between `{{ item.post_content }}` and `{% endfor %}` adds spacing between platforms in the final output.
+
+
+ While LLMs can handle output formatting as well, their outputs can be inconsistent and unpredictable. For rule-based formatting that requires no reasoning, the Template node gets things done in a more stable and reliable way at zero token cost.
+
+ LLMs are incredibly powerful, but knowing when to use the right tool is key to building more reliable and cost-effective AI applications.
+
+
+### 9. Return the Results to Users: Output Node
1. After the Template node, add an Output node.
2. On the Output node's panel, set the `Template/output` as the output variable.
## Step 3: Test
-Your workflow is now complete\! Let’s test it out.
+Your workflow is now complete\! Let's test it out.
1. Make sure your Checklist is clear.
- 
+
+ 
+
+
2. Check your workflow against the reference diagram provided at the beginning to ensure all nodes and connections match.
+
3. Click **Test Run** in the top-right corner, fill in the input fields, then click **Start Run**.
- To run a single node with cached inputs, click the **Run this step** icon at the top of its configuration panel.
+ If you're not sure what to enter, try these sample inputs:
-
- To test how a node reacts to different inputs from previous nodes, you don't need to re-run the entire workflow. Just click **View cached variables** at the bottom of the canvas, find the variable you want to change from the list, and edit its value.
-
- If you encounter any errors, check the **LAST RUN** logs of the corresponding node to identify the exact cause of the problem.
+ - **Draft**: `We just launched a new AI writing assistant that helps teams create content 10x faster.`
+
+ - **Upload File**: Leave empty
+
+ - **Voice & Tone**: `Friendly and enthusiastic, but professional`
+
+ - **Target Platform**: `Twitter and LinkedIn`
+
+ - **Language**: `English`
+
+A successful run produces a formatted output with a separate post for each platform, like this:
+
+
+ 
+
+
+
+ Your results may vary depending on the model you're using. Higher-capability models generally produce better output quality.
+
+
+
+ To test how a node reacts to different inputs from previous nodes, you don't need to re-run the entire workflow. Just click **View cached variables** at the bottom of the canvas, find the variable you want to change, and edit its value.
+
+
+If you encounter any errors, check the **Last Run** logs of the corresponding node to identify the exact cause of the problem.
## Step 4: Publish & Share
@@ -522,8 +564,4 @@ Once the workflow runs as expected and you're happy with the results, click **Pu
If you make any changes later, always remember to publish again so the updates take effect.
-
-
-
- After publishing, you can run a quick end-to-end test in the live environment to confirm that everything works the same as in **Studio**.
-
+
\ No newline at end of file
diff --git a/images/deeper_dive_doc_extractor.png b/images/deeper_dive_doc_extractor.png
new file mode 100644
index 0000000000000000000000000000000000000000..c46f393d51bf1e2af2d95fe4fecfc397f7c8a8a3
GIT binary patch
literal 226655
zcmZsD1z6MV_dcZ(DkY6l;-o<&Cm|`IpfrqZ3sM@&NcsN*TtKwfv#>MHG+Oz82kj-j>
z^4%T^nJ4Ll;i_a=oms3PVI2U+k3CfmHF?!
zk3H{1zPhr?b!bd-#d8Pw=7CsgB@bu6a<6!KrY6^TYuITpOc~|Wi44<&p
zrtx~D&PP$@>MhN9y{Z;;fOb(`*fcqi{oo=nZTT4CLHsHMZ2i{lxaR&C{J-e@t
z8dvCTiNIR|b`H|hBT_}SuOISn#Vqbp>zBxO8kFUvDd5Zn8g6uR%S4)GU-kMb?0t4{
z;$r~GAYDk5VxVA-I(90*O;$L7+*cV5=0z~M(Q_+q3;jqlY^VxK%J_4
zGMd)1MFM)x&!GkRMq>IWL~Q*8;HH-?q;{7#xkRU4Y$Ds8;KkV`+4&*QT#sD$
zxsb1>-vvF)J~(ONP9Mut6=<1;K5z%2$?S(U#vB>*61R`
z$({@O`$&}2#xa<-T<)oHvn~f$gfNtOZn{=Lr{?8!RZ=el0*e>7MTs?C7sI*Kd53yTp-6p7zEq-~Z{Swe=IY%Tp8P@UHK#O^}oDF>ddg;nNOYkkQ
z)$HOF=MUZ^o|q$O%)21I;C@NbWi{20cM#4thHAD?o)GZjpGgTw2$=~k;hzZcA6Y_{
zU(YIpcL|99{GEt^Aj*M&GdxwBPoQkU
zb#d>Lr{B;h>?b2h5wHmbco%c)HBQT`8hc^Y;?Dt38`
z7Xy!d-GXYR%gf)#uNTx7mz=73Jk>MGI35gq&kGclOED^HKPzvq$|5xB?Jk={7n?yx
zF%O&g*>Dl=2ShGRPUTZ~4a#)yolq<*c?lx0~HaNvrLg4oSDK@aFlsk`mO)_5|$RHye~}J0H4-de7XF!IlN=~
zEz<5b%)M02^@x^%=+X`EgZwY$kaV10Z>PQ5RHDNV^wPUI;mOan&jizem-@TRhoM0r
zYd)`*4y1PX&5lnl+Sn|qH!vD+OR3u(kAWW^fvSe{S-3;Sq3JFFnC$2=lMjYRX86!p
zDiYpT5LTA5oBTvYES4_~wE?qt<745wH@odp_;FNo^Tqthj^Ia`qM&eZ<%xr41`23O
zDXrogxe;HVG_SA0#^|{hxP2AK+Q!^k8>Nkg7@zk-LPKPnCPeaqqQp6{*xPc(htDGW
zKFo$~%bi(ke>fche%_z*GN-aqL5$u&a2K2$o5{E9dC9JrI
z-}n9C;0!K;5An$L>&(iQbF028RsgqOJ!#}|IBVi_o#k!{EnVDlQ
zG@WH8&2rfSNP8U_o0JK5*v28uP`@b<_`w=k7*2HR$42K&)_#aO~;v!KMFU4f$gv~F;B#;=Zw7FXL`I~3WpFEh$JDV
zbHqgg+hUn(*E9n2YHtZ@t_%Mtij=(j~+gOfh1+@CO4E0P8Bw8X<9K2OFwIWUKP(1i66Fh@?Gw1*~XK@
zI$(suwi})(EH
zhNb6nUHt0${m{+1-&UZpQpqUMC!k=={H}q7SUyQZ(P5nHBeX7qYQVKcDK`@q0Bo`@
z3(Az1z3~vW?a_NO>bG>JRq5IkUEp0c_^sy8S9}H?sX|sQt7bu{nb!xeE8}&qUYICj
zbaM0KG4WAw@m+_wWAWt8lN0y!WMG%~@~(>_eD@T>d3CuuO(;LWD*JTkT*CIQt|=#A
zTx-iW`rZzYZ!2@!z+_h(E|hkYM&!LvKEbXs3%ZB-3j1)8jz`P{kX*1?`N6U{y9u<1mfmLBF!=XzRN(IFUyn{%xx7gnAsc|pwd5~4&
zi2~J2i+qRj%P)ceDmc%S4?8~j(hzX-XY+S85Z_ks!tSzeI>pw|rTzkm#u>`kdOF9;
z?;Do;i+;q7ERSUox6zP^@!i*}>ZS~_Rf_WBHJBVCe~ZRqUIpzfSEacIowhUjFs^P%
zz+v-ZpnQEtgd@vcfL02hqpB5Y+hBiI{@V`H!k|*qtXVcs$7u-bXh@@DH`5j
zNl;(A?aoQ)_Ys&$6SJk4J*dj$+B3s;k#|*TR;7o!roPq_*GF0z`*QlUtGQhw__Eqp
z4>HT#K$rN^Am9*$Nq-gJkC>gSwUy8r5wP
zEq7s-(T0-b$V0_uYoJI)rEQaLP7O>KP^CF1<%N8*&H(qFax>%r+Xdvd%n3UQz6|b?
zHH4jbV`$+UC0lD)Bd=kPKK*u{{adq>4O)
zLuDocy-F}%7%igL{2m$~cM
zc6(HoU%9~1^d3~v(jvL1p7k4@W#7H?!8tkyy0RY;MfuVaE_^03DV4O7w-Ub5eo-Fw
z)YVcxa3ke=mRY4)r!jou?}$GS>q8vHj
zS&qN?`CxAiyp8J+-%t
z6$fO)1bGtIIsXY}0!gnaa$@W|hGpeYcyoL~)Gm*d=rY3;V4Eo1NX>GN-No5uf-;|X
zsSI?A8S7p`hhVzJ2NF)yINLH5HQ6ZYl;3^7t#4+)W)#!u01_PhNRHBCxGqp&@Ny20
z&||q>xaXn`&x1%ZI^YhqN=~4Ic9u0afIY8I(l6E1PWIGc!PJ;e-QX$2HKecjp}$zq
z(I2o96CARRuC@~844}Wir2_eO{1Efwu~RUt=M^!DQ$1a6j(Yr$h)rP2xwBQQ5PqV`
z=s}UTykV#_+`n(S{UKT@fG^ewQmQ3KKjp(WmWpT}Gjuk6Y7KmL@aWOBu~r0h%CWo=
zf749AGx_1YzzC!DETz>5J~jwOZN^14BMK=9N#zNMs6q%x*lRA6?$7aW-d2&IKne^h
z*;y@zXR7&pL)(@q-uTEt5K4VJp_J+Ju&JYP0SGgKGUm<5@f?>K%t_*4Ct)Y}cbuP(
z7ICzUFID!Lg(Ton_@V!PYtO;{qcF>2oQ5MObk4u~^yR~1(`K^vLWF4EU5tQVzcYRo
zGOmOQRsD*7{VEad-h)_=Wv>9u*CBr{@b@`F#WV>x{Nv2!Ybk%tyvxl_&CNlDO=#@Q
zOsTgL8uC&H&Ts#5vJ-c;!Z|N0n}&plijjp#fcL{jf|AVGhrEpDBE`nkC1AKl05;V}
z`nu}>o#qF32$f9RbZX+mzokSFN=WwT@w)Pe!<}vAtds*wp^1v*pp}m?D~sZo;zND$
z9P%MT5_aKylE8>Dk%0GX_q>&QYR)^!4^+9ny)FiO2q0(2+@d3|{F2H~+5aiCSTc5{
z_#a(G_P>^4@q&m(?}X0(F{Ot0DJ!>fmKmmkN-(2PA_-B&$WE6@Oe)WQBa|*@nQ$ZL
zPztl1p&IV0MQ#2|rT<9mQyvLb{uOT32fyA3AClZ&sJP8oudrjOxlNmlj8?`WT?W;r
z07{ugEUbzIMCFQkrZQt7%|OT`XwA9wGsaeDfstrYG0#;FPK{fcLf1F)JO}rbyh_H4
z^`AWu5IM!l_ufCL_R--@G2POrQe=gh$56F)yWXh%*VJBf=XI}H5cjCLm-s$Iq*du~
zy{!3oqzhNTcZbNAG{0;2;6|66Ti#JzO-i$Vy{Tw{p{cp&SxHYeayVM5%WK?>bUZ8ss=vNk$To=yN7aLt7FdTdQEx2^n1>JJo^*txL(m
zRHUk(&QlR=hnaMFVlTwRWNdhScF0GiSlzYpz5X%ukWa!S+21#tq1>We^M3w_*2lb|
z{_gI*n6%|>>EYx30P6gxCdQ9uyO4#X_dnj1xq24JJl?Ss(nu8|FG7-d
zpeajVCbv8Ph}S7Cgf178h|DCEak)}uYg6
zZteu`DL7Ky%?W8cW+fZZv32x;9bL7c{$1Bpq$=|Hb+S;XtLso@V4=~NaV;`f$DgW$
zbTsTK*Y#iGNH-)h3ug-Q@uGhY{6Xq2tr2a7H(a$m)7G~Sa_8ErPj@xmCbQSTNWU44
z9G<$Tl)cW#$*{S+k7$0mMF0DQVCtPe_Ge7s`~pH*?{R#fQ2zwCM_fwSh@4NqiGZ3=
zsBcN=5r7QKcaOsau>OHEv|crD&Q3Ov3~b6UOGD2t{GQ}KMYDc+rWBAE0Ty!A6;*Hh
zrMsU>2{j>ml#ufwcd^Wf`s5^z1t#}&J;3L_f>%{qc;~N{p9-lH9?|N@ZbhxFMH}Ll
za%%7rw5OI2zg3BT=&Bzk-)iP9w`ZKG74}r}*U9_ysPB@lMd%)oxy~5Y6@=&^B}O*a
zW=)zJEW-czWfFMZ1BjT@ZC^Cg-aNxQ#(I?yX_rbAf
zwCmAoX{;2Lt7z$MF;9H;j9`fV;
z{ztN-X2*{jYU}JHz|iKKPv1)sHe0q6M}_^{<>&cJ;LdCNqTA}4npU8f++3ObHFk|(
z=FM;C*yHwhJEoQN+iE}kE@LKv_xK2@n#EPJi6^MnBY2K|&Y=)Lf2sJYS`R)4o`Zk0Cd?wygs78)As!y*;0#S<%d@Ae&BzIngT#lr2wLZe=TvXN(0`B~QAeiM+P7?BzO
zMxAMW>~nlCMl~YH2KlyJV#XaEDn<^XbvSvwzZvMluog)La4l
zy4dMZqBt{W^Vhxg^H$a+6Bd?zZx9*y=dYiPxe{{TJuOFWD`@FGZW=I&sQ2OS75a5-
z@rqIj4LPCN(9y+U^ZSde+w+HF*Pb=XFA@HC*1vQc&OMTyl2E795T-n?GobV6-gCD9
zG+T=gIk~X`vPM0Xxdsk24tD(k_4vj;Qj^l^Ma+tH(t`$j*a$SxdG+Ga+r(yWeUZcQ
z^E528IcQYWDfa^>BO+!wXZ1Ub6IgDg;Tzn@gX2S_3NG*Nz*XkucD=J@Ey@)-OXS3=ZSWA1H6xYj&N1i19MHXjmoeM
zrD_-F&_v9eyuF&_ZOMUoqp+cb+8%8!edFKzX5Ri$o-JPzJR{>1_;9{T=EHAhir4ul
zAg}FUV871DxT;tm#BBIVAMgTxN55Ru9qGd4W-Bjvjg+Hi%Yt}6n8)b0^c?yQVQl`EFDho^
zlR<@mfLLA>UwD!{?4zz{m_BdXR@_tA{@AC)Rx^a7yu#HE`1>wc-&E>Wmv$cacN3X<
zYjl}PlZni-S!VCW>t}$Kj=B-)(b>JWbAdw5I`5RrIECqhiRg~Gn2Bg9;X-`OOeyP&
z<7D(_G*3Nk8EsUvYIi+kt*;0Mb7>JnMu#F0?@RQHAdJm&Ad@*G0~O+{8(eXwb5f(4
zSIq!-PN4J7a3^cXh3P2YV#@1owmw+9L)s9<1e>SI@s(i372LWneE
z*6-~%w$;`r2=!DEH=z2kX?3^FSld?GQ%!7+mfTV6^Xjx5fu_>fd2;>wFfj8@()iRi
zFh2XjT~v!1cK_R&-TJC?H#Z=tmZRj}F?jVYR<3rkREWHqmUh@@whPbCqDsqYS>lDg
z7c3qhu&Cj2J&-L%dNhgA7FmJrX~GL3$HS%ckB!d4N_R(qEn3N3?z*S1?`seqeE*T|
z7S-%yS#Wcj$F1Y2+6=-7lPlj+gg$XJuf6_FGdX?TSON^+_%5t{=T@ZkuzH&A~4J<9h<`d)RR2W1Mw5D>kMsglr5Ka3
zzFLb^eoT^jaqdh!@lqqLxlop^hny;{yLRusUe(Aj)I5aKL1O6f8=(4JS{HoxiWFi;
z?HRzIM$s8>QX$i^nSoUb(>gyFIXJV_V4%J)pJ+2MtRTv5KrcpGF&^~kJ(r{Bedh?l
zv@xtr^dU=RLH^2#khkS^NvL;z`%9_YD8cBXb7+Hd*DN20X>A*+Gw)=iI^x>1HtQ3S
zVX8>y%;)INV$#Y@^wgfO(uCI72642y)Kez4|6mEKbXL3#rZ}{oRWcMUUpC7G-DDJ4
zER=ApXRF=I{~Yh&q~W&M??6`eLeQAEkrC7_5V~nc86{v)M`BWcqcuWU6P9Qbec3p0
zTKb|z36|Wvr3ByQv^!7Dx9h92{C;cdJ8=n&-}nRsO+r~%eR_5~h1-Eo>T8mO>NVyk
zPbAP~31N@QjR2{5V&ClT#YS%gm~zIUH{Rq;^Wj*eT)p#+1sp$xSJ6TbbiX!pImJkS
zxag5WY8Gm4=DxFh3b@`az*N5GWBJTG-$|=dA1LyDHT|^Idx!(64
z6aQWA->-vztddcb2o>cwGeFX!J3BDoHKKOO>T=4$KSc5`G%iD9SfxL>J5~!K;$50p
zxCK=d{vE0OY8*O3l1=IoXJ7WfRxzsh$;t0mZ~9{*x>GXt1F0pde8AqVyoujm{*B{f
zZ-#C`-|5XH$}(CREUCP@)e@r>`p-gtwh^WwF)>#JUq@o)U)_q~2Sy)9HWgLEgfKsC6(>UwX6wu_^8MU$96(^qKTqL=$y>*eLh&
z|0Tkw1feO)_HrzUz7cUb?^Ey^QEdd-e;Qg?k|}|&+bU^oUX%a)KbD_u`mb87_C15VZo0kDdYyaQ
z>544abfg5EFsMQj;@!t*>6J>}^Pf5KVV`Co+tB|I6P_YH$tzoYqa-CwHqtkPW|$S-
zHaqJi8$o@!21+Q-LnSwJKhijBbLxMx66)exm%elSFv0a<*nc812paiUt}&Oi{#DJt
zY7|x{(brGPTG+U|41_QUtrUafn(Dl|K6)Lxc+L(zg?ScXoY$RS?ez3z4YXNB>_Ddl
zGgW<2R^nQsKDsXuLGaUl$~ig11f>R?Yq}DYJRC~yMo)aQyn-!
zc=WibFeG;+Gc6nVY0oD2_*Cg+AR@Xbe?Q~D*__FmX=2`YLDy2Q~8f*c`^u?x$Mr|p_uolno}A2;kGdcFCqN+gedKg1R^
zq>rx|KN71=ODiwdugubJvMw&}D>k{MKE0Kg5-tE_77^1ESypd+9=*Jri4QqhJ$cMv
z)1MmT*zC-kqRw!=1EQUwE8g_F)og*WPp|wM2v)*^NZopf$MjmNFfX>qCOJnjCnuiT
zqJS6v##a^LuNkK*2Vd9geV8uSCATU!i*YUs{E77~V4D%fG>T3d-cdOsE{cuLGGZ><
zr`mb`yiR=YX*-fN!Va5P%ijlAl5KQ;-nwO=C4fhnDnhR(wE-Kx+)rinoF;S@%>d1-
zelr_N0a~STw6ze!B2CtnXFl$DXr^Lc>uveGKC%e%p>!yi_1`|24
z1e%~bOHK4dMOhp-i|OnnLJwoQ`d8M9v{W3Wwx(!a<~H}E1y~L<1)wagc8=w>ksGQd
zSKa@;1@R^zrev`*8|7l5L6AJ2S0jD@T{cPgw^UR$;`7>zq0}OdDMy7xk53+DS3gt^
z1ijkj?oX^^`I4$3*DRxLbJeonj0?r(QH#cMxo)R0nIVy%IFbaz@C5P8pfyt2$B&hBM4
zy7NSGD*EuwRTLhNv7XQK!8GgWbRK%=2Q>uB75VttXi?};zT
z0$*lN+gW3P{Qu|hc!0Z1bj_M4nZ#8L48BTu8(M2w0<5_p@hc5U3L7&!t=hjei
zIp3Ms>w!qo;^bC=6rS1Pj9iVOJGV-`1p
zm<){E!IxYx&U?w&a;4EK16CTpw{
z&nU6lE-Qci)`!IDN3g^ml+|IdxT#h|1vLvMB$6zJr?6hHl9t#^SR^Kip(BCHWx@Sq
zNdJ*l+-ZS31p}g+3{;_u%W>{GxTvdQ<;n3A)
zXyZ?&?}s|Xj(ymD|A22BGGolERdVk)-!w%OT0ULHgqv5%{q#x0vz)7PdF4LP2vVoc
zEs~$?*_6_j>NSCE!RN;qRr|3UgYMp=brYVCR$Y1{Uq*Tvs~Bq-yw74lq>h=3>ltL1
zgA*kFikwWFM)ikf_wesjJDap>%KF
zT^2ns=}o=tt#BQtwCp&gGoKm}cUcJ4+DPtg`OS{s2;g{p`sqNo;CwQUsW}IqFmC&z
zKB@B_Jt;}L)F%!`fve8z4|I>33-Y8#r^4`z9(5n?!-=P^4*>5pV>c>Z9O%L{ufl&?
z>!z$$H}6MCX`3M-&ZxfLpk(_&5Jm}1t}5u2rMq4|<9o}jLXW&H$Kw*knU=&ueZ<~+
z#PIZh^V)4*cimY^1a~t~46JvU&`#KUR`VYR{|q2pLnZK8e=c#7{Smb$k@h2M9;3@(
zMIXdD-8^~y@@4MG#w9Spvl1u&W=YVyD^~(XQ5L=y9Io}w>!(YEa?iG6mc!qFai%lY
zdIk^|+Wj6d5gi8I6X|Kn;jOI_`m-*{-9=(U>EiKqDBf*Fn%zi~7Gc8|Q0OQlc!V*p}ds
zt*&VK_3Wm@2q};GP6GFWk8Iy+dY+guvJ>Y2eP2&q4Ygtmw3dBv9Nl#A{fRAlYS8u+
zHt2L`8y?%X-yT-S
zy(}~sC%r7QeIPa~clge4zH6>BJ>>vBopF48V7nN3ZDr(LnC*5Bim%%!hA?PvlVYVa
z+J2;c?ksq3y=O3#SmJ;sZs$)xH4+)3WH05?$_{Si7=e+=)|$~I8PL21uV`gISoTGU
z2V_fUNF`i@8~6VKE`G$Sz|Me&j+p2cu!vVc>d`jz#w7}mG
z_GdD$+-o;8*pxzU-Cm@rykg|v!T{n8TVX$PX_3SYy&ftS5fw!;dfuyQopb5lKiy^%
zJun^&++)$QPGZVhY-(!C>7!Z6Ld#^_p~BOn&=1@-@T$l>H?~tZmGZnrVPG@r(s;wW
z_QoTd2OUOpv9@IxpTZqKk>ngytvB>szm0_$OkP(|%N9)ecsGvS^lQ;4(qD}1ZhA;J@6?;Uj00qiRIu%Z
zL0szA`El9Y72(2rrE!>sq3$YbD
zwd-`lc~0q7h*f05mcykM~PIRUWw~_ZQB)3Rn6=_PfzGG&b&$KVqTv%FXcb#
zaOG1}g{tdBZyA1pci~Wyj}}`E@2F=QF!Xi`b752GZz%vC5@od&_xYr?3T%KPmV3o<
zTUjH%bKt0B_;9d|?8Vt$a`b9WaPN%A&Po;ST}{aOK=y;<4^5WJn27S}>~Au1?X%8E
zSl5jEkvP=V)J-)0fM~OaE%zQ+T6}(^P8*BR$Z_UP(mWB&;0Eb
z1|hIRnm$g_#si%?xbi(TOFKw9;p@c;XuDaj_^kI@YHtpzW#GdiAbUE3!u&|b^>jHc
zZP3Z>Bi$*=vB{}BZzf=yO~RnsG-eosgd#T)^&KJ%)#HcE{DOj+G6B9>QMZoNSv7$h
z?dzZk^Fa4eTp6pV==kA@vltNO0u5~F^3kS7vhwqrh;73e7zE8eE>%549a5S~BO5YI
z51Cy)Jn%B-MqOdc7EZ$)eDtY20B-q{EzGQr`og_)XZ%iGdP{$tAD|@$PE$W03$?wl
zF*7#y!A7<@1dR+`Mz*_Y^#ttim)H%!JqJ(y$Gh>qwDL+^8%xl}e#uIbPHtv@nh-L;
zX($j)nfu12mY9(AhN?Vg=6S7U1_?CCHjqATah~4=N(8)46h<@R>@UM$7Ji7-wDj6-
zN_^6FGm7b$bX34MVb(S-)!@DT<^5!4>w(*zPmlicol{hVl?&830p#bawvVdcX{hS|
ziqptzlH^mrQL$7m`{c5><(WU+TX!uXrbKD=6n0ayXgPlGMgbSK@g*`KpR`^==jRh|
z^Z*-pn`uuX_>^+x@TB~Vsu_x{rwH@TP)wo#W
zclM!LS*QVa&0zqb{}?w26*ByB?8w_0LD5YLTeUlA_W|AS^umU+7@{i`|2-Bi=D
z1MTeDT^u%pLf3JNFYJC}iwXcdlj2j-7zsY_
zG8kyt_NS1o`{1B*x_wK=@pu?%vy^*30K4gU*?tpzG_SU|HHx(iUVbJ-br#=#@oaN?
z=HV;XS_?{|F52|_51U_pF=S;RGV?m*tef)>HXrig^b(JyY?*?sPtQ&nZ+Q;8K_%|X
z=!wt`-c<}Ag4`qfGbkbdmL#8POlPZ$*RA0=U={rBw@^haapTjA1y7vy4+o8MD)bQ20Nal-o-0LZ!EWZVYe8ky9@OIK#=EeIws`GWvj}c-m^v|GX#o!~sMtoz?vZ#2vSodp5xe
zz6jeaOI^hC;NxlY^WrWxN_^JQi}cam@ruF1q>($%u3aG{RU)Y!Ry$;3vZFS}2P_r=
zpW9NLu=R!O`xCl7+?EU9H~#@%RG}Van?ZAZhrWW$mwAJP?XS&qmjAk|EUuEqc5k>=
zRu1XsezXX-jaa+z*`aiF;h>Lf(3!PH_M9x%QdI;PP<^*n>3OT+chtb+lc3#mcx5VuR`aU)
znQ6cFkMqEifW?M(aF8;!2^5MPq{2Et@zo+KVIfMe?FV~G>ItbMhfwneQS7EW++z~a
z+>TZIoFSCc0s*qIu*P{ZFPefL({TExS!0F{(OW-mTf8$*>KBS$zE+3NuW^oelaJxu^qnaz(7)?n>lS+Vp
zO6H`F{#}$yyH()E#Cqc^1B`EO(pJ-|@ulS~SA^TGptT_EO}oLs^R)u4f$E?==X;r1
z&jO|)4JD~sL0iZA)FBKH9#7VYdHwUJlr>>b9Hrmcg
z?)qe#l|ZhYOJ>jN*l=rUmgiQ?l&*lTsxhNqMTzsRi3-hjG3j$&Gp|E@%+Am+bW6>)ejFwV|)jr
zX`fJoEbCIernTY0yQ*{U>!xjiU1z};xb4Nd`aRq>7%8IWhae_9-EN-?JnqPy9@}jA
zW|WxOTAjuibb+7_s4i+pRx;c=-;d|Yk~M3=sGNfLfv$4S?Jlhy14BdU<%g%!_-ug1
zKItR-q&*Ev0JZ_)CJ^7z;A%>!x}RH-=QqEQwlb>PHkJr#W&aMTN-^X7+H7r1zPA&G
z^}y98T$UV?8(t)=P9W$)I7Ka}kFMbrlY_Uhb|3hzT^NAv#HOPH;;5oAHlrL_KI@}tr`}XC6%Gy0FJJMyGb@s2)Rr0DY+pUM*}hC
zlqCzf4bbj*xDlcUgMF3c+Mg=0!ol}G>V+@LyTotdLv=Gc@rn7|S=%-rwtE%{b5$c7
zph?oJ(sE($-4?QI$ASmUsw)B(ey9$*M7c)et!~x*Ri%pAI@(b
z+1_Trt$_OnyPw}+kTb2jazRI0E45(4Pc3F!aS)(y=5{ca5|W2mbeV%qZrA=irm-R6
z;y9a#$I83Cvw4Rhu}TTPE?@7`u-M#wOEAzR>)J1@kUnH8(a&ZlykzR0Uk
z9!M*wBua~zTf$dD;?JQ)Eom}_oZXRxT}5lkyQJx-Fa%Ozq8Tvm2|D_iJ7`p5RE5d5wURsTEWl`1zRuk(
z*p|J3K;qD*`r&QZ*?`U3VF>)_WtcM-gBmxeE5iTdxS=6LoBzT4);5i;?Z{Sow>G$+
z->%K+ana`PEV98@aCq<(%Y?gzcJw)Hv7HA%whA<>P)+>?#@jk<=A7rL0+{wBOh?U6
z!-@$}dOVo(gnT#)6LY@-<-ccd<8{@OtGl}GP~YUdCwP-GQlIX>*x>(uC?
zabk0qE!E|MB(eO`ZL3oTlG
zJpKuR3s;eJd(nFxdN@dJd7=d~A^574(u|QD#lx(T-lFDeQ;lFDe^=Kk^uU;aPZ_2{
z=Ok+r>sLSEJJ$P#WP@|&?Cj(5P(xc&ei&pqj*Cf{9ek0NB7H|@1E!(86kuhhD0~_qAq2n2F{qfy@
zqcw(LqM-eJu%?Qd-IPQ$vZ=88Py<7>{JkV&wEP3BZ|&n=ob}r?Y-UoBAI3?1!!8%1
z#w{T+eZwm4o`#k$tz*igdsSK!C2t`QO_sEKPu?6HUWZnLWdq=|uI&*h%~w+mRR*51
zPet>BUD}7i3rZ(hldZ|UQN3nt$HVkB+4Z|Q-q7d(;Q-AZV@+8eC7}kj0@DZhBv9xm
zcb?HmZ$@KZnc0`O>Ct?tA)RYJ&>U#fn)2Ev_hWI>H$Yl@fC7LifEwYJv?^WFEI#x&
zoeH%^1RvbL!MTrURPOyN)qmq*o;DBC2J09%`dPEXUU`XxaB;~!4e0urtGjXLxIxH>$y6P!zZbWSi9rWFrd43-R%5U#P
zQp!DeZr5b$?1VBeS?Z0s6c}F*L1~zqY1$Up$hBCXnJnINB723;;tB7PGz)Z~Vi=`&
zFWnBK`WpR7owJSs(n^YHn3XGWt}wnwdq)ZBnvRKbs4<<3`utDwjf(ni8a|&>C6T%o
zN&YKyktNgCi;rr47@DuLe2^Sk
zA?crLZ@oZpTMUqpjgI=hn*@|5_d6YDzV-bp+#pXyq;sfT*_COU-(prPSeq&uh96i`K_JP2ZQ&pZs&(lJfDAPT`UFIVyjl1
zF{zITWvUQvHtjoK`gtg#uA>~^uw4irwglmt{eCPP4C-hF${eC$T-36ZzUN;Uent>^
z%c9uY+LgogL$o%p9=W>qyt%ouH!K$)_UQYRw+n#2eP^tErLtl6O~)3hrRVGiw*4ks
z19Dw=rNVT1FLQa_-11Rz(WwyH2c9wa6Ki3pEa>+UP5Mh-2V`r0KmMro7*`8Flsd?V
z#us2D0}BHF2wz*%b`-z=Pwi!>4~hDgO{L=#&R;+Myu4kg(<{Vh-cs}o;G;GtZAusG
zFMK~#Zj(^N)-?W%4}VwO>&|j(cs0`3y%-M`pnv22(QVtcrDD%neJv1oz-4>UCZk_7
zTgm?6w831?Nx2{We@NkyfgM&uU?g`2_zI!VE7I==e4WpkV5KojWnq*8*PakW0?h3D!dL#E$
zvxSbOT<^5EF!uEO5t--8PWWC&yj9}*mmsWjW)^Pa|QKqeQAm9
zxmfcj_(dmSD9*&^}#)6
zEtS72M%y%bn^{?4XFUyKjI-Z~`Y7JZhib|~CzBT85>hd9NtogJG
zIDmFzjmFjO3CZCinvRRJ2F|k%Gx^f0)8jD}8+*CAS`kgSoplPn1%>Z1_2a|5o~1=LVSdUkOVW1a=vmUKQuFp#Bg(yWze1v}nOtX^_$
z;QWCPt7Y&GuWQMP1!Fsc?_F_`U0t0cH@~6
zKMAZde$ADKw}6SYi+{-=qnx+wT`7a*r&`f-=+0oA{@D5%{AqIW?@?z2rx1>UUmIj25-u_gv
zHu_O;>1UDkU&R8kl%W~B$xY8dwYlNz)sJ(zJMF++C!6(k-{IztxF}fenpj@|_10L?
zZ2LAJ^+}eN+^jf=Qual))bZQ!l{d9839n?`x7vDa@9A7Q~q
zr}F%^ju{r&)7n2e2VIXG-Vy0i7(1$*>6{DoF(=EFW_je8Sg|D}~Q=VO^Sn=tf^18gaIEg{NS#Mwh_RL@X
z>*BKTAhU-lRzvf}fQp)79*5>Q+7Y_Btvr(slc9y`G!LXX&^=-I7*+(av35(4?HN85
z{}$M-AZOnFn(*B3x|2rPv?WM^X2|R)Y8GpiPpe8U}{X4-CqR(!n1$eLC>z
ztbjRix3jBgmL!XK=MPVzGeI#81MyqIXHGminUkmZ_?@=s7kpf?Sjsw$d#=sJiB%sO
zBGw`SY>~b$+&M%mu9b$twk6H^4&5o)4xaPt!3c+x#%8D@
z0!2-p-*&v%VGGW_I_qw}a4wM(^aY={S!YUuaBkMlQCu8~&RL6l0p#)NBPFu^=DM9%
zwsSUUeC`iyQ$4o>=GL?zeM}k}8e#9tw+_2UqTfvzdp<{#0(PjZ8+ds8NKKXx)eRW*ZZQH(L0g4C+s0av%bax{l
zC^5Rb8>AaV0RG>=SLxaFFc3M~ACoM{C*du(%>(1VH+imt2X*3oRxpLtqlR3iNjW{r<-Te*
zd1v?PBSSA;&R%fu9E7mjdiTRXQJpH|!FX!)gL;2-<5ZQ?yZSNQ$Xcyk#rYjs0GIj2
zkJH(Tw;LRE4erV0K0j(Cmzztc?Q3YSPujtBDvoaj?CGP%;WE&nqsS@8;F|vF8LQwG
z5wJ%}H-+D%-+O_SF4^uS3a=`Kyz)o$^)4&O3OHr%TTJ}{VIgO6Y**csR`zxy>U_;m
z#n{kyjTo{CXJ~Om&y6g1^hB|=A0Y`R(sKH(^BuSM!7;9n_>jx4ei(?R#k8duT_Iqe
zz}w<|V8i$W`5s@l{D(id>R>G{AkV)Y;eo(ZOr{+y)mlc{#Br?RPY#iAWChYASr-{I
z5Bh8ocmcjR9_SOQX~g6xihh!M)@Go1qgmsTF}^;Y1<_;BYfAT@Fh;+SBj3@aa1Gd_
z(!WWROwX&u-@ajJ&TU+;S%At#JDPk7Y%?5atOWNfCz88t8a9?
zVPlk+#gJxxQXdYFRnE5DOe)W9ESZ#nya2j(IOSckCx_*y;Tl2X5OEh5;!1x+gZrzy
zn+Zh|v7!8@5g%=M?({g}`t0>uF6W?RR9kNKcxE+}*6e1%x4CceZ8{+hfNaS>j6604
zfTf^~rw?jw>jurXwW$kT^Z07DX0v4f4((pn95@Zo(_;|Rv=h`Mi5t)K>oFe3{iJ(K
z){<5z%hR9*?M#?~IwOz2ht5II92V&d>Sg*L`i!B=lqlE?o9#-6)IEx6I~=RnIPc8w
z!}HI>4cfJ=?`To)o9o_0P1P^E8hchH0EjbzY|ESVfUk4(JYu)or6l8K7fQT?$A|In1D
zZ1$}#d@^qcpbrv_rQ-i9Or$?=ZK`&x)`}pDmp$>bK^KRHz%pl9(STcSoaw$*1F|K#
z`r2v~j!Z^VkK2Qa``Z%)h&jxe^0?u&rc_~BTa@*K?@C|k+B=NV6A7SGs&dfLtk#gL
zcvkWg-@>soN)y1+yG;aTO1#zz;(Mk2AuR^yS4TuBYxMfXvjB0$(aU<;zC%@bRz*30
zJJ`d-G|DA!I-U7~!YUrQnTQ8%JyT3z+Vo4SA>I$GpDlJOB9c^*JCA(2eSOMK?YQQ|
ziUL_FXTuj2!y)Zs=%q2!Bv*rQEdkv=2gCYTas5#m_eKpV0B!TxVc|@npKT0~AAfljc`_Hl9_o!ISoX4uY71`%RL}YT3y6PQ4n(5!pq&dbRXN
z$eDP-G}!h;1fYG^#bzCw1RIg1PBigZ^U*^{BIUZ_Kql00naY@#{!t@+G
zBwBrcj3G}d!;2|NGTH#ZJZLcr4BZXpD%rYYPB-9s;EOOp6*Xe;x4)dj14k?!3o<^~
z^+X&I*aTe?7!&FuL0;FJN0SqcyU^@rE{{Iv4-CL
z^@OZft!U?>ozwiUbxM_2D%8$ey~o8mcI#j&@M05U_t4Eb#3LKJLmWvq#=gEFqE9hX
zLwhJw>%!Fr40-xp%!KUeXs9+dnvzr-L;gGr@Pl=x1MFmS#9F8~?iQQznH%1;=~v!j
zD{T+a7*S!{SUpyyxNG0o<7*XcMJ|2bu7gcxSl}
zxQHO!?&u(9_lZbTd=*$(;_+bOwG|?9UX^U8cnHZ
z5y>#4(1?BE_=4*GFU$IPGtjC`sfFqUxdR{iMpplK2K>{zYPDatLph`R8tY9LL|yjx
ztaYOo>pE9~a%^|#OM6iTcR3;`9y$NbLivj!fPvn$J~%Wh7v7aDFOj>o-gYb3f7evC
z#V#SOfc56Lcp!pr(vii!p(n0}oKqT<9f$H_N`A#i^z)$gvzhnFJ%%BN5ZO7g9NR#A
zuRr*wZD4DGBHtk!k93(HxPpUw7syhZaCDEO@vhzwzmh*}An%*q^s
zT{T5L0+#nTavR&-;|@hk#KQPuU-gi&#V9_8LI*R{RD2QjvjcHd;lsS>&lWeHdx
zt#3)r_w(;ln?2JtWqrII?VBR(fgQ^CYfqd0FBUOvPKUV~{9bTO&?}S1{&>Nc`Oe_OUCI3fu}bQF
z)Odx|YWl-fHYXvW2KPgK)g%MUzOB-#(2WKS`?KB44by*}HZlA29YOT#!W-~p0JSUP
z*t(`1QF;0)-Df*qayj<^-1q)=9yBz#GSnDIALuFwy?=^;g!NSTL(W)THqJyVr*H=e
zdk-{g$iylI!ibhe;Bt8jem}JdE*StdrdwmjFM9nskLst%)7|jH$<*z8*$+K=4%c(N
z*LhS^XRZ6r9NV>cKdE(loKxf`k#;c&&5sghQvd=sHvX|5N7b)r80&^$V^5A
zeZQ5r&3@z{Y$n>YTQ3l>ActBSeyjb(fG@n-hLTt47KlN!&)2-)u0rm$V;aKjuz!nv
zgjh)40=2yS0xmCY`Yht%P(*pmK0odP9SFze=H)*pdLkvG|GAOP?Nm*luGjxPCIgq7
z&FY2k?5x%M>qAGy{CncIPM*Kt*Gs>JTQdjdpvB5-MpSb
z)Q1djw|?mRDB+~Rp4;}JuCY$rPT&C;3f*vrzf9&s^5O~Tp7zT$H`RxPZ7!P9@iXbD
zzK$O+(yOCwApREOVVtE;I(|+BuA(RR0h5b`3nC!|f2ApZ&H1zND_of_4KpR%m9Ar>
z{f#35GW2=E`=37|^TtZ`xiJZyg5N2KRmXNEe~4&PKpE@bYxUP`2RdATx*LL9LAo)Ah{(G+)6%(#nYE%*VBH3jnL)?cQn5F6N&sU6OA;cJ%%il21b_G%b
zUxC6+dHg{3q{URiV0L>cE1VJBiI0zh`yLAobcywa0EUe&wOSj+VAzdEZU=rIxepmg
zGVE*fF)_m@lSiIw9~(JkH(qMMp0i>2fU9<_*aC=DdttsdT=^(tKAQNlXZRIBFpWi5
zuHuPu-%@?V6~z;8Vo9ePz=u2ZApJEB^OjoGYmXXN<)SLbJmrt{cBmrCYfijoW9YQ|
zIlyXZ&z6JSitd>-mdgwIBpPEkpf-+<=Wac$9)1iT?&{CfLClNXk2mi8rE@-Uv&lLBIMT!m{_2(&@Qeo&m?$h>UmWxaorw
zLm?X2(ZPL&`dL%z>z6yqemf(MKnI8mlTx;j+)PB5^5?+~VK+{W(dy=@pQfMyEh5S=Y&zCSO
zSWpl$fqI#5`-m|6Kog=GZP2)G=T4fg-fE#)Wcy6u-^2Sgm#rN{tC}B4*z;c4HdK&)
z(FK10V9U%eBjogvSCZ7aboFHq@8L8+@FN6=+Epq!;5QEqGa~l;fuZ*@X)BhIzRCW!
zHW06r)kK4mxBGh$A)wsJY5lmZ#Nv1&%@RG1pKQSrJ#F@C9jM(TyCbjtv{jAW)HI>{
zzQ~!vC`^PL-54u*c|3o;+A6^}+<{)>Y!R6>{O}vr9@OVDLM(tLw^^4XI$fU~JW8;&
zNS+qRLfB*PDE>0F3iER$_Q#xi=wUc9sxtvPKjZT)QTK=^>U37l!`x(digt0}*#08_
z=#eB>2AUHQws3UIpagEAUGFe^yw0OpJSTd-7$@MoXz#LYcj~C)h-m1Xb{Rk{N46if
zRXMGQiaGl4D_%TKJKpk0;>a)ZGY(D_~
z)|nm{8W`~A0YL5nj7LW;r!19zr!{Jr12@?;m^h}As~bM6&eVxo`^kE`{GvZoI>Nxz
z4lDCX+-BujJ_Oq#S2l6>6d&OIQ2n_cxAgrS1cL>slOWLz0>NuR|Jq^P*l|?lgn|7a
zGWZJ{sS-LtNv0gW>Eqt!QxgL3x;R*Oq}-y%yb%kx(VsXAi|DmgCN8a$>C
zE{Tu)mC%Pi87x#Pbnv}jgEo7+>U&>$PETv%XrgH8@S;8xC!$O=QZY~Dj9x#%?(_=7
zEPV?D+ueVSKJaE>`DX(1y>;H%W<2X0KUh!FAg=PoUR6HGA3DlfYlsE*V=QiFRLy_N
zp${q^M>YL;>Fc-fEhRr4!x2uXKS~vXcHxnIzNogH_(|36+x9=Qc?>Ywe@};>sEbeW
z0lf#Cs`ZFEX1h2IaCo&9aJD0}JlrYQA8>JwUIx#ezl&!F2{)trC=*j0XJ+~J`3(KN
zI-yt>t65Q>(=1-L92|m|$rQzg7(xTj#>(wA<5vtlry70sMG|u3aV}=hQ2`I={iy#r
zaR1z~e|dKaLZue>9QE!-w3S^Z`i?bamm`9`>y7C{(FiN}MItt}Yx0wS$#Z=pG%7HQ
ze>vN&(TWu6HzGK5o+eB$+&-Vg$m6aJQoC}Zlm!}qxv2UHBwt4CRyuJ!rO*B+t)TIG
zw~g_n)2$}>w8v~yPx^Ai#0ZxA`r=E@&H#;rsN@4uO_TVm3j
zU#PCh>RWnhUcA0<=
zrJJv^xc#eD*T@(9PBV9{IzvJskE(u2($B`myk2)Q*@>E(B63TJ`;*)}NUlzy_UYIU
zS!OoAqlEaCq5u?Gb9HjII$LFza>$Hw#c>`?Kv$0KVxph!z3@W9ibm)O%Sipe0DPnJ
z@ru#Kxt}yd%ENiRj9mD2rGU?&-s8oQk+h@;kH?Ww6R>`@`j}qlF;TK#)Qbf`xPcZ5V=mq()7E^V)ap?STMG^>4lk`v)Uc2C}UjWu^a0+LiStIeTa}k|w
z&yleEXPf^tX8F5;fij7s+R^OHc~`AMhp9ea2jHpcx0G8sFta2VPLw9eC6M+3gKaU~
z?am*H*GSIU2vbo55jV?XSP|VlpXF~pK0s4d`X8*1so~Vx!;=LaJfiU`jan$1;t~0Z
zViA>MTwDwBn~@@uKVd}n-0S=BQrqkL#fzEfuIG!ujTQ`)yG*s{`c~N$L{Fg8
zKNcEzk|-OXvM$xcPSTH2r1@GiD5z{-`+DrVIRAJ|8907VaIo_U;bo_fb#GPJzM9lj
z#e@u$*!XDC-=a8ZWs!NspdvOP@lb^O*qfli@57mkid|R_VTs-G`dHP6#->|Tf@I6E
zu?;4&M_=y|-Z2PRPylluukm~M9BqXjP5qi0j_YUmreCnYQv(r(h}IgN7{}djrP1h8
zNzQD0V9u8=xi$?0WJhF<;?(*B#xx=v-Q%Z|w7~3Qai%Mt8#j`jD|<|-q(ZI<8izX`
zx7Mh1V%syR(uHs*G#r@Gr%nmBb5qmovr9ftROR)3roMl(iBANkanMizal3iDXza`lEg^umz;r?@Y94&YwC$cW
zzGCqwvhoB_sq7$2#z?aLL?z-rasMmLef4vedG6(H*W;bM;$xe^<3vs2pI8e4d)_oF
z2>Uz}q5l#%5e>-4XDssGt*^2+{QLqr!Is8R4Y4$BSp+PVh(+Qy-))Z=!?#FRrB3Ae+?zeEqZ
zBHoZ~rcz`w4Bd*(w6Cv`zWPG7ejln6Dm}izfYC4A#R_ZWn
zy-i=(vvy;i%dnrc@v9k)-Fii;lh_ZFgIQcUS7HM7gU{j|S)8F~uik9Q_#S4WrZ+#z
zy^uh?Y`A*j1oS(4h|{C3d9mjzL!e_!D@?aQd-R?lEA~;<>;z;u>D-VPY=J&GU}!1&
z_E~U>pFfQtb7i8~mbCAf1(wu}m>wQhsU7(`0L8FY^ug}1q`}%GKPF}f(y(rfq1thpc_~VF=)PxL(OOy5PPNiQLlh`gA~a+GK|GXz*XB
zPZd6PVm$CWO`cUxO-WGzot{m5xva*&V-O2?ZEpOPnUyzqy?)A7kCL?%*^Vz_<y~n5j1ns}mAI#gndiJJFxJNUs;veEA
zCR7yN!1_8d8~en|e69cuw&;9y>Q{3YFpmm3cC&yiN4SHVvp!5wd4HWzv3u`wPBtK$
zbFvi$-5W|fd@4a#Y_sMN+K&m%nlx0pB~|4Y<{9rSaLQ>My{C4C#6+I<^KK~WgC1rD5HpzG@{zG7}8pM!k20;q4!2tLm8
z?6@`tnCCs@Dl*5Wkb>?sAe!JF};EX{WN*=FeU5zq&UX*~&pwj3|R0n9TE_Jt_0=Wa~B
z@r{XWAocsD>Ft?*r
zFw*X%j4QLL*uTca1)d?f{BEIp!K&qC%n@2S07yc*YrBLF5W-^}#^ZMbKZ>Ub4~Sxd
zZy+`H$C*+~f}F0KmqYR8P=wi^i_f2EQt4Etm(FT!)?N3ox(d7IwFrQ=RZ~}uW%9Ua
zxJTgd9>bGZfW4u|#iDeeTEav*4erBPxAF09x=u6b2Y?{U8q!kLXLl-XVs9GRVHePB
z&J>&xm)5uQtsOrxc?qpy(p4FsB8t*(xFbqgJL4RF+%*z)+&-!?kHkM;JYDX-*h9s6
z7CSO;ux(Iy@A#uId=B#_nPsh|QBJsH3kvX=PJ|6PX_d71i9zs_rpE%_xRO9|q~F
zc5>128!tYLZ(0hl>|#>G;%|i79y8`Prxd)jM`?|lsRt!|k$&va}S0V^piZEu177eSKB&_A8hu0{K*BGGES&5umx1^5BT|G
zR8bp^9GGX=8~7%QF-@t+={XC9((1ivjL5N(FOFKFdZk`*XA9n;rit%uxt`x^+4_xO
zRkV3f@GSaHX{6tNeZ?aG3+Tb&h6TF8jYd<4^KzLD11XSRwf06UE-0|C9;*TVa!g3fjuiXDcW6E^xb4JpkAi{lf=F$L$@
z;O66HwAa(>b?cX#39Ch7|2hi(ezkuA8eN}STP0lca_TfaNcPwDGrjXoWKlv9+GVqn
z6!PH?J-%C+F5$s3`2+Bz$#F5EZYbqSkwWd_6--~<|Aa;VW0{T4u=iP{Y#FvT_(6AHA1upx8R*$Z{mG{n4Y24`K1l(C9jR4o&~|Nrvh
zmx{@lj}7-$>804%*x=jG4Usz{t4{i1;M@7}syItERQw6W2}EvrD+xY~U)WNH>y=joK90SI0+OwO$9ER&*h{1m3eWxit$8Oky&IHSw=g_2PvXWiq*;h?|`x
zQCO=cSpSDr(z3m-6J*6EVR@UAkI$61uXMm$aoWlKtqZDdQA(d2EXH&=K4H%Tsr4He
zt)-|)C2`|=%`u%#2FaD$mBifgQ_~(QTo*g^*$T<~7~i^FA)A7qxOaRczqXeL-CqX{D;NMpk3h%L
z6c&6!yV_W;J?8AapE|6`d%dTQ`3}~k88!v7aR`gwV26j0+ROH1XLURhZ2{_@Y>tMhQ|T*ChL_c
znGXjs3QQ*qFr8BgLX)frcnUf=Q^}|1yJUX)KEEtN74Sy
zg?1ehRSF$xw%IE$_Ch@9nEoZI^}nveYIy5?YFEQX!JF}kOlW>W4`if;lx2q%pCk;o
zT_MkJ!wRlt~By(hT$Ozx|zHpzH!oFc9-Y&
zKWy~R3+%rzTJLSEj>mR!;j&nAl$e0-IYZTuhCKzzBO}1v)v1{IG72}<;_<#cmG<#C
zpb^BNft(llbzZK>e!Y{>DMvzv3>jC1&BAsX&__#H5PLYSO$t5Lh?Dvpc?7jX9@kJ;
zy`{ZwnLw43b0(E%=ii8p1kiipm*k0yWJ})rWq1$hunu$(%q*G_HN>ZIVe^Y=N5wZ1
zHpHKDa^~$=;Lc+OHG04p7Tr4D$lfJ;U~zGNYt3k?3Y?{irTPsKiPg*;lm)OO_nYx@P*e0y~c&TrQg-}1_G@T
z>9(@AFAC|i8%iaxdyT;6N^>|x#^)fM&_QQ)usWP3E_QI$-nwu>31AZA2=0mReb`%U
zBUC;lil4m>kKijlWXaq3xn
zv^JBV8qoGjGguocSiT&%toMwz7DJ(0Hw^upF^!Q)u6}#kZ@j^<-XXj-K>d>%OSSP;
z*faXy88f@V^=ZCLzfa!88Gb)r&B}g*MjmIQpWcB7vMD&#!0GLtk_fpE2auVRwo1SK5n+{Zwa{aN}qQQBN;^KX=!$%84tR3`{O%6;LxKDEe232yDZyqpa(S
zvM`ozC)0r%PK{N8=%(VGt2`I2SwI?rxx*pX9_KUf5|K0*F_>P(t(1Kg(iP9BkqclR
zb!VhGrl^X`>ZCFB=^4f426B`6img-L%
zS4sR_9M*a~X{Fq&5a)GaTLzJ-7=0GqdO-kUs7lUbGYh3H=3#d+)VG`qD=hnzhSJ!5
zl&8v-PPPj>4SjE+!{k7N4ta`HNl2@lV;1n~ZQ7IqSd#hp=Q(W-UGKH7HAw)CIS-%Ashmn81C>f%>Yj|goKCG+x?R6t0mF4TcIAjGegmN*
zodS%C%)vu5;MomVt1-8QO53Zz@7-RllB%gRM+$(i+P{#yp?mGdWb!yy5pEW}ZiII)
z%QcF!OlQasRl2)w2_+h!FS7|4Sv2X00US*jt()O)WpO{!hKIRhilWHwMc*R&yBB{^q|6Auz;bF6kc5##5CEf4
z%k5aVTS~v#NE!*^dF5~EHIZG9laH&BykxC8(b!g`D>W<)4caXZ`dsvXxBUMOI#~DW
zyphRCj}!?6uN3pY!fUH_ze&5ud+I(U-lQ9^n?d#!^kfro+@DVRW(3RGO!iZzYv#gY
zi}l6gr@bNJ$iwLtoQrJsVl{${Si8$Nyj;pqR^PvQ_IA{U2fPO;FMPntrm5+))Zvd!
z@JEDM{#jr?CI#zZK32+!uL8$BV7aEuPp7g$A323QASN+HaSk`RYWry6tl7uIpHKk7BB*
z%Rri#hdv0jHJEXpJo<|ElKBA%Ub>rrdtnt26;cx0iQ8aVQrv;B&7bY&ng=DPhPAMA
z@>hwm2aE-dsjJvzjMQbO=TGP1+W$qn^9mOH`S<$JDnf3Vw2$>`NmB}Z&oLRDfvB2(
z5-p=&bZJ;)PQgpdUWL*eIa;{eX?%RbH3A*HfO8XL2(0uL;l9$F8I(fzOX?~+2Y=B3
zzKu(7DHMdMc;()eDyiEDkNF0kktpZ?VH+?n@!DaJU7wyYq4IGdgNDQ8&ET`UkU>Mo
zU^prA;CACB%5nU_q
zc$4@`?pZpo#Kl*d;BcmBs7n`b&5L%gsL@k*a^n}E6)9GKds}0FLPA3g1w}C
zVo5jK<}+<8?;$4ppFL6b+!+*yl1(A}2G@cw6*)Kcuso$4d&(JD=Vi~Jq;D$otK$xI
z4zZl;c=S-mSw~OaJG%1b9Qhua|G4jcdKDJt7lf%zT36?*sQLkes5D`+s2{xfeq&Y2$9$@#
zr7goA)zyT&yL*M^_u1Z=|IYo(3~{~_G?~lHgx4Rl_8H$W_-L?A1!5yVb!N2H%Ft`>
zAEqVl)fT+va~UlEC$VbPAl%8Q12cEHR0ezc8@u2Qhy=`?oD7#VH}cx|qg>%ELFUy}e;X8?kheHY4~#zC*eV23b^F}GstVm
z!_6J$HM|i1aYj94xyV3E3wt?fyxhvswo=o!RXTOrDW%-SxHl5if9*h>>ML*}O_zn_
zt)6kKuCDI%ei7q}myX92TApy*6>?q*pw?opgOOPciLA
zM$5wKSR|cdxBMzI^Y^Y15*-a)pqPVA`{wlLvFh)S$iikrV(*C^+6kxf+*72D+i?4_
zGbqTRvn2cR;8}+HL1<2|j-HLjRZ)?e~yymezq%g!8e;>nD!RZ09Gg{(dZ=rj_{KY^FtM
z>VWjp7eB)4104ecCp5a=Mb5Tm{nNMe#U8ClqmnbZXX#=T5Ak4(%8xFU<|h-ycbUFN
zpkgxVud?k~utkPHt0o7Af6I}DTctU|rPn6^XVm}`ref&W`A9>S9BgcG8F6KKj#~l?oLoY-CSb1t(nM38
z&-*bSW{uqn0bZJ?rrgH9ck%H_3X<)AZ?r2|UKq(H)EhfwK?^mTV)P8G0VRjB@0soY
zud?ft6j+36w7ih{)NlGAWMCrmuBywvEcZuvRcLWVZf=)&>;4>=_Pj=Gb@5YoR^S`5
zfh=>J^cgNqERPnP)S3G#I#@fB5T@-(S$XplVaa9XX_L3b^7ELR8C>qwz$Q`*x74JS
z9C)bw20OGUAL&xB4=Ppq?0Y`l83j(bmf}ovdO7;A83z+-ig1R0-`lt6X5FIzbPIp5
zv|Py&ZkMz%T^)me;nneRV}81|;rWvN(ER2NIAw5=D5vm!FV<7!QnQ?ugS|aoOyTD8
zvO_|RAaSJL{B8x#FfIY>+(b*97UcX#ylO&_r}lY$Ml@{QlCk=cr~5|6wP1G5
zViYhv2w_E@rN!IVh~qWwOCSKfeEQB)q2Q5(*dv$er-{9CTH|n2mq(Vv$J~U@O-38F$45&*_O$Wa
zIiHSR*LuCuwAt&3w>~#vljw#-zjvilHC!ZM5we=Wz}JV?w5=XV9(8scs_)|$sCWDN
z^q#odg5}!^8Vh*RoEusE9hOVdBQ_-EjuO-T7I$9n^ja1;3n_eItI|K^<@BoaArMT}
zpl;w3E3GjsUDg-&6T1x}Ga(Wq>1-TbKil(BOcm2g&inr
z$0w^cRP^2k>TBaIv&p`h4o5i6Of5#j`bu1YP0PGFT-i32eSy6PCF=w_NCDPn{1+l!iIk
z%51b#2M9MXOd2eF3oj12Z;o80hW2cuchg#Ou(>!ACSG$ChJ>@prS=EQyV;~sFl!l9
zEa)Kir^2vq)RAd|EX7%}up8pQ%^G-*9HkMpU23L1*VIHT
z#P`(SHf=dDQf%})YHXtOx@F7I42zMcUBrvu8N!u7XYA4Q-pbD!pZ>)v|Lq}+6p1{~
z&t3p78h1Wda#V6UniP^|E~NG)i#61HHNDm~Z5EUHV*J~|!kX*NnO;>`a&S7~Ms
zE5S(r3wbB3Q5`PFanP6i=(bO-=5UDT!_I!Z;O)ruk6v?{D)`oyl9gV}H4FL_bSjrN
zs@ujtCl9cz8c~h(UZ>yHM
z$K_B4;S;fWrq6jp(FUyv2~`qa3CZEwE|hZXkps`0l+jC@M^r0gw|DsCOO5{3Gncc&)#S04({#2vexKJ@$|Ofl{MUwkaOX$
zt!OhNCH#!BCTe#VIsSmX{l3qtaFjyZUUu;J)YQ~a_nvFsy(glk_7N+}UWD0xA9mCj
zH!@hLba-v?uiPhutB?ELjw-pg)+yYZbyKY_U7(2AKxEdUXkaEetWRHGmjB2L4L+HT
zSzC$Q4XfO>&dse{30YY@Qa>&6cHO#Pp>i5$up*b?PQn=eClDFc6137ZNXy8Jg|!`f
zj@Q){5x5lmYo|NNL{@0Z=n=i2Z9jp!%+N?QZJqrXQX>?vzg?f4tlL-u-`huSZr)kWO$C8mB5G#F#vXcJfpB^F
znlPfwye9wA0!ZE#5Od6T19EWLW|rYBXDN2Qjh-qlX8HQLAI0lfDK%s=?zi(smGWs-
zlt{{J5yUO54E>{+Wd&{xG4osak3WPBp21>ORlhbgCi*ns-)y0&dY-y$aObG8s;RQD
zUBMFeL(2Z~s*8PbF~Gd3tYOKIBAZK87fDd;yp%&;syYKBiZuq=$V?0At)Ycy*TW?$
zYiny?_>E$&&`eeAP8IMn78|QKw%fn*HfX+n>NuTwY3#802b9(ypEBb5Tr<870?o@;
zTZ@@#X?d(tH`Jb(vzezHY++;h&oOHAI;P73hcZ}A&|J~Cgda^G{pEXSa8O~6=P&0l
z8GK#E{aSm@{`VLJc16n5hTUNszNh<$z{{p)#6}RUSyGghW!k=hU?q}XYGUT7XenjG
zHuh@`vhq5RmG^g$C^c}3y>dGLV(am!|Alx!sp_N!4v>*=maCz%l7^7UFEwI@c-{+h
z(0cMlmY@8gUrg)^7csg0@oDIB?s;)ZHkPqAmY-hsku~kG_x5Z1Sb8Q!n}g?VV1vD_
zF*IH19A_w4c11w~J(uy-Xv+%vNm%e?bUSQjtlxm>pcdx(+3jQ4m;gV286e2MmVIe&
zIR2GZ{HsOaq;9Y4*=P$6iki*Ufxa}6>Ep3RqC~~1Kwi5GH)&q;(|Aef{M%%aGR}nZB)bxUy!^)fhZy
zTb+00xBAuI@hRS)IEZQHdxrD!<3XE#LTCtCQqT)F5;?v2qjLF7GkyK0P+#+V(9;3z8_ZA5ch=T`wo^RB4Ts6%W
zKBj0{htJJrJQ?-SyRRui{#?i>%v;j&nNe({i=`zvg+0n8U~>#VbP0WEBu<5IH=vL)
zyx0%R?#QtF0P`egFEFI-`fl
zf$rh&klA{dTIuNMVkc^YE^X>LUQsgxZXoh4`{W*dET40+d`4{iru9oOjL(s`>RiVu
zkK*T^^Z|-{j+jFohOGd#lZdDwp`sM+!evl#isoEIJZuc~dV-$fH%hRHg_Ywtv6?DV
z(#bdJmO_hN(?OVPF9&LZ!7B_Z>diO%d7z~m!Lo?=J*0+m2eJnFg@p{L-kAm;ew(P0
zoRPKaC%wu!1d(qAf}uhh$G)EHDt?2aFVs~)vW5(=63~HOESTjQ2#!dn>(%YsFT>scAX7FCup9*V|g#y})T~OnKY+poDoaB|xWhJ>G
zDLSRHMajazI78;*>vPUG+zmq#SJflb+bfg3!$Joc3t+0bDP8L;MJnNjci3pgsv*{i{9&RbC!Tc{wXHblYjLN-}@5(W;xVA
zOV3q-IE1XIra59Sm}*Pq`DAy9^md>!C_zHNjUi|@Ihe1APccfmkS(8mXho&a2MBRJv*^(Tt3fz8%uO?!+iPH_wXo*ce_gF}Z}RkdL9=AfLlvNX=CnB~B%c4x-?JJ+oxYu9?z3u5r}boO^2qtjM=;+#
zxJ^n+^EKM|;F)=K5tF|NuwsJ&C+d~nXL{&g@oG*a}wg=Dj5<&;38YFgw@=HQfe&mZDaJ(9+r{fU(0y#+>mypP9
z@NGGBOb9CI{ZRceG-XZ~!l5h)7Na}dOZ;+cES9^g13H3N;zZaO0`tAiV9Z9y@4Z+i
zNpp@bgjH1NM7Q!H6NqaTuRYID0ECV4H@Sc^mwRbZkW2YANE-ba4&nU1&tk4u?)UVm!{8Fq@f
zVcbg8m`YgbsUK=c#~X~sEg|Calb`owcZ)H%5(!xu?
z>X*2yYroU&))_jb6L+Y0)RCt**rD?J*LW?7l*eBw3UyqN_VzxMlp=q6h<|#U8enU9
z@QwGkw@JvcaAy8KN~M!rU*rL^`dYIv=HC6YjsE8mSv(1YOhB%`;QZ@Lt&!BNC`F<5
z*MkrKKfn4$8*L{)Fx{YqakMrszpr&9kH{Uu>U+}!rtHoixdRJ+PtKn++vTWy<+}R=
zOdB4#yLgEKco*^Tu
zPPYJpHV7j_&`2TS=>(gKKu;k-r3)^787BvFy2Ev{pXmLDeLoy4ln}hPdQr;
zC%x_9Fau~#tbP>ruIt91aPr%`|8disH!umF&<=fMgrZrn6-x@ce!l+cTrNgHOCuUN
zSx%#T*w7$2F*de#;^U*|aTMr=Wf2!0Os@F79!J}Djb~zLXzLM~%L_F&3Ci_+murUw
zYC#$+h64JOp;L^dk2rj2KH#So)l+T-OSraFSLW1nmiuPyg(F*>xsW9@{kR9RwFrs*
z_V-y^Gw-^eNx3&nuK
zGIIsRHVyK@2Z_8|VAc2SnPC+2cRP?R)qJ3w-e*(Gt?j7jp*FKP`q2k-{I2T9`i(^V
zd%yk~x)Iww@eec0SznZ61EFl&u%Akc
zR76n;EuyT+mc3AlEK&A-&o*TrV~I!$wnEI`wSc$
z>igS!H8mFpA0D*R%+ifVdX^_`4#-CF=-$l~JP{EY75lk-tm-(UXCejS{Z{pn%DX9n
zryKvPoAgKPMgu?qn&2wR7SJ0)keCx3(ER+RdkK-CLhHJzMjM6QA5Gr*};qj+4iiPyIi3w|aW(S?1!&iMQEiFyxg;`mhXoF{e
zHdDNptD(^2ZmNuooQ60#Ip?%6#yc}G&D6UD?WNBU+1+7v4UMBOFy4YPxEI}Y!&KHF
z{e`|>cmp;k=No?+hHhKwNFAxYq@?IB+(Qu0wdm%D9V@;)he%V`=Ximdm{{#gm2csgjSy0{p=Ok^1EpPFLT
zba4AYn;v!nRaRCKCiqc7BP^X!hE&FF6LE+c+*?`inzEWT4JBN$-`|K(2*|yfq+ocp
zY0gb8o*g;yvO&R*%jYU1<8a-ak_VyVO%-ILw=N`GTyoS17db8g*41-h4IG>F|LiFd
zQJO4ysIINmp2F!)*nXLcCv?Y2-l@TgVKys2NLDS^Igsu_Ywn_KOHl|^Luk!Gd3JI_
z-^l@#Q=0vIEf6llE#7R3^Qqw{`bNnW;BY{XI7+5OmSTl;Z{ihm5U9af*J=2KWqL;W
z`ePDPnuj{szJ~a8m5^VV(yUOR9N4aV(r6;%;_Iy#kccHYhREJtMXMp1YH!e@3~N
z!JQo)*9Ukw!;L0jFn`gLBgGyD*@rbVgj5?>R|#htGml(dX=gxLSXQpIyy+z1`7u&(
zBfPq0B{sF$cBTarKoOJ_bMGR$x{*kPzDa6}PgdA7Nf&e^xi}$VMcrm^rl-_ZnR^wo
z>)t#05<0o#X7@x{1{afjAwIm@q`Jmf60w?iQHNVp!X=Y*ouvnOU8B%M1?n{>=zjAp
z7B~T2N1XDVd(K;a*M&JF;9x19$H(TVH#m(7uEx~w0UE*3ECDD86A@Q^rM!;r4{YO5YqYr=mD=XVZ5
zcu^%PP2YY$d-_mVu7r?%-%A7E<~7&B-igNVda#BW?zIkeo2hyoqG`aY;uTd#O!r1X
z*f$IB-TM&x>q6R&Fl975lyHp58_6+{Q{n7Ft7~xG^11Sj`ecY~z~#3w%qf5IRjH}8
z-C^*1Be8)gXiF|cc0)}6oTRXF{E(O2yUgP*)-=%~1hP%Vg6l>XrjB}LQS)OL?Ss)~
zcxcD;2776ORvKPi4y38>y9M`>TH3nZGWUtMC1s--9Y~v+K6KfPhxk8IjsIekS^(e3iakfl5Oi$9YY9&ln)ikz
zKb@Ey8d}vzl|K7*9bB6HdY@ZZxg10J)|hugv9Nb0qevwa+dwOY?K)pk^zuxiWYBl{
zP{<=Fz0BrqXW-KuxE0l&NP}nfH4+1=Ji9B$lXpv9n;w6WwpC0vKQUf>%T)k`0A{oVl|oVgXYwk_rj$a!3s-e~syaRfz
zUQ%S=mcDpLgR}Jq=BYALPNt>h8~z9C-HjS;gS$l~S)s1@q03|AJdDnX-#v;ud%AMQ
znloNLE19!3Rp#Kld;+-;#&1#e`EgO)iAfvW-ptH>QZt8PeB-kuVl(XGyMF1YV@^r0
zb$FwWemXvHQFL6Qd527Wq%Y^5Cn=3d8{Pg4Vu=}gIzBT~#<=q$yf^@|5PB~-?qf+^
zxp0btRr-&zQ(^6rE>jE@HHq)3x2TP(y<47xoMHntil*a$=7_`wfjKi)3{TiOjdIpY
z`B>le*1GrNJjcv#1UgiQdp^MJhV_lOmTg;S?Q_QyJ0yNqdjGG4`brt*#Al*L9j1#L
zjp2eFXiSf-G$rphDBFi!Sl_B-^*6*b=a|VKX!qYqhmG5+e%s<~VRkV}YGY~ydeK4s
zjeL|5HMS#%I#BCdP)r?!m1Zbmk?}fIeVfl3)V!VqzKZiv?iSUW8eo1Eb(zz%w8=-L
zdv{c}7`DBEH}`Y$mF=96R<&jT!L}X_bAt5_uwLnO4GVRC--9!~rhF!m_``=*=QLp_
z#`EZOn9D?i`tw4>biF|aQO?w*D2#^(kHin|-Ja_vJcp>l2YZO11(aFCg?E}8&2b*d
zygNpqW>x`ECl^;-LrWuqBq+oezu^#xIJDaKN-bE3`yPL>?8hd1lbh;|9CE211mOU*
z`8CtpE!tud@J?8booC53lQ!iFZaYI^r9m)SJ!%G?J2ou5QMN}{HJcwdP_r`bQNOoF
zq?g^ERC!`9@0!=*w{9{%>2txy3g+M3vgH+Ovsl^+=HhaBX|`|9IZkOMH-a;!6#eXa
z`f^I((XAHLyhEnma$^1LU{(OFc7O9GTglk0@g-8x-7aKIQBe3Zc87E{z9#R;Nu1ye
zG`G_-&F+asEv&&)lqqhZxJYYqYwL7iCpnmY{^Ww+o<4czl#PzQOQP~Rw%424X>>a3
z!gfCeG-{`QwZ`UTEM{a3m{zywT>YFAwQ)(o(`hvSG{WgrG)E=VI8F4jQx{byj|hHz
zvPAV<0Cl5qz}tIwSj1}|Yl6p#GFZv8eGp|{v4Ik0-|em~XOl`~SW6D-z^Vtg5IXhd
zAx?iUF#ntO|GxKDL=NL)i{y|kspA~NVugPGruNS75%j4r!q6>ESs1cM9Nr-7lJ;J&
z4)-LFH1A8(;c*fN2x?#Yt_8_a!d8P9dSDEBF-fUWn6?Z?tmlH8sL
zRnP%>!rq4JW{yV__oE)u<|~2n=g!?Y^Rs#NlVb3Qq_`Oz2A|?K?mQ|W_uETy?+Y(H
zIrW814t
z*iIo$gLVDs+pk+~5lkP-rX?7-g*po@X?w0eNp0}XSzFs2ESF}=)_V
zT%ifMrHoreh#&>1O7C3VXC}Wdg^o&R>-8_uH!JuYxZZc)ZR}##pF&nvlAd}Ku9Mfo
zl+D4ngp+0J84-e?ya74vrAvKpSB3Sxr#jsE@LK?>?gIUQs)V)afX{Qs_FYpAu!@t5
zo!ng(XcjVnexQPlLG7t>@I@=`p*A|;G@Ou@o)BDa9k{23lKvn4?mrKQQDM51{BqQ6
z%EYK<$Q0SK!VC%V)vym)O)HanOx^W4Qa&DvkGrx;avDAw)^Kvpq?g;f$#orFKY6l8
zMoOHe_jyA_#j>uh-r*>V^nUl;AS4E*_Y&ecmz13B=VIC|%F670Mg$r+1w@zlNdTuqOHPCPu1>alN!^
ztIsi!HX_ot-fQL2MsWF8ddc<5H8c5OX2@AXs#;jjMg_23`tcQgWNEvkW$BnTU*R{N
zgWu;Og6+*-V?#Nib*Z_|X)k0<(9um|TvgC(x$iMeSr`vfpVFy}Mv~KLLE4=L3$adWcEz19Uc
za4I39pB4QpoJ(c}QbK3xv?RR2Otp>w7=pf-X&}_8SvN6mD|%bt)3`8I*0lEwv);B{
z7gpYnx`7WY`wXvV4L;gzd(B%Mxj1)=txG^t5w6fQ&r25km@}GFi*qd(TX0Ih^J;P;
zA{n}G+2R%UT1NdHd8&U4>$B2!xRafWVj2lTn2{~3F+vv7oFx;WC|D1F{b%#ys^h?v
z`>Qe+hBkAaJQM1iwdm-144WAIU}XP7PX7u-nk=wEK>0}Lltsylv{1ZVE;wa>iWODy
z&KDCEbt6!@T#~!e6P;uPYUVL5N`8d(uA!7Qw7h^92;{}o+F*SMEVDJH`-t!pa-eew
zX+q-rOh~&>Ep#Zn%`nI--+%u6#bVuC<^`h#2oeOdI-HfdMCEWcM
zxc?9svz{F3ElcM`^F?d~kq=j5KOip;R7A<|J)Nd6UhwuW23Q}auyd;tJA)pH$1S74
z60FR3N)uHqjlYb@cFRd%Ug)^#T)9H+M?Vd;5qe}#-6RQT4JXCdBe2!ZFC5N%&morV
zGp(w*-Vf?0;e>ktp5_$yAM_Q^=-7aP}M(3X!r&%ew=|8}*7wR#D7_K0izw
zobv5*hBc2-+Ou1)k!H1P=4;}%EKNN@wVR!eFTCdNOIVXyBJ0hCaB)01)+eG{Zpt{^
zggX9umc=`}YVg2sOV7K`r8NMR|4qNT30o(^CaA<(!HWYZ7rq4wQDr5@+isoap;Nf2
zKWxFEDR^}}6o(w026nEympF1{#DWoP?5Tr2DlZ|ilvC`irl!`iH%8%-^#qKA3Ds(B
z1-GQvWu2V`10M-R5x~iehNKs`Wb9bSKTi7p=9~XP0jLr8UWq%xK8<$JdmOmd@_Sm%f4l8j&hhVZR+=3=Eb1zEw*fuHv;~x&Lb8lK(-IBuWnbk}{RmWhG-;imgC8T3CpjKoqZy
zF-kI`*JTcv9@StHVgYm=dbqf-M(GNvRIXon&}&)D1Y;__imVN(G*)7g#b
zK1rfT8Z6c0-@u7)raW3ct*9n6iDOU_eq?_lfGW1(j;yEwzb6inx8>7q3#Y_2E5Dyh
zR4%POQS8iUb*&o7FCtuj3vo4>B<*rN%W8c@IUWM3&)NX7t!?{C$Xi?u3OHe!7IMeh
zM$3*w?t5S}FH}_bsz;az_l;5cirw-Q(#sp!gJorDn(&?Xk;dWPmxhv*LU-8JHw(X?
z!y3-iHsw}fed4Bzq_SoYj9-Rx1yfYUTcz^`p{uU||ArewKq86YTS@oV_Dw^Yv#OsHTH%&GVLN^T2y
zwP=5To!dsZPzbCKu$33)mlo~afbDYL8M1CEVi+kbaBiJDD)+HZ9YQg>=bZK)IrVtp
z?NSf=O-8QB@gqkw7E7J~WEK67tl1pK^zFJ&a#R&?TiecXMnRAr{Lp0lS%(|O4wFP3
zo%1y^w_+%p_ZixXKQ?WA+nebS^jhh%;1xzgC|vba3a2h0R~K`(@Uk)UgTPZ|Al>4I
zC(PmOehbT#=kZ1_IxI-C&tbZ8dgu{iGb8qEY#!2{vqLj2vJNOMX1KfFxA))>58EA0
zgoTj-c8o_)ojG$CTv;O~d3>q4X`?Abw3$l)wvWUU^2%f6%H{pz=+*pJM$b}^$)!gp
z^m_Tp@dx{o_Y*g6@AoJiR7R7gbMElvV)KjL`&M4ka6Y_@_F)KrdHW`{&v9U)Jxq91
zzdaq~l7l9-`$(eAaB0G$DRY!TmmAmnIqgf`jyKG@uJ4{aRf!i<*#i%8u*IR!DAW*P
zbHImTXayZXec^TRSi;)NpHPEz8pBL#H0;*t$jO(UWDs|0u`}XTpRYJOdlLJXw2IX{pIbioe7DuN?JJ#t!^~;Gn
zA+5+dz0qZKMqu;w9@rs>sAi`bC#!HW{;6-_vOjG$L{47>lnysQInV6coQ(3@YDjJu
z9Z$<>p93MV0$r4
z#tmCrxH)sm45{0gF8gY@H4Jf7fGbM&)phdA$G|zsWNN(MZ;aY)BtA4c7;Sf1IqLjB
z8Fs%%roh!JT2Bs*Mb@nJNR!$?ol388#0K|u-`Niumld$UI+|!97!}a&KHwPKSGr|~
zmC;WYUR3hr6?|7$-cV06BMFa+@dbe#-MAVLBB_%^1xC7Qt`Z}z)mRYG*xxVp-d!>8
zn+_Cpi1)oxD8{Fa4mWe9q4g#t=J;2(Ot+c|Kn;nqf{*
zsr!>vz?W+LdP9q?qU}hZU$Rt+uv7Cg0;X1{t9HN@z!}~VvM~?(*<8C`vl6oS$!=`*
zRq1;9kLr8Dx}4x(grWC_wq=9t>b`G(8~L`+K@3WV5Bz}o_U-QE
zV$5x88dNXf_9vrGTfw#2kqXoH#>^XOYPE5%1$DYsYRFC(4$Q3*10n&i_8T4Ub1Fs>
zgmHrs(1>@nJx}*fns5eeD^3kI`y~aK3Rl}TU_Zra(RQ;*tmU(|OlR-URw{<|h*8Mx
z@rZh1+O~6|@}qxGmf7jLbwbDw&Ac86pYxG9HFH@)k~66x^Nh9e9rmxZ=jH&u?geV}
z{}KG9zXxSEB0B`w4dj?r>yH>b)xP#YGNyFTvabPaOIvK?s?#7{i8O+Ng9FyGyxvIZ
zR?C^{n)uZet!PU?W#9COfZIFNop+}9p_4OhZ6*12x0(TE3#C4tHt$F3Hde4BCYPGH
z1BCNavRQsP-Vn`n>9bC8xXo82UviF(b4;p~TQ}%TqlsM9A(F4)4Mlz(ha0CblcV~E
z&$fapTb&QM4l0(<#Wh@t8Qm>JRL(T^+)^Sb9IS9857pg(IJsY7q@Wti8YdQKIeYj@
zn}zrZwr+PR8%xp@WQY&yGiqc`X^W5rt>_dzIJYRJh4bI@d4nhP#>JT!V&072VqKLD
zxFcXj?Xzvns3xtH`#6FUR?uNi>}LRUnfxRGQcTmnR^_VjBX|K>Cwg1UP+#6Woel8b
zwM(0MBGW4=@1&IhWB)p^L+-${nYeXinPpbeJ(DY1$Fj4*-%FCdDShHQW7q0dxU5LJ
z#^#`%;k@hANa@3~(r5B+??KM$t-f$^@MP;te`Tk^h4{hubXT0k|NN(KMttXG5R!`x
z8`}sMn$&y`iMsD2tLd9;rmJ8I*$Sfmh{BwqTW7#&7;V1Mn>30SUicvT;N`BR_g|>R
z|96mBxp>$k;DGTU;dv1G33T`@m>lBfu3GEZ)mxqPjP1Oq$4KzUSqsmeLIcIBR*xQb
z!<;QcZ$&nT$!K^}y^}?qOz%*6v%Kb6fzKJe&V{-;vacr$jd~j-^-c&?z7td@qh&u0
zEmg(D+kp3tMTzQRrj8{US5Yzself2{KAuhUQ$iK(Jtu8HdpG3^=r2yn-XlRfQ8)VF
zw%D||yB8^EB63MR%<1B|N@#lW-Ib#bFy}0Vtfndv@|;r`V4iH$YR*ilVqEd4Ru$gf8>!3OAnx&A084k2jgg0~d{2v2Ua
zd4A0AO1~lVYE#Mq`f`gs6~}iiRbxyoz5VSYV5MGtSJ!nQDdN7riAxGQ{-cbjiF=(x?tMPM$ER>^
zPWu-1tQ8EzO=jJ=Qkd73878<{JaRola;H9AB9ljE;{k4OD@p8{&g1v=?Yqzso^pA@
zkJ^z1JwsDK_7Y-%WPmrnwq(5aNXwCL<90AMda{fAT=)D9)5yDQjL_o#@!0VG0<~E;
zTFT(KX~~cL=Jr-g5OUm#B(J9(_mb^?vxUgfG`15Pd5u^tJ2Slwm-87TXTxe!Qx^ix
zi0SR7HZUGO7J6(~ExaFp&$;aWz=e(LcRqJ#hN=|E^<{S#TVp=J8CP+2aTHG`RdjO^
zceJKPUoC)MA8mi(^Jat7Gyf}jRlP9OS}dRm`zZdlDdr1e534{4@yV{&Ef$(oaW3;|
zeaH1<^~)?pYK&Uhxzh>9
zYYewJ7Ir*ET4%^aOG`d$=Cn2{uXoRplo$smOuxqAwVTxGQQ3$%dBmNqLir#5?Hy+#
zbarJsZIZs6HQLOLv&uZy7Aq&u!y`w#!{Y)ELnPFKBdag73?-Il)#Z0ZCBeNyng3CZ
z%roT~zB6TTxiY4Hw;?7gSt?%|d<2w=a%zmNUn*i3Y%Y1uix@0O<`hn{Ik9r`@P_|q
z@ddDXyo0at2cg)KQDBIHu&&UAm+&Dtz28BL6)&Utq*HvVbmD0x*i!^y%5RZV?j$ZW
z-nw><=NtA+JrV&Oh1Ia8s7T+-QK_w<)W*81!*W=aBB?zUF%~Z+#_?On%Oia98(}D
zDbDMqUQjQF4$q)l!dhx7<%=X&#m2r2KXyLLC)p^PK)vd3p^(ATry%BM;W(n
zY=TP`0Jf2^FO0mLkhiWE%BL{c&!f3@6QbU!Ol2a5iilj0A$KR(Ta`3t*#JxMTu&`%
zuCxRcRBq+>rDU=bt_;->`Z=Kqxl;c!I;APqoUU
zhjkWb+WLIKHz&G;KX>mgLh!oY*Dqi3;a13Uhg2qgS`w(dFVW#T4ZMQ%yPiebvL?FTTE?4X14R@Oo3}(#5P#lV@}PwXl90Q
z;H2l@VIXSQy)DJ6$=jeZEgzpu-L#`8J>owf)oi8KJKgwEU$CmAou)lf6Y2|je-EOf
z(w~v)omOqIxB{aZTsWPPFOqNc1%me`Ag4}kQfhTsbk0jR03OT26klK5D(V`e1BPO0
zv9eE_B$v<{H#XGnD*!5u$xQe~4p#^MuBG|)>x9Km87VFj&n_e(_iWuZK%L>uQF=(l
zsH-L{&kC~j2C-LCN=9xlN`zoFD(;MA`^?j4znpsvHZ43j`Pdl4q;Ws9KKj(tB1F;h
zN8Zo7U;TM(bx}1YyyJBVDPtaaA)+SYM2l47N&eKY;sz!g&*Ek84VF0UD6BP;6o;J!5IFL*n2|%D7ItI=258u+nwt2=kS%hUOK!J
z*{aJG>|Jrjns@Lj4%w31l^$`>uTs8j@HWjEeUab){9ZKO{Hsaicyyk9KDl(nmCK0j{qfuk3Axw^g0ETk4SCz7=7pXu{4F6`{RdnaSGupovHs&;j2_+lbia`DF7lH0d#>c>3Pa=qUVvz#$(rk3Q7fze^*^&40@cqx
zO166$omLquUJ{3aTbQgH6~$Ip4-Quojj{!cgyi-MB8_C(PR)rG7`?UdKySE>EVo=9
z=@IG4HQSLs#cvmve&p?rGM{Pbjn;5>m1BSV66U36A4#xInPxq&P+*Pgl`TavWvOXf
z^8SY%;}rR=0Dci;o$>A0WBe0#{%a2PO@jyEjD)D0k0f9KlKV`sa~IBvTeNfxrFdbw-JFdrBID>fTC3id!J<|IK|FJq-}#pnEq*>U2rE
zMn-DaAA+QePX6qWlqt|Z3O20_*!6Gumv8Xf;fBC(X>6Hz_j5=G$jx(^4aLds4
z2F1mF&lZt!tnsSZfG1>y(NEHE#8tvEmV!SvyU1aF>>)u0m|BvFl9E#S*Dx1oBG2EX
z9)EpuKbPa)b2@Selk=;J!l26YiQJr3P-tBhxH@|!n^G0B`UhMXa$OLoHnV3=neSgVmA>ZB&zy;HZ>&dh`Pclq-IFXQnq_vD
z1x|$)|07fU>!UBb8rUSPjFN)dmTqdiLp06ITmdF~{#0?B+c7=L9crQERuZ-TwMDCS
zD^N~A8C6$5jjd~%fPJ3S>ipvqZbrT4oF1g)4q#2>w0SosxslYhf+1h17b2HSI`8JP}vxCl03wXv)JH6Zw?cE#pe
zRWonf-D_h+#Q(3aBf$e)Y4JkvhfuwfrHdENvHs%oUMs_{y~RHH>%sWvLjLEcfyLL#
zG=mq5^z^3BJG+^c6qUG~SL*&L%KE8Q@Hx!SPj0Hs$wSZR7ucw@Jv&yBf1O$7SH#fBT|*GfFL9>jGe*1Q}qEYyvkya2Ly%4;s^jR0nzHDs7N
zV|WdH>1$Sg4=wxZ_tN@rh0G%<-fMCOoKfPCGBr%@i=GL4)S<1@-NyG1Ej(xWI$lzL
zsYtWF<8g%<@Xwg|^9_{F%zD9dlZjWUc{;VPL{VWjDKWI9Dprr;vAS|g6s$T=Eq(5a
zEKKg>;IKVvi{A7)p48}YHhiTx$3xr@7Trk3lmPL6PT0!w;v3}_?g`RForIOjwoDVN
z$B65b;b%AM&r@q8!1q2NzForVh&PxP4eg63<08WY{ajKLgo*Aw)O?(u-24Ed`MqH^SjQoOVCVw
z#ELG0zf)yj$oCA;iXUMcu|aV?Hn@2z)FVHDc`>@8Od+xU&c0fOP(Wkr@e|RFo;^((
zPf&}}B1|xr)S&j@uwL;O8y-uB;N3@vv?K{s0H3r)V7Xg
za4{FWRQM3)b2~w#e1qjC4qAEP4v+4c0oRo=5fOPBk1P@|eUI|&pGS4|HLYrTKqqT2eic10R0elR$!k
z9jD`4@qFQBPrhW}nGOXjsq?(X@!uD@1^WbZqv)R{8R=Ev{2GPVeOMNCM?dviXq!Cd
zEdL_he7K3aKqp<}^5hAVH859~4We0A@MX<=2Pik@ws>B4xz^q=i&rq0X0+;|cNg&g
zz|6&Bg_z?;7jr8#(_cOs{`aGVd^m79#9qg}jVZ-*Vtm$ypW9fQXT7#Xap_0ULIM7y
zag%$xocArdeE&s3VaMi0>wvC;)nCm3^IWD!rP-@gO-8GwhLPqAqL>H^>K#n{jOqYv
z{e{$~T(Ms6yS^{qN0J)#+X
zOBZ%#GI{2np>}bn!Gta#Y4JyisW9zHkqK{)M`+%Fv4MDt!ouDD!?0CUFb``e8o2DHh?*_)h7vDnjm
zrE5_X3ACfflI3^EJ!je_yX$$w)n_vzC?Gba>Y_aau4BJT^DI$s(8Hz#7|ixX?J@a%
z{YI3#IKKLFz(tlqDa9S|Y&yBwI1-vAZ(d=
zga>Vn^m^*uIkaUy49CiKj|jDt8M?0fR_}dys+Z#H(Nk^Rm7qT<(hYCF8{3nWRBd=?
z_=bTE%6w$=5%`%}L_tAK*!LoL-d7sm3J&_25SL9gZs?j}ruR}-3s9ktO23{;ulWI(
z2RJ{M;#1py3Txbv-t+NKCsC;G>y$lNK)i9Ij;}QHxI9=Ii^btqx31M{BB!PtI&)B`
zIhQfF0~-AW^&lTeJ^5SpeNiLN$lhWS_I+FMgGfVz(};;G4$uR8C;R@UuI`?ZojYx94h)K8d#sv6I$Y|Zpj?;_qmx3;=7J1
z5Ft06GZcw5>ho9YH}AB#-t)r>7s#b1(cS6)dtUg>pSuhJjJ9;03`VeIITs2!#I0Bw
zvGLaDjfKDO+4l|_u=~$1j>-el1qrsQ{Y7NdR{s&{j~Sx%qSrRb92Xt_l2E*3Nk~X>
zh3!ugCx?gKech@AS~iFCV+frJKAqy&ut%z!TauW%(q`Jj_cjwtL%C>#{O*-U2LUv*
zgLzgqww}J^^tFI}Gg@CTOauCSA#X2W2XwHUCJVmwd@G$s02yl{TI}Uuhye0XdabCP
z#zQKDpznHT>EuWuD%0eEP*m%7HnfXsP
z?QKZG@)xPLQLhGq9INJ#tH*yzMV>kfr%KIeq}^pM)~mc?aWJIdn;PTs1%_%`9}h`!
z&epY6_oZRGJ)pH!&+aCMeGM(@)iVRXNUemUFs5G8LL=il@fvk=oo^+3(-0+EZ-IUw
zYG8~|&*)j#5-2Z&VmzmcrL8SMU1&S+?J-ePkTws`Di!<=gU`oVC|AH)XBR+Jrm#P~
zYHz{-qfO!l>d8RIq~}Ka;%B)l%!r|}u^InO0{-bmfj^3pk7~bNm7e}|HcOP#f>x*0
zlsj~*AwlhEP*vKd6>SmC@=pBsg#*)Vw&`nr4?SG<9{VP;F@2RmXs?8X@s=rNtUB@M
z!D1f3RO?4gqr!>uLSqKtfvHAt4}e6~!nWJfrRWvvu=^Zt&^W`1569j8>x`c3=DTiw
zd{MGM-kH;scYE^&@W7kLhL*TD&%E%M(uy*cjtN$CTR<+8C!q
zOOdV6i%{$ZHYW$T1U9Q%;nIlM{JNCr~(tjFXtZE?g~U
zV1}30(T;y>KJ-B4_XFfOvzEU2FaU3p>P7k$#1WC!3Z
zN&EB%DpGAt66q1(#1}$L**c2}(#ZzXh6W2sFI;LJ
z#NsvT&Al@uGwa=BBu1m7YAwdm~j2Kfnt
z{5TT`1aie)Qxj1ODm8Y4x?t8Hqk#!q9J!@v&43O6Ds_g(9CInEo-^IUn@;W;ILU)@
z@K-KQ&Mr(!r9X+hpR!ehWTosDvIW&;R4YBL;FR;3b-8Ks&=0wunv&w_=QnwO%8k|3
zccx2AL&~tujrepramDL$wV0oT8Kjw`Oe(KXB-U&55t-CbpSe?vLz@&z%A*>PQGiaO
z7zs6;h%J=t?Kvn8N~ah?Lw5g&fT@7xUH$b%5Hd9C1S`weSoK@yq-~w|L9rg$6@RP;
z-66Si=atvAW?J<0FU+(FA5U&8l}Nvr{I^`#iT@B70r*his%9_~DeZ7Ld_W?E7rEDV
z8hdpg#ASDMFj*25e=ZYX&rFtEEg&#PPHFQzEU9yDDqM2XD~5*Q?=6j03s}{A)?=8FAn=0ioT#8&Vp+Lk#$qgX00)y0Nznt1f3jsf!ft8Ud
z-QiNppsIP?Vx+%*W-+o|apF5Gf5E5kzY@TR6W?KhcUoiw)Qo*~>1i^(@vMji==v`i
z`R{e=>h;^{yx!e~cZC!?jXcS{k0r(BIK1Z^AbNpilk1yQza128XLKKTuq`RoYAyA|
z1yh$Cv+_M`PU@O_pN3K0X7^DqYM-2>ygcWs&)Ql!oCx93$6Zj-cV!i0+aAgtTbtOh
zmG{_q*Wj~i``P6?-6%_EXx7%YqW=l^kSD@ChCNx{{FwklQ_~WL>*J%g0Y(@Y
zHFK{XF#{$2p_PC8`oQ!Df*-WlpBZ94egY;=Rgax){o70>&%=R)H^*I*u4XUf-`@H3QfV<1RcS6*6?Vyd$8`z@TsbaR(iQ%P)QxTOI`?1u-lKJN^X+336LxM$TREkJ&Qkw5K<=@mkuGiF)^$cE
zyQTa38bJnBr{K4xE=FAAAi2oL)!#quQ_q-yJ8=4FPupQ&V1PY)>2IC=e47-~-kul4uUFbI(99|6G*f(h
z7ZS9Qnc84);VC3(9AFe7SG$l37{@Giq}g<4mp1QA`2p#H#!TOTF=syBZ|D6MdIePW
zcn%EHC