From 48d623057ef00ab86048d95ec174afec4ca8f585 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Fri, 20 Jun 2025 17:29:55 -0400
Subject: [PATCH] docs: refresh quickstart (#8582)
* content
* Apply suggestions from code review
Add suggestions from first half
Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>
* icon-and-image
* more-cleanup
* replace-urls
* Apply suggestions from code review
Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>
* Update quickstart guide to clarify script execution for curl snippet
* clarify-tweaks
* indentation
* Apply suggestions from code review
Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>
* fix-broken-links
* code-review
---------
Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>
---
docs/docs/Components/components-prompts.md | 4 +-
.../Get-Started/get-started-quickstart.md | 610 ++++++++++++++----
.../img/quickstart-simple-agent-flow.png | Bin 0 -> 1203775 bytes
.../quickstart-simple-agent-playground.png | Bin 0 -> 149974 bytes
docs/static/img/starter-flow-simple-agent.png | Bin 335719 -> 904562 bytes
5 files changed, 472 insertions(+), 142 deletions(-)
create mode 100644 docs/static/img/quickstart-simple-agent-flow.png
create mode 100644 docs/static/img/quickstart-simple-agent-playground.png
diff --git a/docs/docs/Components/components-prompts.md b/docs/docs/Components/components-prompts.md
index 112a96151..26e018ea7 100644
--- a/docs/docs/Components/components-prompts.md
+++ b/docs/docs/Components/components-prompts.md
@@ -13,9 +13,9 @@ Prompts are a combination of natural language and variables created with curly b
## Use a prompt component in a flow
-An example of modifying a prompt can be found in the [Quickstart](/get-started-quickstart#run-the-chatbot-with-retrieved-context), where a basic chatbot flow is extended to include a full vector RAG pipeline.
+An example of modifying a prompt can be found in [Vector RAG starter flow](/vector-store-rag), where a basic chatbot flow is extended to include a full vector RAG pipeline.
-
+
The default prompt in the **Prompt** component is `Answer the user as if you were a GenAI expert, enthusiastic about helping them get started building something fresh.`
diff --git a/docs/docs/Get-Started/get-started-quickstart.md b/docs/docs/Get-Started/get-started-quickstart.md
index db1dfecf2..dd0b134ff 100644
--- a/docs/docs/Get-Started/get-started-quickstart.md
+++ b/docs/docs/Get-Started/get-started-quickstart.md
@@ -4,188 +4,518 @@ slug: /get-started-quickstart
---
import Icon from "@site/src/components/icon";
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
-Get to know Langflow by building an OpenAI-powered chatbot application. After you've constructed a chatbot, add Retrieval Augmented Generation (RAG) to chat with your own data.
+Get started with Langflow by loading a template flow, running it, and then serving it at the `/run` API endpoint.
## Prerequisites
- [A running Langflow instance](/get-started-installation)
-- [An OpenAI API key](https://platform.openai.com/)
-- [An Astra DB vector database](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html) with:
- - An Astra DB application token scoped to read and write to the database
- - A collection created in [Astra](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection) or a new collection created in the **Astra DB** component
+- [An OpenAI API key](https://platform.openai.com/api-keys)
-## Build the basic prompting flow
+## Run the Simple Agent template flow
-:::tip
-If you prefer a pre-built flow, click **New Flow**, and then select **Basic Prompting**.
+1. In Langflow, click **New Flow**, and then select the **Simple Agent** template.
-Continue to [Run the basic prompting flow](#run-basic-prompting-flow).
-:::
+
-1. From the Langflow dashboard, click **New Flow**, and then select **Blank Flow**. A blank workspace opens where you can build your flow.
+The Simple Agent flow consists of an [Agent component](/components-agents) connected to [Chat I/O components](/components-io), a [Calculator component](/components-tools#calculator-tool), and a [URL component](/components-data#url). When you run this flow, you submit a query to the agent through the Chat Input component, the agent uses the Calculator and URL tools to generate a response, and then returns the response through the Chat Output component.
-The Basic Prompting flow will look like this when it's completed:
+Many components can be tools for agents, including [Model Context Protocol (MCP) servers](/mcp-server). The agent decides which tools to call based on the context of a given query.
-
+2. In the **Agent** component's settings, in the **OpenAI API Key** field, enter your OpenAI API key.
+This guide uses an OpenAI model for demonstration purposes. If you want to use a different provider, change the **Model Provider** field, and then provide credentials for your selected provider.
-To build the **Basic Prompting** flow, follow these steps:
+ Optionally, you can click **Globe** to store the key in a Langflow [global variable](/configuration-global-variables).
-2. In the components sidebar, click **Inputs**, select the **Chat Input** component, and then drag it to the canvas.
-The [Chat Input](/components-io#chat-input) component accepts user input to the chat.
-3. In the components sidebar, click **Prompt**, select the **Prompt** component, and then drag it to the canvas.
-The [Prompt](/components-prompts) component combines the user input with a user-defined prompt.
-4. In the components sidebar, click **Outputs**, select the **Chat Output** component, and then drag it to the canvas.
-The [Chat Output](/components-io#chat-output) component prints the flow's output to the chat.
-5. In the components sidebar, click **Models**, select the **OpenAI** component, and then drag it to the canvas.
-The [OpenAI](components-models#openai) model component sends the user input and prompt to the OpenAI API and receives a response.
+3. To run the flow, click **Playground**.
-You should now have a flow that looks like this:
+4. To test the Calculator tool, ask the agent a simple math question, such as `I want to add 4 and 4.`
+To help you test and evaluate your flows, the Playground shows the agent's reasoning process as it analyzes the prompt, selects a tool, and then uses the tool to generate a response.
+In this case, a math question causes the agent to select the Calculator tool and use an action like `evaluate_expression`.
-
+
-With no connections between them, the components won't interact with each other.
-You want data to flow from **Chat Input** to **Chat Output** through the connections between the components.
-Each component accepts inputs on its left side, and sends outputs on its right side.
-Hover over the connection ports to see the data types that the component accepts.
-For more on component inputs and outputs, see [Components overview](/concepts-components).
+5. To test the URL tool, ask the agent about current events.
+For this request, the agent selects the URL tool's `fetch_content` action, and then returns a summary of current news headlines.
-6. To connect the **Chat Input** component to the OpenAI model component, click and drag a line from the blue **Message** port to the OpenAI model component's **Input** port.
-7. To connect the **Prompt** component to the OpenAI model component, click and drag a line from the blue **Prompt Message** port to the OpenAI model component's **System Message** port.
-8. To connect the **OpenAI** model component to the **Chat Output**, click and drag a line from the blue **Text** port to the **Chat Output** component's **Text** port.
+6. When you are done testing the flow, click **Close**.
-Your finished basic prompting flow should look like this:
+Now that you've run your first flow, try these next steps:
-
+- Edit your **Simple Agent** flow by attaching different tools or adding more components to the flow.
+- Build your own flows from scratch or by modifying other template flows.
+- Integrate flows into your applications, as explained in [Run your flows from external applications](#run-your-flows-from-external-applications).
-### Run the Basic Prompting flow {#run-basic-prompting-flow}
+Optionally, stop here if you just want to create more flows within Langflow.
-Add your OpenAI API key to the OpenAI model component, and add a prompt to the Prompt component to instruct the model how to respond.
+If you want to learn how Langflow integrates into external applications, read on.
-1. Add your credentials to the OpenAI component. The fastest way to complete these fields is with Langflow’s [Global Variables](/configuration-global-variables).
+## Run your flows from external applications
- 1. In the OpenAI component’s OpenAI API Key field, click the **Globe** button, and then click **Add New Variable**.
- Alternatively, click your user icon in the top right corner, and then click **Settings**, **Global Variables**, and then **Add New**.
- 2. Name your variable. Paste your OpenAI API key (sk-…) in the Value field.
- 3. In the **Apply To Fields** field, select the OpenAI API Key field to apply this variable to all OpenAI Embeddings components.
+Langflow is an IDE, but it's also a runtime you can call through an API with Python, JavaScript, or HTTP.
-2. To add a prompt to the **Prompt** component, click the **Template** field, and then enter your prompt.
-The prompt guides the bot's responses to input.
-If you're unsure, use `Answer the user as if you were a GenAI expert, enthusiastic about helping them get started building something fresh.`
-3. Click **Playground** to start a chat session.
-4. Enter a query, and then make sure the bot responds according to the prompt you set in the **Prompt** component.
+When you start Langflow locally, you can send requests to the local Langflow server.
+For production applications, you need to deploy a stable Langflow instance to handle API calls.
+For more information, see [Langflow deployment overview](/deployment-overview).
-You have successfully created a chatbot application using OpenAI in the Langflow Workspace.
+For example, you can use `POST /run` to run a flow and get the result.
-## Add vector RAG to your application
+Langflow provides code snippets to help you get started with the Langflow API.
-You created a chatbot application with Langflow, but let's try an experiment.
+1. To open the **API access pane**, in the **Playground**, click **Share**, and then click **API access**.
-1. Ask the bot: `Who won the Oscar in 2024 for best movie?`
-2. The bot's response is similar to this:
+ The default code in the API access pane constructs a request with the Langflow server `url`, `headers`, and a `payload` of request data.
+ The code snippets automatically include the `LANGFLOW_SERVER_ADDRESS` and `FLOW_ID` values for the flow.
+ Replace these values if you're using the code for a different server or flow.
+ The default Langflow server address is `http://localhost:7860`
-```text
-I'm sorry, but I don't have information on events or awards that occurred after
-October 2023, including the Oscars in 2024.
-You may want to check the latest news or the official Oscars website
-for the most current information.
+
+
+
+ ```python
+ import requests
+
+ url = "http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID" # The complete API endpoint URL for this flow
+
+ # Request payload configuration
+ payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!"
+ }
+
+ # Request headers
+ headers = {
+ "Content-Type": "application/json"
+ }
+
+ try:
+ # Send API request
+ response = requests.request("POST", url, json=payload, headers=headers)
+ response.raise_for_status() # Raise exception for bad status codes
+
+ # Print response
+ print(response.text)
+
+ except requests.exceptions.RequestException as e:
+ print(f"Error making API request: {e}")
+ except ValueError as e:
+ print(f"Error parsing response: {e}")
+ ```
+
+
+
+
+ ```js
+ const payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!",
+ "session_id": "user_1"
+ };
+
+ const options = {
+ method: 'POST',
+ headers: {
+ 'Content-Type': 'application/json'
+ },
+ body: JSON.stringify(payload)
+ };
+
+ fetch('http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID', options)
+ .then(response => response.json())
+ .then(response => console.log(response))
+ .catch(err => console.error(err));
+ ```
+
+
+
+
+
+ ```text
+ curl --request POST \
+ --url 'http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID?stream=false' \
+ --header 'Content-Type: application/json' \
+ --data '{
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!"
+ }'
+
+ # A 200 response confirms the call succeeded.
+ ```
+
+
+
+
+
+2. Copy the snippet, paste it in a script file, and then run the script to send the request.
+If you are using the curl snippet, you can run the command directly in your terminal.
+
+If the request is successful, the response includes many details about the flow run, including the session ID, inputs, outputs, components, durations, and more.
+The following is an example of a response from running the **Simple Agent** template flow:
+
+
+Response
+
+```json
+{
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "outputs": [
+ {
+ "inputs": {
+ "input_value": "hello world!"
+ },
+ "outputs": [
+ {
+ "results": {
+ "message": {
+ "text_key": "text",
+ "data": {
+ "timestamp": "2025-06-16 19:58:23 UTC",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "text": "Hello world! 🌍 How can I assist you today?",
+ "files": [],
+ "error": false,
+ "edit": false,
+ "properties": {
+ "text_color": "",
+ "background_color": "",
+ "edited": false,
+ "source": {
+ "id": "Agent-ZOknz",
+ "display_name": "Agent",
+ "source": "gpt-4o-mini"
+ },
+ "icon": "bot",
+ "allow_markdown": false,
+ "positive_feedback": null,
+ "state": "complete",
+ "targets": []
+ },
+ "category": "message",
+ "content_blocks": [
+ {
+ "title": "Agent Steps",
+ "contents": [
+ {
+ "type": "text",
+ "duration": 2,
+ "header": {
+ "title": "Input",
+ "icon": "MessageSquare"
+ },
+ "text": "**Input**: hello world!"
+ },
+ {
+ "type": "text",
+ "duration": 226,
+ "header": {
+ "title": "Output",
+ "icon": "MessageSquare"
+ },
+ "text": "Hello world! 🌍 How can I assist you today?"
+ }
+ ],
+ "allow_markdown": true,
+ "media_url": null
+ }
+ ],
+ "id": "f3d85d9a-261c-4325-b004-95a1bf5de7ca",
+ "flow_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "duration": null
+ },
+ "default_value": "",
+ "text": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "files": [],
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "timestamp": "2025-06-16T19:58:23+00:00",
+ "flow_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "error": false,
+ "edit": false,
+ "properties": {
+ "text_color": "",
+ "background_color": "",
+ "edited": false,
+ "source": {
+ "id": "Agent-ZOknz",
+ "display_name": "Agent",
+ "source": "gpt-4o-mini"
+ },
+ "icon": "bot",
+ "allow_markdown": false,
+ "positive_feedback": null,
+ "state": "complete",
+ "targets": []
+ },
+ "category": "message",
+ "content_blocks": [
+ {
+ "title": "Agent Steps",
+ "contents": [
+ {
+ "type": "text",
+ "duration": 2,
+ "header": {
+ "title": "Input",
+ "icon": "MessageSquare"
+ },
+ "text": "**Input**: hello world!"
+ },
+ {
+ "type": "text",
+ "duration": 226,
+ "header": {
+ "title": "Output",
+ "icon": "MessageSquare"
+ },
+ "text": "Hello world! 🌍 How can I assist you today?"
+ }
+ ],
+ "allow_markdown": true,
+ "media_url": null
+ }
+ ],
+ "duration": null
+ }
+ },
+ "artifacts": {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "files": [],
+ "type": "object"
+ },
+ "outputs": {
+ "message": {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "type": "text"
+ }
+ },
+ "logs": {
+ "message": []
+ },
+ "messages": [
+ {
+ "message": "Hello world! 🌍 How can I assist you today?",
+ "sender": "Machine",
+ "sender_name": "AI",
+ "session_id": "29deb764-af3f-4d7d-94a0-47491ed241d6",
+ "stream_url": null,
+ "component_id": "ChatOutput-aF5lw",
+ "files": [],
+ "type": "text"
+ }
+ ],
+ "timedelta": null,
+ "duration": null,
+ "component_display_name": "Chat Output",
+ "component_id": "ChatOutput-aF5lw",
+ "used_frozen_result": false
+ }
+ ]
+ }
+ ]
+}
```
-Well, that's unfortunate, but you can load more up-to-date data with **Retrieval Augmented Generation**, or **RAG**.
+
-Vector RAG allows you to load your own data and chat with it, unlocking a wider range of possibilities for your chatbot application.
+In a production application, you probably want to select parts of this response to return to the user, store in logs, and so on. The next steps demonstrate how you can extract data from a Langflow API response to use in your application.
-## Add vector RAG with the Astra DB component
+### Extract data from the response
-Build on the basic prompting flow and add vector RAG to your chatbot application with the **Astra DB Vector Store** component.
+The following example builds on the API pane's example code to create a question-and-answer chat in your terminal that stores the Agent's previous answer.
-Add document ingestion to your basic prompting flow, with the **Astra DB** component as the vector store.
+1. Incorporate your **Simple Agent** flow's `/run` snippet into the following script.
+This script runs a question-and-answer chat in your terminal and stores the Agent's previous answer so you can compare them.
-:::tip
-If you don't want to create a blank flow, click **New Flow**, and then select **Vector RAG** for a pre-built flow.
-:::
-Adding vector RAG to the basic prompting flow will look like this when completed:
+
+
+
+ ```python
+ import requests
+ import json
+
+ url = "http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID"
+
+ def ask_agent(question):
+ payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": question,
+ }
+
+ headers = {"Content-Type": "application/json"}
+
+ try:
+ response = requests.post(url, json=payload, headers=headers)
+ response.raise_for_status()
+
+ # Get the response message
+ data = response.json()
+ message = data["outputs"][0]["outputs"][0]["outputs"]["message"]["message"]
+ return message
+
+ except Exception as e:
+ return f"Error: {str(e)}"
+
+ def extract_message(data):
+ try:
+ return data["outputs"][0]["outputs"][0]["outputs"]["message"]["message"]
+ except (KeyError, IndexError):
+ return None
+
+ # Store the previous answer from ask_agent response
+ previous_answer = None
+
+ # the terminal chat
+ while True:
+ # Get user input
+ print("\nAsk the agent anything, such as 'What is 15 * 7?' or 'What is the capital of France?')")
+ print("Type 'quit' to exit or 'compare' to see the previous answer")
+ user_question = input("Your question: ")
+
+ if user_question.lower() == 'quit':
+ break
+ elif user_question.lower() == 'compare':
+ if previous_answer:
+ print(f"\nPrevious answer was: {previous_answer}")
+ else:
+ print("\nNo previous answer to compare with!")
+ continue
+
+ # Get and display the answer
+ result = ask_agent(user_question)
+ print(f"\nAgent's answer: {result}")
+ # Store the answer for comparison
+ previous_answer = result
+ ```
+
+
+
+
+ ```js
+ const readline = require('readline');
+
+ const rl = readline.createInterface({
+ input: process.stdin,
+ output: process.stdout
+ });
+
+ const url = 'http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID';
+
+ // Store the previous answer from askAgent response
+ let previousAnswer = null;
+
+ // the agent flow, with question as input_value
+ async function askAgent(question) {
+ const payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": question
+ };
+
+ const options = {
+ method: 'POST',
+ headers: {
+ 'Content-Type': 'application/json'
+ },
+ body: JSON.stringify(payload)
+ };
+
+ try {
+ const response = await fetch(url, options);
+ const data = await response.json();
+
+ // Extract the message from the nested response
+ const message = data.outputs[0].outputs[0].outputs.message.message;
+ return message;
+ } catch (error) {
+ return `Error: ${error.message}`;
+ }
+ }
+
+ // the terminal chat
+ async function startChat() {
+ console.log("\nAsk the agent anything, such as 'What is 15 * 7?' or 'What is the capital of France?'");
+ console.log("Type 'quit' to exit or 'compare' to see the previous answer");
+
+ const askQuestion = () => {
+ rl.question('\nYour question: ', async (userQuestion) => {
+ if (userQuestion.toLowerCase() === 'quit') {
+ rl.close();
+ return;
+ }
+
+ if (userQuestion.toLowerCase() === 'compare') {
+ if (previousAnswer) {
+ console.log(`\nPrevious answer was: ${previousAnswer}`);
+ } else {
+ console.log("\nNo previous answer to compare with!");
+ }
+ askQuestion();
+ return;
+ }
+
+ const result = await askAgent(userQuestion);
+ console.log(`\nAgent's answer: ${result}`);
+ previousAnswer = result;
+ askQuestion();
+ });
+ };
+
+ askQuestion();
+ }
+
+ startChat();
+ ```
+
+
+
-
+2. To view the Agent's previous answer, type `compare`. To close the terminal chat, type `exit`.
-To build the flow, follow these steps:
+### Use tweaks to apply temporary overrides to a flow run
-1. Disconnect the **Chat Input** component from the **OpenAI** component by double-clicking on the connecting line.
-2. Click **Vector Stores**, select the **Astra DB** component, and then drag it to the canvas.
-The [Astra DB vector store](/components-vector-stores#astra-db-vector-store) component connects to your **Astra DB** database.
-3. Click **Data**, select the **File** component, and then drag it to the canvas.
-The [File](/components-data#file) component loads files from your local machine.
-4. Click **Processing**, select the **Split Text** component, and then drag it to the canvas.
-The [Split Text](/components-processing#split-text) component splits the loaded text into smaller chunks.
-5. Click **Processing**, select the **Parser** component, and then drag it to the canvas.
-The [Parser](/components-processing#parser) component converts the data from the **Astra DB** component into plain text.
-6. Click **Embeddings**, select the **OpenAI Embeddings** component, and then drag it to the canvas.
-The [OpenAI Embeddings](/components-embedding-models#openai-embeddings) component generates embeddings for the user's input, which are compared to the vector data in the database.
-7. Modify the **Prompt** component to contain variables for both `{user_question}` and `{context}`.
-The `{context}` variable gives the bot additional context for answering `{user_question}` beyond what the LLM was trained on.
+You can include tweaks with your requests to temporarily modify flow parameters.
+Tweaks are added to the API request, and temporarily change component parameters within your flow.
+Tweaks override the flow's components' settings for a single run only.
+They don't modify the underlying flow configuration or persist between runs.
-```text
-Given the context
-{context}
-Answer the question
-{user_question}
+Tweaks are added to the `/run` endpoint's `payload`.
+To assist with formatting, you can define tweaks in Langflow's **Input Schema** pane before copying the code snippet.
+
+1. To open the **Input Schema** pane, from the **API access** pane, click **Input Schema**.
+2. In the **Input Schema** pane, select the parameter you want to modify in your next request.
+Enabling parameters in the **Input Schema** pane does not **allow** modifications to the listed parameters. It only adds them to the example code.
+3. For example, to change the LLM provider from OpenAI to Groq, and include your Groq API key with the request, select the values **Model Providers**, **Model**, and **Groq API Key**.
+Langflow updates the `tweaks` object in the code snippets based on your input parameters, and includes default values to guide you.
+Use the updated code snippets in your script to run your flow with your overrides.
+
+```json
+payload = {
+ "output_type": "chat",
+ "input_type": "chat",
+ "input_value": "hello world!",
+ "tweaks": {
+ "Agent-ZOknz": {
+ "agent_llm": "Groq",
+ "api_key": "GROQ_API_KEY",
+ "model_name": "llama-3.1-8b-instant"
+ }
+ }
+}
```
-Adding variables like `{context}` creates new input handles in the component.
-
-8. Connect the new components into the existing flow, so your flow looks like this:
-
-
-
-9. Configure the **Astra DB** component.
- 1. In the **Astra DB Application Token** field, add your **Astra DB** application token.
- The component connects to your database and populates the menus with existing databases and collections.
- 2. Select your **Database**.
- If you don't have a collection, select **New database**.
- Complete the **Name**, **Cloud provider**, and **Region** fields, and then click **Create**. **Database creation takes a few minutes**.
- 3. Select your **Collection**. Collections are created in your [Astra DB deployment](https://astra.datastax.com) for storing vector data.
- :::info
- If you select a collection embedded with NVIDIA through Astra's vectorize service, the **Embedding Model** port is removed, because you have already generated embeddings for this collection with the NVIDIA `NV-Embed-QA` model. The component fetches the data from the collection, and uses the same embeddings for queries.
- :::
-
-10. If you don't have a collection, create a new one within the component.
- 1. Select **New collection**.
- 2. Complete the **Name**, **Embedding generation method**, **Embedding model**, and **Dimensions** fields, and then click **Create**.
-
- Your choice for the **Embedding generation method** and **Embedding model** depends on whether you want to use embeddings generated by a provider through Astra's vectorize service, or generated by a component in Langflow.
-
- * To use embeddings generated by a provider through Astra's vectorize service, select the model from the **Embedding generation method** dropdown menu, and then select the model from the **Embedding model** dropdown menu.
- * To use embeddings generated by a component in Langflow, select **Bring your own** for both the **Embedding generation method** and **Embedding model** fields. In this starter project, the option for the embeddings method and model is the **OpenAI Embeddings** component connected to the **Astra DB** component.
- * The **Dimensions** value must match the dimensions of your collection. This field is **not required** if you use embeddings generated through Astra's vectorize service. You can find this value in the **Collection** in your [Astra DB deployment](https://astra.datastax.com).
-
- For more information, see the [DataStax Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html).
-
-
-If you used Langflow's **Global Variables** feature, the RAG application flow components are already configured with the necessary credentials.
-
-### Run the chatbot with retrieved context
-
-1. In the **File** component, upload a text file from your local machine with data you want to ingest into the **Astra DB** component database.
-This example uploads an up-to-date CSV about Oscar winners.
-2. Click **Playground** to start a chat session.
-3. Ask the bot: `Who won the Oscar in 2024 for best movie?`
-4. The bot's response should be similar to this:
-
-```text
-The Oscar for Best Picture in 2024 was awarded to "Oppenheimer,"
-produced by Emma Thomas, Charles Roven, and Christopher Nolan.
-```
-
-Adding an **Astra DB** vector store brought your chatbot all the way into 2024.
-You have successfully added RAG to your chatbot application using the **Astra DB** component.
-
## Next steps
-This example used movie data, but the RAG pattern can be used with any data you want to load and chat with.
-
-Make the **Astra DB** database the brain that [Agents](/agents-overview) use to make decisions.
-
-Publish this flow as an [API](/concepts-publish) and call it from your external applications.
-
-For more on the **Astra DB** component, see [Astra DB vector store](/components-vector-stores#astra-db-vector-store).
+* [Model Context Protocol (MCP) servers](/mcp-server)
+* [Langflow deployment overview](/deployment-overview)
diff --git a/docs/static/img/quickstart-simple-agent-flow.png b/docs/static/img/quickstart-simple-agent-flow.png
new file mode 100644
index 0000000000000000000000000000000000000000..8f855dbb33b4a1547e568eac703fb01ad62b4adf
GIT binary patch
literal 1203775
zcmcG$bx<5%w*`tb_z;4-2MF%&5J5s9NN^AC?he5N!QI{6eIR&ncbCBj=S}Xr_tvdf
z@B6;|^P{?}o30+JIdjh5YpuO@hka6z#Xu!Og@J*=c>hl7GYkw?77Pp^5P$@|(zugS
z20g$!e3q4fsTd!;Z*KDu2>UQz)%!YEdylx3BIDlVx_Z9W7@St*ZN(93!&cu(-YZ2I!fbatb1);~Bm>B%PXtPLbQBCu4
zmgo1omrLPXL9$4byx6xxKOVi@23&SmU0O3+L-&ODJQR{b0}l#W^BeE8$*{mA)5YM&
zsGesV@5|J!(^hZ?zjA?GG7b(-91b>iEGZ#jazV(z5xumi-F?`sVxYJBJ70uJDhi!Tm6J)DU0de0J1k*uyX>7>
z6Bl|n!lw(m3$Esq_N_(1v<>@_dEd@KUP#M|mB+CoTo#@|K9918dm@nLqqrYGW@Th$
zD<>3o4?$))Ws0Ztu&*foiOnxo1}5jskR{PV*30XuAoJyMFO}TuYO-W3&exZ;--oy)
zX1O!t#YPb<{v6aLm^3Ij@BLEYKXbVTHsXsuKBl+`!q-W1d^l-b%g(uMbzG~zw>!Lz
z?p~u2gZoD|wy!7@4|lSRGCtQ>KDWJKaOcaj{nN^HN;BC3Ev~_1gs>N({_Duyy^E63d^*ZWNEh
zu;SrboG@pCnX)>XowO5Ndakis6x2KdL6AEjDiXrh$z%1@OJhmw)Yfwq+K?zx!5gI&
z-uyyX*NA^+;^N{<)BRzokJI6Falu%wf{ddnFE)bRm&7;{
z)gyaBK|z^G9LB%m?gjgAF3A6>MMB}{NB2ovMdd2LtgMVzK+u^ZyV2?SX597k(YXP3
z59ggHrhYRR)S2xtqSTd2vLYExE*Cj@(ZO`wEgT%!`{iPrpC1%CFU$j+e5tv+ExI7WDZ?*5!Y#b#x-wZ*AGv
z!MmEsVYAV>@Q}F>!R(@iF4Ba1$S@l$GPH=k-axcx28)CR&!-q%@>LH+_;?@
z|JFBJc
z93LO=UGaXdsr`or>dMb|>0}ZqBqZdcdJ^^Ci6nB_2RLmMt-%YH0GAp{L7fy
z6Dlt7;)r*$7-^2fa+vT+(iv$#
zcD~@lR>E72SLMHM)Ove*DsEIZI{%?>DDlJk@xlkY))fvDxf~i=_Gm}8jFS@n&UHKn
z%flGVrw+Xc>PXC4{|7G=M@PrwuML(9+7CA;4hPQ#V}@4gnm=ze*^N8@goq4TN7c~N
zfg6IE+GllEo8BB;&S`RmK+Fv-6{u_
z4hep4yy9&dnG5WV`#aQhC8NiMIw3e6vAl6JAG=b4$<1yU5+c?5eNcL4dqasVz?$Z`
z?H;$Ym%5i`L`mqu-@@smL+QJGZ-wR_BX@%&qy9;XdBg6#Ni0r36_^CLkjVP^lhqh(;*(bI%&{=Hw9)&9K@eWp$gkJ$zvG74
zj;tqo1*iSpctFEK#8)_AdaI_e#3kBJxqbFB?Fpkq<%m`6#a85Rzt_88SyWp3X4Vtp
zkNF;i%@o?ckM+_Ro7Y8*M*Zx2uk>n?K>;hIc`ko(-*8XLT>BLsG4&)TsPs0?SubD?
z2Lh-k*cW@jZXU#d(wuqyFubXWK+M7GbyuS)r;dz4dHLTv7@2
zez1?-;S70@;}`uqyyM4|)b(x1SH~_-9JBK?GczMgrP?{a$P>f+xE$jfc?P)iJAXo}
z-#6jZzi$+Z9aT!Ry!1<&d|cZjl6fmcwQD0o#Olp+D}6S@=u55&edrv+U%^Z^``lYA
zHo?Rq$mc$TQ#KyPD_^ICV3PhQ%y9pZ;c?1;@Db^1FVjcIy5)fG`$T0tanRo1ML;!1
zKYSkZ*~?xcjSe}(EQ`Rq4IL_Ksoeq#o~t`5NG0)U?at$0!i9=YaMT*UtE-EYJHU)i
zRc6y@p3v3>W>QA|hUhru*62Chg$cvnWsb%Mt=-qfUW@sp#gPJUX;phnX+HL0B)>Yp
z?)N(WIpc-G#mg&NxG>R~{XirD;k_e^zPig!aABIqZ?M}M$Y&Js$#PgLT0359R3!7d
zQW|z&o!<|=_7Jr~d~0Q8bx)C$)d@i=6aU)`KporlQB%shQ;p_jc@UTxz%F$G9OgAs
zd3wVg|dAMn=X~CA~rE<$Ieb1w&*%^P{uPdZp!L5!+Wlz#&|wa%is|5&4+Y
z?P5FWsIv1}_nMa@FZyuPxfL;aob=pHGJtv->!~i9Oqda$MGMdlYXMbO{t5|ny`%Ki
zTh5=M>Re#>T(lG$bGMwxyc_Oj_{@iegb&H@1^?}mnJ|UB(>&bnsw^=Yuf_drUnHJl
zzSwv2dFg`ou!o*^`qyJEEk|XO%BJR5nvy9I(u7zF{Vjtpo)vx|+4hU(@xuKd0LlEXc^eu_y;o%{I
zgfrgXElJo{1WpLcCsYsPq4Cq9OE$6bI1hx5(;b2BqDT~O4d7KI2aD{G>fj+=Cb*NujmxjE6*
zRDaUm_>trnEz6}SGO8m}6O&)_)rPc`l;T{GPg&!U@PGUCVq$PsjPt8@pE)z5Z8sVm
z$aq;kPx1RV{wLJkwT@%kto3{KRKqYNp{TjJA1N|2QVBylNlHd$(e%u;2m8Nc1C&WR
z?q}Af_?z%w`yCoVW-6t@{Xvvs8JJmNlg5cB7P%g_j{L_6g#X{SHsbr<<{!pgH5)U57~9w1mdi?Sx?l75z#j|>~{Jdd=1x4y(c$D
zqXQ4Gz@qVIXSN>Xo9TlbBLK%xuDQA)S;d6+J3~ljoqc(Gq>~%JQ*h}qi0S6T6hw92
zDBTg^ui!H4N0z_Zu>a^Ep#IKd-gAR0>@TQoqg$fs1hZ%d~(LBG$T?h-Qvd2+ls9;m5N4PxMnS20*doCN3V^
z23a-nTW`xlfV(OnlMN3Kk2^kQ;IR7IP^R120BR9>_b0^X`oX+<-h2v$Y!}Frzn76o
z37b&i0eg`F&9I9rp_l9Je*9D`DB!vU`MA3ju}!wPe4QU0f?><3Hr
zNz+4TENv)pr4_Q&P>xZoFPJAB*i|(6oSN$KK_O#=bK`!oe(u*|y#*I>i)=ivn6eS?
zpZE`@I`Kc#f0k>y{K^nU&dbf!-kZv%x^m`sI*b^Vzb-f5LXT@|a`nQhsBzga&g7z}
z!1!rp{}^e`e^v6m2RVytnL|8fHxhg9cHg@Fq?1QBMcE+VP&L+w429%P`1Hv940v|?Ba(mPoJxN{oygrCNp`RyzbB6U()n~^
zGt5-kMm6ZWsvH&;7EAjvLH*~>aNmP9Hp$R%4^&%RTruaqs|ZJH#DNzs6+rL%p92dM{@SM}dl4+xsy~
z5mx%uVr&-+5N+mFQ0wnJJDnd*IA3ay^5$+1xP|#8a#RaGKG%fVH&jR$Sik*&0)Blv
zEjAAq>#X?0ddVhvBAVyjsV4Ui9#);2xrl?$nW7TZ6UFRnIrZ&ujvg1!r{HI6|LL-BH<;1NMD;P+_h^
z@=WmGMa=(AViBlt<>gj*$s&x5j9KzlDrwsQJ`}zh%F+*#lDTpjX)KeIlZh|x6rm6r
z+-}88nnP^3wV2Z#t@L-+LGPGqx~gtpb#V(jA14_Z8=LVw(3sRhg8n^{VT%BWxjs+I
z3g+kK$)%*EAQ?fcZp@2n;l|RPw%OhHc>pi5iKrBX4Uins7LQZH@t9+-uHKt0m6Zt4|NOa^S63$&MJ~#4eT{Lk5wf(s-0Wcg
zbZtSy&24-YKoo4M9=lWoclFhd`(~|xxWImQpP~9y$6Jjt?VoQ>0|5sB3K4R0Vmd=^
zKQ~9Cz`FN=Tr@I6$(l9!Ms6ua$IOX#g1=}=8lC2*+-AHhgHOp*JkaMVpwzOyiVS8qx%e@kIL%mZ!{Y$p}HpLS&j^~ZSA|sWtO(}58T;|0e;D}$51QHPmDM1Wt_@$wN>;ATKB9117nMNiv_kea#HJUJi3GJ^iwk>)oMb+`oOMp;WA(7`@FRAyuDi>^On;9GS&hZ*Rc7^}Vnp4~<_J!aAC-%g(`+
zTY`$~ND@uE4SmtAkUTuQV(jtp+gADwayEU55+f5GHhp(b&$I@n_`^dYetR0V7)L%T
zgM^h{KiSRIZi-J{1sZ2&WoAb%5Pc>6SAtC9n`&mN7iQ-_fW)-s-f;~#720&t;Sp-1
zt`UlsmrJI5U%EXCEmw&5HKM4oBsp8kYI}q^#V^qVCLfoxR+%CPk
z*N(97Ga`LwwGj8m_h-yp5cc)W_dCjuc8K^p^^$@INn~6-AUmUrLa2tv@<7a18H5$qkFrLF1#5&RE
za?8tS&=&^1qkhD~?u8E%w29?T4)fsx*ILxK8%m`axrX_L0B}Ez%0pWA4yB`he&=d|
zn;~LL4^QXwal>Py{y7{ubr%HfLytRlPsg>bPIAms!8w2hga#^ZYbNj6sXZ}J-u3c$IlQHec_rF&ehY*yp%ZW|4KQ5%J>kYaNt;x%KACXrh`
z(PIO^VVetB9QP_?u4`ZRL_5HOjI{iNae_Ggg!&Al^wQBz8tTM@X3rKi4F~s!SC!;U
z)pJEK+8;|q?)68B%D&o!%_>m3*QF#Wb3fb>IPHBJb?f@fX;oHN@mox
z=W_nJcJq(vn%^N@gCnV*X&AFx-?e*$e_RXb%myUbUVW=r{64}WokIfLCJ=li@KfK?zRC3U4}C+vEOUToSH2+g0{$fCD?&x%XdPXQC$Kj3uaTAfc0
z>nqs}2L{_As~$s}mz$dgcNMV=ELochW*RXPoiG#3h(w@_?b4mCB4CvZ|`)V>Uet6h^1z@XfP3wP^VjjCN^a1!oY_3&%HX8bZ11LS=BkBDuz#
z(mX|@r#DBo3X}q-@gxoDvxXDW8`u%v?5GQ
z!+&yspJGq#xCql9{l7)d^jADXLb~^83OCW!28W1)wh6b8_xf{Xd3ikyZ4&mW9fDTV
zk94UJ(9eyx|B6K+eTP9Puev*4ZdR23Nyd!RSE~*mOwpR(Un>*A?fGJqDm+Tb!SM@W
z4#0JUJ?7rmP-S(zSg&g`l0=7wH!{TyB_h-5qPmqD!O?f2ogOI%{f5cOgmiR47?}RL
z2o@{#7T|u=cF)%P!~7p90;^K)dNcF$6q=3JjjBpY?CxU=P@?6`+8#01t8VeM9x%#i
z@|O4fdZAYPB-5tzse?qwwMq7A;qKCjZZ(*BsG8nyHb?rB3wSHBBe>#kh=nVTuo;we
zJCfYS0^84yZ`66yxFcb!qpWP<*MS|_*3zPS;>m2T`@Z2GxK3TfpCS5E?=HlPj7id<
zhpk?y@PUYWPMepCHeS-n4at+_o8aXo+I4!>_ptYwD04W>iWClLu2v0n=eJf(>tiL~!p+Qm
z;)^6_V-b)ex*9jFPl+9GbRO*EtEVj<5(&Lo7Ca6@Irmre7$7hM7vZ|q|MnQU`(5(u
zrbJoZ{$?LB*}h)(>Xd{yg84WD7xxPk;E@kSk$PAH5C)sh2kPnUuVnIL3`@;h#r8(2$=P!3Jg>c~N$*(OrBONTzi3%Bta4Gun9@t3hP6>6_6D
zz|HDKIcr^est~%{jypuiC0r8>H^dL_B_Y8&v+Ql~ygk!*yPA}pIXLirycB(@MR7=X
z5&!)8hX58!)!PHx-;(5WS`Lu{3vv!EJI(-<^^~89iNi}aohw!<2t{j+Hkl{~A*tUw
zmW)DNK~QtbcIw(=0g0gVh>Q#pwNa~XwL$-mmna51GN$amz_@JgC}MgYZkMv!3bu#S
z3^ks2uQXa5tG`b*&R377HYR5gS=ic~v|9{9*1V`BYawJZq8Ur}u!pnC5y`#65Iuw!q%O&)QmAbl~dlON3SrvOZp2?;1uv30?|3jX&Mhk2
z2Qna^kb~1LS6aA<_Jzm&*}A+jJ>DShXTLi3X~*oGHFVO_2`U(<(R@7qwe71-
zBNIkbx-UfcD&(4UlBnQj+V@NA2|773ZS`Cf#v3tNW3^n(sOM}|j>Jgpr%Soan6tCR?-v<)oquKNZ>8>E`Botwi6bIa_&Y+Jt6-v#rmiw5132gC>PQ=YiSu!^%
zGM`7gNIKxH3}!y~j~w$-Wb?x`!;LQf@DFlyGSI-`>Oqg{J^L=|{}%;o+x%Bew%Ow8
zK!snUyp>q*tDGNi8N^@v7;TfCA};hKvg(%IWQAi&*#6@8Xjmq3SO>r=F^Sm1_~HD{
zd|D`M<&)PMa|m=L%ds+A^i^`|2|Q1j*|HyFn68ffiBLwljHG7tm7uuaZkFL~;Feqy
zB3x)h+emWKhR~joj@gZo*TGNL<1>7(Q}=R_G)9Vt!N!hjX1BxQ!mEzoz^AY4>M(^(
zM-{CKwH;ctfP!;qDEf6URXECzHMW#xFG)_6F9`QjH-
z<+qzy+Jq-hwlowgvF9mjSiU+^A=io2STaAjb*V52QUz(>flbF8>Pr|
zoE^0#k+2M%Pp@&mM%A{##F6zqJ@&a-&>hx&-tkHq<)2*Owro(Rw=p*-;khI%#_9Gt
zU-d|p3k5Gz2iUOy8@8U`GBO_6gE0ow^Ycx2${SZ}VJ545Zd55mM7|!~*`|TN(ZBeH={)6atk(vlJoRt*(ahFDHVABHT&_yEF*tmhma|hEz+mEWc0&
zUa>@0u+?`XT5SqXWNVBqU8J;iK6Q!-=~fU_W8EQD99uNoloIc9`ixBpIxO?IU3T~&iuo-9>
zg*(-@T_$2I4q9!!T0A-5YG%B${6ri<#As;nWrE*%o+vBs$0n_y$9L4mRuc?aRlCMk
zc}^PgIluz)+pj!V7K?zhK8=zPBT)SroF3Qw)+7E}A
z!S@_wd_fRRl4|gF#bu2dvg{BY2FlIN<(?344V${WxY)ki%S=qv
zaUWtD@w(ed9JR(s<*uMag%hI4z1b6eajPZn^&YWz13-b=FIjRolH4=P(R4vI&byI1
z7}zggzT7{48G;5vN!a_HW+9TF|B}=|3*K;)HcJg3=P+CxiHR3dWBV5xp*|_CfCv_z
zCt%=#`is*a?H;kE&t~4+Gn(HC&I%1JoSE~!Ok-+>jK}r}1U!QhQWp*2n%I`W10z%E
z_7g;O+Ub;N>F19h$My0QFt(Dt(&Fn-aCGu$Xpob>yV5`~r$G*OjuAvk7qhZThax=F
zPl)?YPEHpW!HJRdaK56A>7+F6tHrKfb+-8UhC>!hqZSTxYTObDEk|Cdh}^
zf%~>D?`DeehJ9Dpum`k66{wWC`rWW-8FM5J+BY3yZ@-03N`GDK$!q4;`sy(#II+6S
zVihzhe04gs?!8@aPAJNxLuH60LUfd-R)u8#^X!(Chaseh;m6%{
zNGz2mMYi{VqKhFYbLg|=2@69piS`2se-bZ%xzg74>Bgik?Q60#WG=PJx}QguMV=2}
zWGrd>vMx0p*BjAj;L8f+=;?}*Yw75}6ZU!5a!L?OIF-Sf?2XY;Q8Ax54XlTVo#r3-d2x3o<7_3H!fDfLIO)-Y|TrQ7K7
z)~+2%4#~lDLeapWjX%6^0LdiEArOGCAPcmdo#XxX66>BmkQ5h6#P)EE{#jewf)MNQ
zkY(TNci9&GSDCx`csm_gdfkR5=cZuW5&tPv)KkP|-a!tyo57@*q@-`j?>v__1)HcW
z?(Z%E5uZ#oWCtRN3k~TY4ikyW$iN6ca7`!0}1WE;xZyBt@Yn+W3bU?+ox=T>A
z1%kJeP^um}#VvUe+}Ii7e1lc0Q<#HJvwi+Zrl@W}AW4G@Va*b?q(B97g?03L}^C*z8uR~ueIV~-1|5$CIi>0!1T(x)>Je!2}2nqyowYuA1d0j-N
zz{N9-!(#SrYw($cSOTP{M`CGnar3czX>AV{LU#X#fkDZ%Km8`d@xIq-soF3kotSTT
zdt3bl-mN{Yx{3B*S#|unX?&d|=ZR8Mge+V-3@P7n%o^9$aJ0ATH=@wJ0)5p`+&Nyb
zuZ7&sb-OQhcp*>Ua4K;t!PARDjLZ}v6)q3a;cGiPU(8vt>zTR-@CuG%*g0%gg(~Gy
z8p?Nf!xze@rs$KZ2(SHdZO?RV&{gLaqK{z2$!BSmCdiH=m6U`zoffh7m}kK*;8l94
zFu=Jqtv8NqF<^EG@$1jG
zC`U6Uq7|jAf#8T-YC#%~Hp!PCT5oToJZNNeca*SCHm%htTj=y`%&yCKiq}^2V7ol9
zvn1c?+VA`8g?DPef3ba`yyQpN2MoXolJxEIu6gFRr?QQuyR0%ou|RM~=JzYo)WR2^
zPZmD8z<3jy*IqB9em6oF;ku6oQ3|f>`;or2<6~n9PDit5DjDM`+1wNH=c0ypcXxR8
zLKAk6(WvNUP!S#Fy=MnhTx&NwjgN*(3?@<-)AW$ozc6FC0_2j`vEK%VBx=0&3=N>{
zLEFs=Pz7R3Rv`;wN{vFH`#zQTr7@c3CpWiz6M{9HR?1h}?e0Mom+nQ)ytBb{@pz1Ni3sfRg_*AHfzt4}GT3y?`u=NHp1cTrmC|XfTbJ1w@
zN>Dg!DjKAtYN>&!r#Ct@^!s>;KV>1e6^0bV#5A7lOEyMj%Lc6m&EB~V_`8yBWeW#h
zwEuM2D;a&Ksj6!2f0mFy*RHrs2dDThbdEnS*#ZAPFl(8?mXCo+u=MiHfn&r)=&z3-
zKXNM%DWoel)u*x>rf@Xv>jm8H?Pk;*VNJd{MfB|H?Ukzww+L!hOiwZMAJ2A_>8=MM
z8*VOd_;SW?30hW8GiSgfsC3OT92^|rA&`P`U;ItcHdhqA4wZFGg{G6a%zmu;WR&qX
zt;N7@gG8UJ8}C3OH|$=rre&*#x}EFeMb
z9%H~Tbmn|*-UuePBmrbXRoAs)sFXV5hZg1U+9^>aWI9GNyc*@);cxuHPN}X7r4IFe
z^S6<_tDpAjK5zMTP^bjo5^fnhCo*yc_pXHD&`%#&H-=qOW`yjMK1pmxja(97!NTZe
zLeg9DjmSIK1;i*YL%3gSQQHo1OAWZc*7D$sH_*ujOxTeD4Zv%iYh%b@sXYP8cU?|%
z+Vme2-cDu_vAFFfn?}$NG(%e>PFik}Uv;rRdObpgLbWyx6Ws~KO7lz*SabymazQV6{^}t;cVU7=7;^)M#nCe3Q3vMFtFIX4GMmMduX+W
zF=nJudpMC*2|3Jw)0yfw4~fjWXKcE#^pZHmQFW1oXGWr0QO*%*%P1I+k}P6t%kWF6
zz%bJ;WG||Na(A^AlEu%buLBgIVruj0t`~IYQtQ8vRe7!XTe>W~B{o)Rk*8m3MPFY{
z;|%6SByG+1tAC8=Qo{;e8|JoFkQf{qo|f^P*yY!lP4?qXiUso-5BiPk7_cFS?
zU|SgwdWDT;$;#Zc4xa8siCs;_C&D306d?kkP-!=qbb$dH{;zZd=X1`-JT`*x(|Qwd
zHLV_2d5UVi9-Qx>1|2gA<4`~Sy$nH@ipR%2(Zobu?}a5iT?&D*IhfJJP?hDe-g|rm^|2c*besi~ffETFy=SHDp
zH^l<(qN}MLclijIDcOZ?$0;@PJT9WXB}C~jO9;RgkeUYS^y*_E8j6ubSs+ge_D$J-
zlWd>{bYZJ!75cmM`N1O}FXlW$wTM=>fG$#vacntqILMri$7ludeIEfakL7;C5Sb-~
ziO>B(VY`H#7SozPq=#PQ90e^2i}C^Ltlb+`9a_p3}8Cu_dqmUt7Wd_vDZH@mg#?{Nl0|
zZ9;#%+a2Fh3;v4`;TZj)yS`nc+`f8%g|&4}{qI$&EqHEnBNACWwa{FpoZMWa$(*|e
zr-81;CL8D5z(78nwQOcf7NXgyV+nTl$Nr8`HV-!|CXKz|y1Fo;x11i+
zp+VIdsKm>k@DMQh+^?FDezp(5#R@d|`K7?0PHNN^q_PPKd*wt<#*yNqGcu03g@l}7
zjVHadoe?*@Usince9}gWaOb~AC|(q6M+V!C9e7<*x?2?4Eo^>TNKq(4(|W!)%4
zsq-CX#ihsErM2V59gpl`b`R2l?W@@xbfMb(Y2$}8M0zdoll!FXXQ~0&k5^^4S(^@5
zIJpbsxzs{bml^lcK7;XO<%E-|)3^xsj$Xo{t&_~BjEPO9!q1e#*M5e$AR=Qq_d2No
zofbG!@G!M()WTX8RM)95H%Yzq97{XpIFSzDHS>)YNEZ*eCy6g6WgGXTgw|>f4N8x!
zo)eGw>h@yqMR}E3<`9q!wA$wNDT4gk8sXqipfqqP7aEFIu&o{^Wy!g>EN#4QoJnGL
zp+;|Z&g~wUVTu1t`)Ghfe$&%-DaPE|>7<9FZb-=;*!?0gI2dUfLYwP6oYUe2p>M09
zwrMmzf<9N}0;3X~Pd|v-E#z+_j&}#iFwX6=pmf$a$BIO<;22u^MZ_&dHebv10#fU|
zu5vD#z($&0m(el02`(a0khQJzO?rJI>{aBXiWV3@h+6ISKsJi5R5pgQLFXA12TXI+
zt3nOdcZk-9e%}HjE%OfYwC+6M`(H;S=8rz>A
z0t3&k-Pekdza~mjZy=v`L!CaYnWW-ZA>`g~78Vw6FePN{j8J8T3)cz7V$eO2O4bSe
zlL$4YblrAvJsLNjZTofx@t(&7!AVt*H%m5&mEPB-38M&?J)RR}(Y8P+gb)c(|QW?*SbOf
zuN2Cj*47m!0*rMKMuZ(#h=D>kDo32p7V%ouIxK)-{dJq#1m+&B4zy6b?t2+!e|Trp
zO|Y==a!&rDWV@CvysGRP&2K5BP&5ih2K1FodO5BgCnA1%_Vn3m1CGGRv12VG>z#z2
z+bMd1J=SWQpGVgoBegZ_Kuv&M|IKCO8_Ab$_B1B-&2|rlxq*YYe*>F7zySc^idh^U
zH|R6Gl)gK4Vj&OpSUrc$4yGC~p8*wK!wa>zbSAwm#vgu7Ah-)T&?(N*3_EI9&CXI`
z6X3)8dChrgex(rWB*@}mWL&IK?seWWvI2QR<-4rzFwl{EsY%`pckid~EMbQ&4guza
zJcnOz2sLX1)_R4mUKGjUUoq^e{Z;
zD!hpJZmPn@Cq-+@*4*|$qhqfQy$+V>J0Wr~;P21&*H&n$K#sYs_F;}QgvFG_osoeS
zZ(~ucXspC);?M4{Gq-+{6VJ5XF29Uy)?rZf^OgeI>&v9SIC)HTSHI(RU3H_H^rsw@&pOKT}V^IhZqi{4d
z2z8LZi%GU$j>+ucLuP!BfQY)ARU+FcFaFhg7c1JAItifq?;(nrc>^wk|5a
zUX4SyW3$Mtfr`JPH~b%_u9_a_hmwv-9nUN;Ib!
zulZQJ4xpy6-`W19$KYwM}%vjtHCd1AXO
zgIu~tk~yz4l1zC_+5#v5!Rq(@_`31qKF^m4ZbZo-{o3HmS0qquP~?|F**5}|q<*-n
zF&;+Xxq=qbG|rq57P{IfHiNSW;2ea=i;&s5qo_afFB*!XE=rW8Wn@&qlI$X<(Lp1k
zR8+*O?U`n^LD03^*}6Cs%SWTcv9m@*dcE9bzA!+YhA-Am@XiEA^vAa^;Fl-SVWcPs
z<*mNZ{6_41GKbYRx7u|0z*FFF=z9z_Gh8=O?&f@+)I4ku4_ZJg1o&`{XA*v{?ojs+
zoe0PV;TN*aqjuK=RH73Lu(JFKWdMs#GNfy8vabLQE~m?8bg3v)ZSk|nIbU)&)1dJ)C$26`zPY6(No2$
zg98yyD5N_{D^N%;0k>=1kEI$ZkwKrOi2HSUqA?XC=$jYlaJJ5Y~kRUBK7SH@zyfmajU`hRgl}iQT1%T+#GuD+jav~grBX4Xz;E0Wy_|XFKaOv1884sq^`|()j8A+9dQ;SyGkm|HQEW{{~k-rZkv{
z0U&|IGKzlc@QgunM)>#dDn^3k;n-N1a2^mcE?9~x`Ba`6si9l4kp(!=1Q=Q%X@|Rd
ze1yX}ql!b2^6NmPG6Xdm}
zLZuz&;oyzXBCjJcl@^ORZ=7Tc5nZROcRwD$ogfmvG1u}kn73uf~IZHxv@!jiPzUjgv$sW+C&h;Q)tsRqw(^O#!9icHLH*AWq##1bwjF`BbY7Cyyy;CphlWl0r
zQH7#wfQ%xvTvvN1pheAf^yK=K=gfIU^-)0TSfTlPHuY`kwKRPJL3;?^{vFLXlU>O4
zq*=r&u`n`W{wG5TiNbQCcb
zD>^*w%~A6zn=ooBH;3<<`%yU^V1SGAdobHw=JP@3F+4VF-*2G2q@|GI0J=vf#xz5^
zsL$%ErpvNj$S5M1H$IY>H%06Y+L~bUv9hQrX6@cNxfZmJ`@EY`5s^Xv0k+u
zrx|u=US0kPED7hU3!VDCNOwK>9eUzeX0;ySA*X
z`B~lSfsnVm0J>w{Dv|K@JcWf8rw}h`;Qk~0G+
z#n;Lf+;y558(YBxlEAT$G&!Z1wX6D5e+g>LxYZrdv
z{k2m^z=R|O*ql~-qHig69-PgQbW0+i{_Uc>#qF#cc?ZhuAu@-Us;u!(gPscKZg29`
zL;mHM|F5qO4#yWBmFk>&3pQ{NTA8f*4wavj{A>!oKd=z7#7b|RZ5T2JTQp|%PZjQ|
zJDW%62ASw#eqP`AKkl%7^M3=%`qY4cP%4-ClXmrzOyT7UvH>)a+oUW#$k6vWn<$P%cjGztRE+G&G%ln
zgR27}r<-qF*)*1(d^UVcxVS%ym@5|#p%t=U!5Bxh+}u^g4x=eQ&B-HFW$D=c1f@2f
z7@DxgGduUIK7aXQwYd-u=crgYRcJcA_Bg7$D2&$asW?|8dI^{<$b#9NrxR3L2KD~x
zE>WmW^#n7^=WA2dShl>2M{-Ikp3{FM_+nbh+2zNXF~z79Qsjd9J*^CAhW>+An7~)R
zh8+AVG;Pgw3j-~q!(y(2Wy~pwE^vgk{ptrwy}qK%tmAyq%j5Vfkz?xbWnEtX5>=$G30n8bd`LbBZNq7B
z+4s7S{kox|tx!0YYTHp=Jt?)N;Pt|sBz6W>EHV5&Y|mH$Z(+pwZ>gJ5M8F*n6{F;H
z44?dbNfu^mYiim;y6rZ4g6L{won0T>CC=daZYh}r;6VSb+Z3G?)+i{L0N>!On+4j+
zevNc2r$Cn5t(xep5$!wx(lQwtWN#&!#n>B3E*EF2RMnhtMUy~JUGDIDFovAM&u-tI
z;}E%W$y)hfi(7rF!a7;=`2-)+QD`NUTn>FeoLmJ@ObU5TCZK~577!u{;A^M%(n*9x
zI!A`87kyD!{|{sD8P(L=uKQA@Nl^sp!3GK%%PQUX#!4?RE#H4sQha;9sawbwrT{NH!2FN_RyWQ5E)pXa`>`?`LQTlAMvAQ?8E
z^ralHQ%9d#R-z&b=qsaUzLTx5WnG=NVRh$GFPDz{J{J0^Qj+;r8b{pv0h3y7NKM<(
zT@?AGRXjr4iFqYI*?*eUuTG_*G0m!~9;|At(ofBs<7mBxX>CZm*jkz3OGIw*8Ek7@sRzxZP+R;M$C
z?IX0BUa#eEi*)CkSjoZ_XLqob_M$R`F#C%dbu)8fMnt}v~=rVe4ae1l+Rbab1NC7Hi5BRMxiGw
zmt_q1_-0ru-GO8qH051bK6a(=W#rqA>%ip82%bUHFQo>U@jch*7>6zef__J~vp6_#
zi8=cfy$gJtdXqy-F*(=1qiZ2@-nG1#c4|gj=3z*~uT-$eE3Di5s)Ng@u))!1SrOl!
z&~Nam(;%(B9-8YK+u^1gFY{_Vp1M^UBCNj>WoaafA338hlJxZL)J4wGegfZ3x*@eVads+?On
z(oRWAwt`gwJiXz$3bL}b{eeH?0?>eas
zkvn8H9euQGKp>E(TcK{o8kQc-Sa}RIMymjkE~+(03dOE=Y5-`}pKnoLTEMM&`6-1<
zh0QhjQBP^KL+AXE^nf`3kC!t7-l<)D=LP2@umI$+5jvy&G_xRZk2FT*J?{eZ=7sX$4wsEjwn0(
z&grWYcIQk3N50Zi$KA_aDKeC<^=K~BXp&IB?xt#L*kk!VC3va(S*>SH-$*{(T@{$W
z7;^h67;wBOQPT`f@^ecq?wP2ot}fgRK5Dszsh}2>?)0CS$TnFF3mUGqp!;l9`P}T{
zqS^#0^`@CK{(Bph;L&Zy%8sFW+>7M)!&^XCPIQ3!2E&#uH}TQYfk6uqA!A4TRi8e8
z&M3|OxtYnd?X6~qZEbDULYBz?P<2eD=Yyxqx%o$|B@t3mjM9CNxL76=iRbDb&}nIN
zL}xcxZZ=xJ!Qyw+R#=_GLxw5fE%uK+2^ZIET@9!S8r2kGQ!Qg-M`+XY3?W9}AA=KD
zz&kUjivf4PjOo68U*#is=LYz(NUw|SmYy`HoOe1YH1`qdjfi4B_POxMJONw$1y)Zk
z`?O5Z)9tX~X#Hg37}0SGzz(JIp%4gUSZz4(&qE!Z|HvkB&w&m6sd?HD4h|fE@N}#H
zn*qVsAK0}8{s(DO01w!H<9TQFGcFx?#xh;>FRz>73*1ArUcP&SH1E>VJlM{WBO7f`
z-#G}H^}HYFf*{AoGj@5|7`-gjBd!aY6#Lsc>GO@*Q6C=5Pc=$TOTU82X*xua;9s;8z%3Os*
zvOKd4V9T&CvaYe23f{eCYSHU4F~5}NOOkFm{Fa>Jxy%{jvKi>J#1x}@-5zhu&}nL^
zzk8@6+9h)!)xCP0TjTsI#EA@Ef~RbvC2P9b(Hu7?W?#SN58Kq{Fp_*TIYe@87>a_fCP(c^j7iGjMTn*_x%5
z+nsqM7r55mf8*EHrvJ=4^ed;xKw?hSRLbM{U89*2(AUphpY-`a(0gJ+gmQeK47W!ZJ8u$6B
zOVa4g<-3BO53n@
z9QgcspdZ)=GYl4AIBjKzXRlmV
z!5ov}G;ao;IBiX?cwnZ7!cel-6tb6Y=Aj$KUh9M(&oX3pvj3eMN0@DNsb19#7Z4K4
ziwJ`E)x1>X`y!|7e)Zjh&RE_u%z?MY4hw?hKOYh%Au-6k#fw+$Z$JMFAt}?L7TiOU
zv+u3BRTo2k8yhm`Q+f|uE5Ua&K$3o)M6Jl^uC#Rdo4a|YOmgyPW7$1qjqmH;OYduv
z4$kv)UR%7)be?mu@}t$}uI`D%pQlUb1Eh0ibR2j!iKZ=9adH=+jMaScVt}>nFIVKR
zrTS)-3OU^JQQB?$*n2gUzm4O$WfC!x^O1%|#OYCeTMFuQO`aUrOuB#9M`2ezI_diM
z|HMFk?R+>VdlghaU1o&;l3?UP-^WqiaJCK$YwNtch(#q)r=LnK(LzvO_u-3lgB73-
zJL;EIUl4~1=P_EaNR1f(JrO-|U}?!EJ)
zqSq618d}NldF`21hLZgd>;&10+Z{WXYyX&WEGsf7V%#=$ef|1iu!>HSK%dd#u34*O
z`ZF0zcaVYw;G5fQRqPNb<@nY9(N5u^pvChuAueJHd
zTqw=%)7U@r8z9m`7SCgaf1{YrMeJ%Z#U{g~k^$S|
zPUtBSP*W!vebsDja_xs2={FOI|GVS-zhBtaaI{Ygfg_k{uG_OdyQ(_87`Ai3INVQD
zr!DntQtV7|;Dj7zTyLrGS(2aK3xymx2@B*mqGw?QqoBt3%I$a>eyiMC19VHpEv9CJ
zKn1slrpje0U%#Fov{b#4+dlnL{!d*+%q3I*3L0e_VZ93Z<8q@A0;8k!x)~j_UAevC
zS-I4_>EsZHsj42wWG(-|N$f7Ki`&^LKpNE5U;#6jB=oDm
zyJ)!*vQ8(g9^eGmalLcOH74?7@B3aK%&7EJ+GB78&K^J!z*EU`3Hv9
z0Yo!Y@CMZV)IA!@x$}swkMVH63ni(-e;x7?Nl9aS(C^GR%+RassJ+QOgiE(p3+3169ZEjMELRNQnJr?%4A*tid5iS%HA%p9OB|3kSL-Z`{hA5XL+VFMh-@HptH;
zsnr1UZ|Okf#6+4sM`o1pXX~mLc}!n@eDsS9YR1pT{S5~XETOcaVOq19>FF+-!G)><
zLckq_n>{aUt`BSL0@?hC(n$g(yIz7MJ2wRREt0CKyKz$lx
zTwIfcME2IK9z_9Vt7oPsh$BLP;B+%Huwq8`fGf9t5y4j6KQCREeyfs^)<>(_am8&Qh0
z!?>){soc~6=KdVi^?f)g0-k7uhQYTlm?_(=h?PcVe6Nx7n(J@5h^N2vV%Y~En)L52
z!&i}Qvk;KId_iL)8-)!iG+V0H9k+c-DE<+!Hwjk$2H{FS0Q&c>tWEX`T9eFTPvt_Pq5eL{?X9kmbCAdc;YwfD{zl?(e
zn83$hq~;@a&pfB17QZ8-rM1#5$MeJE2eAVD`p^i+`@#k#_^l~v9G_K_!5CBza>7b1>0dpU=J?{E8qFKQ%K02^OAkLc#*3HR
zzV_Dp^q8qQ3Ej8ISE7o?>rw5LU}pke3R@))b4S#elr}ZtV=s-h%cjeFCe6VCoQYfr
zwm{bc5cX?7eEGsr#i0g=OX)IJo1@&X
zmBp-;BI(BQFNJnpLq49lG&L&BdXl|>q!y>2Q}43g(TOt*j2B(PLyn%@0jg~=XU{`Lb>?_N!a=p+shE#`jZ4Dp{EYUm;d{b#FIzu
zA7g@(TF8WEm%AQDqVbnG3yD^#3ok
z>bJCuA3nl=0dW||B_D-+pc6`qV&6{O-)H88M{NKhb%|+kL#b)yK-zY==c4eZa)A#g9!XC$0DDp<;=asn(2AS1|#XBPj
zD646>p5GaBX_KoynGZ%9`$g2@wdw_KDw5Z|UUjvCwt|7Fr#66{N0>S8mWQs2&-+AT
zgMrDy0VCEq>W!uzyWLf$Q%HDy(&N!}rw-vIb9Z_QW
z*DJZY4O8@#c}4ZDt(yDoD-a^vw9ztae?IY{;DuS{&M3s6G
zD>Wx}ww-Nqpw44%V#@H#bkOH74f2ypp7!=pcND($X(s=GFx7qKY21N@_^RG1=y$6K
zJ3CU*B_-khwJgZrM*L8QxtgjSz;rxC>K3nFY&-rw>tk7EJ5$HB4|Ipl3+geAdp~7nE2*^$h;+tB^HSY>j1Smboq%cknKH!3
z!3?!OXq%OS43CB_4Ngs!7&{w@$0^f`pZEEo_L_{i62F4`k)*y)8Rl^r5c^jRnycEFOib-awKHq(J-6{Z&
zNj0Yu}p!QAP?JP
z4Z_wU2QKA{PDs7GQhc(UtTu00Yn`kS`nQJbkD%QY?)aY=#QYmPv!x-+z=glC~=RVX&XcT%9rg`I+rytUX-s=N{t9hkGJG
z47M=Ql!2SEse?h~QhH1tryf^YS_J)}2N$!+vu8mkmt9oo5@33Q^HJ0=b*ZGsEqZJA
zjDm{-G`9n6SOn5Sr30TCPXw0h*btjO5jgg`0^cIyxw0ScaO4AMJLSy3
zlRJDe)JkQ70woJ)Y2hVr-}(|Qe+RLe%>;}&DuJK8=<|I~GSe
znjLHS^!|M$-Vl({&M=tW{7X`WGz(VjaD=r11^8T5g8i+I?rDzi%a)LS07h9xecxjP
z@YBfRAyDII&zw0@RLp9e-+LMot~FlJ6E)EolFHnjo97J82DeLmZNkh+oW8(b3Zp@o*=)a`LONR
z3eOI`*N1k%<=N}StOCCLIvB7d6-8u=rY{6;nd%$ZD@(;wA|w{|p}{C{UZzM@*0S`U
zM=xGPTg?E|&Y7`Gxb9$;vT9GS9YJOPqO8lPNRO^tOv-eT;S6Fzw|yfIBf>ly7L{19
zH}`FQmz6~y2F*BXl1fT$M5O!JyrvV_Q~W7uQTL!a$AR3iMSH_a6(C^f0=ud7FBNULw#tFJ)0c53C)E!yjU%W(U1d4ow
z|I9?%EN-6B84)Er0#^FRkS8uT6?FCVjGZ{r476KX4$H1n|0O5>7y^}BTsX?EaB^@+
zb3O$oyc#w?IF^}&C
zr0=14rid?8y4N2v>Gc26T)6W|b3-o6q99=XQ`+aD)0vH$fPz{70@A47hNkC6=hH_w
zVpy0sKD>*$IeruGm|RD>sAo0@jVC|02mci-P6eLe_LMVMv#4B-XnIMk^k
z-q6eREqu19iyKEXoH>Kd-BBrhNJBgl#D&A2vb%ZgW%Y?#8wD?!Btb{?n)&5RSc;cj
zHIpNUWgkA^biMGpG`C~5-vT@Bs_Nx01i~Q8Wp#Nrx3}3iKLbF&6DHbW;7vo{uR0+h
z)2#dx<~sd2hHwV}Q)>=-47o(toCAjR2C#W%NKsiSUvPF}$if_mGTrzBArbttKkvli
z05DuT014w2;doo$-wTXMAeOrsmvT*-qspzC|J1oRlV_b2DGWI*vfFtNpEBPZXC_R?
zSW$m_WaHnBd7j3QKJQK;LP1Q;yskY5Nl6V?>dK0BAkNPx06rd{i1S8mZFu|L1V%t*
zg{>oJ{JOUmc&kGoG@X+3_D72cG!72MStH2-mN<*SaTe!0A0vmj9+WJvrrI23$qBJ^
zbf6j1oL&Z#Pte%BIHBKUUYPi>xkk?cR>61u9b}QkhDV-?w9pZC^tY?B2mf)epIdWi
zkKr`vRaxIs`vkpEQjT`+2uOMODh!|*cRmNk6A)}2c|AWl7HtJ39ooqg_N+s`qKe#3
z@xUi_%4T6H)LXs2QMh{Lx4kvA6z*h&LJ
zs8;Y@9;4E5}rB?5l{rXLYMKf-NxrngZ$E0-$r_e-{2ytKI1@ZLfDc^hHHNr=ETHx$gDImTp2Dy!q@$APQcqL@A>d~iUt~NgIcw=zrUXO`N
z;Au?`<%@m|Pqi7MZ39oa*n=I=bcV5+Q0lB5rr#g?zC{-qjk^D?YRkb
zqaL0iGx~`S{{WR(`Mg}J<=5$pNT*+s)rN(6x@cyF|K5)O8ygKyJ@U3)HK=tly9dQS+Q~H4JDUZztp|d!*pZjb_
zt`B{cxUI6dbZ>}YRsc4T>;ye>T0{g(K*H!FF@#|sza(U-
zg_C)>`f5_-#NWwfTsSVEWmynLJIrcr4SRt)?v>Z{BCtqy2Ya;OM|Ylq`YfqWl>C9b
z3zS$7<+t8R1s+29yF6~Xj$N{Ywr&$kd
zO@KsMQBfs>Py^!P>8S;XR%scs<1|YYg;6;r<40i*zj5DBsSZ)+aVoE3WwP!SGoITLaQK^d(fTP->CDuA5K
z5rR7!`BB3l=;?+OYGDta!|XS&j0%DV#z!J*4;r~!OfnV$OW__B4ymiOrZ69}N@^Cr
zOl3uzf>1elO9JpxQK|qY-A-LLYW$}%-!J6KyP`UDk-+yj~5tTIQV_&mkXJ&GCnW$);C<+2JvmOn0{SC^nBuGpj
zWqh_}eRiAEX~;MFjnwo@O-@@m_a+fKb(^H|DN+6L@1$b?%m!>77F=*t!Vn7Dr>3yk
zbf2`%`f2gt#-hUw3x}e!xN55J=jAe~uW96$*8;BOXr}wp4@Us-!xoSfsRL1ti#T@6
zvijSOYCY-nu}4o#OgN2OO@`Ydf7U8B&?si4^Qk_l^&VI#jx612L`#7CR#2TjGDSL^
z>b~>F<<{HH!Z(@3h8XW
zm|Tx&*M%i$TQUAADJ|XiJ;@DtnaltqL+hURyvk9j92l+t#gNdfrG6@na9%J)#>ZGK
zAdF{awjIqk~{oT`+0YnP)EbcfCW1dyr@vUlj9N0UI_
zW3tg)89q>`)iKU&ZLD|_(uNN?N~RnqXCvieY`y8D#BD7(#j2L0K&QDc3-Nt4jn!~R
z)FFYn%Gm4hFZwQ>W}fS6*<8nAbE!praJK8-{+2pp*@WK4KJrEN#KZ&#kJ?<;s-K?k
zP;hW?RXv``wLUu7>8FfqXZ{-h3+naYh`+4K#cDAst2pk<$3UhLiVIWuyV*Fj7pW%9iHF^bz8lUYT
z9YE|-H(u^u|G!JNzjeR(Lv>QJA1nj|97cGaW_a9_GHI_LsJ1gv@oopmN%IqWvI8|W
zM!cOI6YHH%?Z0X%tCm~0ifx?*kJ#U*kk>Li86okh_Mz(DrhHm|CgTW4V`_k>Rz4`x
zsH-M2UtC-~^rk}^J`06imPnj;YC#fJ^|J-FM;fdhOf3UW_KoG6Z_}~r*Mm&X>?1uk
zlmq5BSc1v=>!Yf#R-Ad1pHc0f*lXs`J*AlSns?iN)oSh$55KMKo46sMiyl@e9_nY6
zcVlIztjV_ta=*$R@;L~8tb&v{0%nlo#LgVH6TqS~YIn9`q2ouBoNQeH>CmD@AEIMg
z5u}uG^(|RtS{8zt7|dfQ5>Zf@w}~$Aw*jSR`m;m^lO`xpHZjLfuZ9-)Q6DVWn^F7a
z^o0XT#`@KtxKDxM)n%9rk0$SFhp}&xzd%vyFN5C5mX|Zxz-_iFJD$(dLvnwPB}tUm
zw2J>MDK8j1bLyRt5xR&^-_!b(QLIy94izh|h=g*9W85j}A*CzMMYY+-uoTv#ICb35
z>??J@Xh%aB`nPZ&EFc0!zK<)84N&j0!hVd#&y9-j^eQJ}0tmCT`Ul@tE<}@?kXS~C
zk!r;Dz9Kzbb1rRsFugvv@~L}GZj5tTtN(J%MT^Ey8!eMaKFXH$R`Jl{L2Ym!9)@oP
z*18T`dWe4QZ$w~U2)-GGEnaH@YT70ds)4oPb^@RtJLeE*(VgwvZr1iVAE1Qt09=cL
zB=NBO|NjQyKi5HOx-yptz_Wg=Fd%JrK3w?1WWgIA0F|6M@h!D)S4OzZ){*|cD?BP`+DvfXz6yYZ|p4_D{Ry#q}6Wey~tbV4{!a|
zkXI$>eO;bE^j|+Mv16xa
z1Qrp@dhm!}{u`xfCh|a73;x8QkJ(_C+VW(mqryKVfLIBEOB<4^XG%8q)
zymd1}-jj{R?z$jhi&+TS$@6IR>%A~{qBp>Ph`YDPB^9>v>%D=;bu8g`65t{tYF?@j
z3aXzVFG-Rw6A$T8MndAhh*v--53YZ_@Vdos;i-KgpEs|Iuk~WiOj1UNeb_fgbXZbg9euGDar5@5XWWjvtTtCIjBr
z5tQrZ+^<4nFj}qb`}ZlhOI=K^;^95(5Nzylc>sA?giz0Y(cRr@DIt2Ehd?b0{zle0
zeCSg0C}Luo)mpi86Gg`O#0ll^r2#9l@~Iv*7Bi7(b!_tT!^=Da-0d!&m2&)810ods
zDNKS7K!%fqK=lat*iqt%!X|qBOA43*#JG5RWoyka8>52r3<4KZgh+H)sd8|z#P6G<
z1VU4VLTy?9b8k1{LZL#}XUN(=xd*Qr*}r23J?A$_@Y@mqqmGpYl@w+JF_vH}4GWO?
z101HwRrWn10<4Bgw6pXc|H)-HtB-6yi37udmQ{yw7Fp{@mi>xElo|0lMCtveU7a!=
zJCXd|CdxHg`!>4z&0Z$12SLmqD*An1q7yuSqPDYm>eEDHEn+g3YVMGg3=bZt
zqd_!d`nMh%HVRsp+X*IK@j3I;wbu6VIAShkZv#E=H`(<&q}ZaQ^u!-iYU#|%W4P{%&2il
zB!g9VxzUizxrD$^$H%CV3QQxpG^VijOOLL+JIevXn9!GGcniBa@>`N8lsI!F4?U2t
z-Z#<6r=DdGU7)S=K@UkCt7TmL<1)v0VIrD_wM-v9yihg|ZPEJ3F%L8pv0O`VqH>$o
zzg^VsQ`27%cUENa82d)0`|HUr>bnB>Ez1S!lv0@C77N7!9E4yF$D0KhP%P+6L3ew7WYfV%u$^<DxmsSmPBaJn(^dQ2|CRCmCOE#2z58B4LD2>DU65G9J
z)>B#J9%TR>X1#~|6~+FK)PGSu1;gsB&-^dmMuT`A|U?JZf~|Cn_qKHl_57-ycN
zD@8W_X>>yOwIIF0rzvs@k#W_}`^}e=YCpCxpveT^yr0{?-WA6lhq2T^6Zl$Z8u#Ce
z2yQAeKMEsZY&@qgSs=-w$~ZIQ5>q=s6IGwIQ)clMA}PvD6*e|b&EpE>f%4EPq!qTv
z>dDxFt$KD+E=f|EHn!jKj<4Fj=VhUPPY$`Hpu+MW!PHg?X@_08?l0c~c3nHf^z7YaByqzP@FjQXI4lAf
zMH@Zb=S6(e=djJfFfqCzSEs<%!rwCVtr&6TPhcy1u^9lW&{V+_K96}Nl+K>l!z6RV
ztDGU*^;J=3ZFo2vNl$}vXYn5-F%E!)%G7N;ch3%Ol~{Y0ojo=tO!lZE*zauY_~j}-
zmJx-|z4an9s}>3SE?dtxwWw?S<}WsS+^1eNY}@{IWeoYVQV?P_kcTv@b#XX;ipu4l
z9M}BCtdw0+Zi@KWql#~N`KR9VrP+$NNq`>V%gK?p6@z)Z?Z%&LLODkd7+-8*jluz;
z)QII#8(}lsOQQ9#)RRql6r|+aP5jCpw^wzbR$iujctw2uiN*)>PbVxk$D-_Rs1Oem
z7pwl@w~?b<-9Qv*UZ@N?mBf;r6Wd2FUD&N}aX`OdXM!4<13X(nn6E_NUC2<=nSw`!
zW%3dps#AHl!4Q9lw`EH>P3K|HZ3KPG&9a{owRSnu!`O~>_(hY+z0b_9cy*lDF{)p6
zx8-Zo!0%8|++NZhil4XFWNb}T6UD@Qv)s(=xznb6Z25$={`Bw-5OPQHg&@%8_;%HT
z!CPHDwB*v~lVXs!MYHhXGkV;m%O}};^Ur^yiuBAHp0Z@U&FQ^iW6Q@re3{prh`ms;pM@U3BI+_EZV9>X`p1yCxC>(cKL^
z-Gg`OZT)3}s!nNj_56&mG8(D}$Uo8Ioqz4n^#C_=1%a_X<^Z
zpHk0ufi)f>QY>QhJzgFPQhOW;UZ~S2MH;FsO;~vDdpGt7O;Vnl?pbKW@u5dA(PICM
z%(h5veGY>Q*2h)W>{&mJorWv|;zlZiCHWWahz)ad5hmDxa2Q~vjI@DTF+M{+r%9K2
zMb3k7+$Nj?&h0BRwU`(m`y?wXRj~JWNtJsajcYIjNzxyR9iTM_sE~l_j*B^pY#po*
zGR1qVVIwQ-;S%KZj4rw?;8^shBnw((`h{=#-|jYp%6BnEVyDFTW0VGpp3q3^I5Uw(
z%JGyB!F^{@`&_mYjPhH?Du=E`*l0-#-By-s=Gu`A-J7D^585*U^zJS_lnr@56$_kB
z!K7>{&ZEkYn5g|4?oL1J0T{csTk+PYspY|oEk$Met@G=Z&r|q=$?IC2BRC$3%XyU^
zDRIk!gbaV|u)UwIEBs|E{3I@{5IMXobEXWgD;rw|2jX_5Ma3M#SfN`v1J_07m|eo7
z16ib{ecN$Dn==Ryp5PF~9vB_?vFB4=au_b(PTTz?>}9*b^nbDdu&y>N8nfxn1zP3#
zHT_30;x-FfGXbWLHxO?4Q+Dtj@lC5^WqRC_8aJx=tiaXD8!J~9gY#RT4FziS!{E(W
zA4wn{#g?;xrw{oXAO^J8yi~Pj&4pvYOwffM^~+P=1CiFX(Z3(62DSKnCXoZ6_yAo5
zGV&x?7h49NzMr%BmlFeYl39N@M=uY=we>AmOsGSS71VI<&Pd3n`IvpR>r*5$5RLt-
z&_Sw}T)PUWa)6WWwc1;Mhqac`tjI2YqWvc^B;rIYmt2{pyn_RGkc7_8U_n|5x3}3z
zDfRPBs&v_|nVN9~L=~)ZH^GdguN;M(iUZ@w!%+F+)L$D9H@n~xX6J+*(@zcb)}7blGb|Dm}y!sE5KPVs4#8!wH8IdyZ6HR
zK%5O;r;-TYz4_{k!-26wnDr~o^9TxQ9lm?8%5}Z?dgUNqq6VFen<=}NGBNKZw`=K%
zad>#oJw;+>ctvB~dw>!-c3htEJIgsEty8
z>~j1m0G8y5?62;aEXwXeo%_c<=Ren?wfpK?PR#*3)j$@1M`c)n?FD&X653r;
zeHhr`=kxJrKalGi1G3ixjqU1Ky4?2B*jNHn6nn~L`X6D$8B{gE7-?Qa14VL&XyNR6
zf90H;J?T87^YiB-=T}R^U+I2HAM|J;k!Zmij>21(B?sSAx(fhdr(h1@m*}j0475LphLRz$=s#bT2M+R_}s
zj5IwgA28!CAM$QzS}N9?Y+nU+b;2MZ+vQbI>s_m5IcBg^>Kco4*|CiZVLcg(+mN<1
znRCj4%x}Yptn+G6q!0KxS)s!8rK)sj)@&fd9eEA5s80mM>{?Vh*%J9tsrD8Xi
zih^D{i{V^)x?7JO%se}i1h?w!;SiO!g#=Dw6kj@K3!63~A$Td}!tJw0qa4-~7*{>%n}^j;jv3EMiqkxzLQLuqlJkt2?(
zkwz2Pz{t(Twq2ICg^wyndN)3|7W&JH9)~`UKVyAAQ>{DM?7cH0|
zsZF(-32k7SH;BrfhJ=oMeV-*-L)&>*8RaOMZ`%nl?y_d`OgbhFv7bxOzn>~k$;uvRO`
z?jQT(t2E4+r|k@3Lu4!pw#}kdml*WT|1Pr957R^6CSg%GHoupY0~3DWGmx>DEN=WC
zW&m%gM6T9@EIcB(MFWCietkON1m+?*AMW&zCqsL(&w?kfaSksD0z&yG)xB;*yONdq
zFbpzu>!d-Iu>KKzze;qAkCYV9GH6_C9@IDg@nU*oyG2=fZL51>NxtW#7{6;t!S|6z
z#Xmb)j7)-TgZd_sI6oj(m*=4zoC`mbpk?i!mSSQOD>y37Epr@2q8?Qk3f=f|h>cH>
z(O+I%27jxn8>myQ2%K%RDzkCP+)nfig?I<
z^<+i=)GD@1;e#=`{71un+?XTZ*&mfvvN7lGip5hE_uya(14>T%Go9PEu?tcf#<^FvG!@IV<%;e@h!;w%HZ7^V>I_VE`t!^+M;-qw{Uoyj#Ze#@#Z$sM~j+@Ce!Jq<#4pp|}$iI;qZO|-e(Vl>WK&p(7v
z-f|_gO?r9z`#BvoO_NRu^^(8IicYB726&3ErCE+6pVQjkt)LZSwNqu`+3NRuyra3P
zX$vT~s*jHRF_2@a|ND1dFX@?MzCy6B6s}0J
zjNCWDRv=-?W&91WvscaqE>9@36tvXjZ0)yB1A)LTU?%!GOC{(Je7LF8G|hk4h$FRYzBYI!kw>Pw&ioug7cGH)vfgNWr
zWKcsP^w`T37goAs409g&3MjX27@g+O_2Gm0gKYdHkoZ^I_Sjf%;cCBgu`0PjU}t7M<#(R-yzde#DK%!r(ar4uXbp|Occ$Z8VPK;~;F
z;qZ1Y;R;)g{M1woM1>p-6r1R+fwUu^9G8=Q2f*6oIMd|U--z1N0@HAH>ITA590>B;nFJscxCawFRxtSTKa#+(0FzM-vD=jOlvGADkNVq63
zeX>!NP5w~PegvFm2XTu3Suvxc%w%KiWi1e)BbICBP_ukusITgftg`>Wbc+ng68?Y}
z`#;7v0%z#6@i<&`jOwShi#JVefxS@89Yh$8)7({R=C}G|*qLzYpFX_TLwYfBap2fr
ztEQHg0l2QY+uzD!cQ38tqo?lRO0ynjhgku6xrQ&_yxt>G(y~$NW_svD&fov>ZcL2M
zi)<3JAqRsqkO7$JxAlQEHh|0g#(lD4zHNe_@X(&-#x*94xwyM4`kmm8V4W(QMNUQL
z#WgMS$1MYdkobvlu&rPr^TbS17D77`(O)c9TJp2=QGWp&4L-Fd8>Zn3{W%&teP$q3
z{%}f20^{oT9$E?!L?YZ+wbeXfYB|k2f1P3fwR8koH@Mrx2sWHlt_H2*)NV40lap=T!W+8m_&KJI4Vz
z87eL@DYssnPw2e$i-6A*lI3!2HEAzfAqWUma~qsAcr9v*UtqR7@1UjCRbqp23H{2A
zL<-R8szWxur*5tEeJp5XD%8(mi&!@gxA9@Y;d^`U&j2te$d)~*8qkq2E-OpYSN`d<
zOG(mSco2rI}(SNd^PPUw{rJijTR)r
z3_>lBPl0HYPqXP;p-Y@O6+qCt%g*-r6%16K_-`+wln*t1E;~E>-#MHnRW6NqMmqQ8{%Wb+
z(|0t~inlHd(~JPto+IHg`ibeL$*8X;Cqu1%bQqfleh;CB78dqMo3@h=u(cYSk})T`
z5?8s9#UE+xWW>xBq5xs&wmo%Xt7}I9cG&7BH{?=0v!q)6z_DN1n&>ZpodT+n2S_|e
zT>x4!Y&Qxt3BXz1P%y|P9>`RcL!Cd?T++lOZo!8>8-x0L9sc3ZkW!;}JpW*R*uWDw
z6SM#HH1``HP(FP59{ybG2GQ}2e4M_;%u~BWSs{&Wtsa}XaeJ0j$5`zq&9qjjMT&WpYtT0TF*b$5cAmiSaSse(2O2i^U#kLvh+iQ;0DC`}#wX2(`l^
z{VC7WUe5uuVdC5KeNq3umHfMbY%rfaE{SM6j-65iKQG8ZW1ehas@pu{rX=SuI$H>0
z?KB!=COpT<$Xl@VS8X#}PgejYw
zdo<@L*~R&1RV;;Tza!?gAGolqNZJ@UB)X;&x6wj=VMjl9^QKBmyXszUOd2@S=hO#q
zxg(2JkG8~B{pYg7EU>747JE=?>(E`4j;b82}fE|o*~8`4eA#yS$fImzOyJ_BeU^=Z)y
z!pEVSeB}T7fB*FAUATHH+`lcrC&m59{dY3Vci(ci@dL2Ty0r?<8E>uEYldha-oTFbEq&=%3x4|KDPQmuc+8V-0^x
zvNE8hV9KRfyYpig+d3Zzm&!m5Gp+nx(}?5##rY3w|qy=
zs0Kphw9W3lk(imb4WQVFm-@dKeQUQcC8b9YFj?i%&#kHg9KADg^EthwIlz(Q3gD$G
zl0#Rn)Y*1KdV{(o|NDD2=tk~b7mB1*4U3%Wl1vj+QH6qgf5$imSo4pnp#r>f)Hc6e
z_^+b=pI?=!NAQ7^U^_|ojIXoJ7?%4_iN}TLQm=Cfg_iAfX=%v~k1SI!UNfGzsYw5z
zVew45YOy*JVKa|(vQoXr&xecKX!MgcUQ{kl{p2iMnAYXHYD7R%!H
zh9OdN#?YZWTg=?#F7Ag(_bnOvKzYj!KF-}Bwzs!8
zB#+(N*a<>}xB(TNu?OCt{nwh{(3#U~FdSqEkOH6OXN}d!bV*dkZvWq#B|IvoVkOV5fEqtF!O&-z_=7
zwKl0yZ)3>ZQFT1ZavI2<^7LPLJEicEdTq8{RBZC6NVR*h>Tzhs)buq+BcXRg|JdFA
zKkU7CRFm7bH>{$dB1DlUEh@x
zg({sOE!0rI$9wkP=iGOk_uO;dy}$qN7#SGw$yzIO%{9w!mi6CM);+G?Vb=*_5|aF)
zqA5DM#S!zi8vmC^$fY+wC8i5c4w{%a59&yvK3;P!F6G|pi7u|xYn(=pEn%=prssw*
z1nF^Z(J%+Sb$)6sO9Fzvws-^wa?xv>8H=z0A93%eOrZi^>tQmw;{*ps0|a>rvF3XV
zNx2=gE0v!Yz5km``DbU)k5gJgaxz}4v4C^o;nw5-@%i%?&AC+6RZaF`1*8BgNoSNL
za*U=V-LZM`;$_qK2(j%QD-n2l6=S8J2Z~o31
zVGf1scrrtXKBC6Xc5RheBs@rRPz89_h!U*)FY{jhjRpSxh~K!DX530g_`szSW&^k@
zrf3jdSv8b2Iq*tL)jIG{K0m8uoY?ay&qp;8rmJqRAUHB!Og2<*s$RyeYxK%R!AsRS
zO#hO6z)9<)OVyA6$CL8k#KixV&$M$S^u`_O85l~No8Q=2X4l=Nq^!;>s5iOxiix3r
zpMsulcST-aK5tM^jCVV+U%@+g=QIBq-q(i4In3+Q=y@?C-zmm_wvqq&-~2e`CHUqK
zIk?07=BXm35i#tz1m^qayJh7q;HCewB>caA#sA|!9s>$Ai5Y7DukF!)k9vO_I{ltX
zlA4Ju>0h-akrFyO6ZV+&_ug3rncGQt3+`Kc%nKJkL;j^<^&b)3ukwa5`}<1AMT6hD
z^FR9dKYQ43{?cU$5OkMhC6aGK_P1f-3xt)3C8(02i{PsU0
z%HlI%$p0nfKgFQ_!#(<6QvMZG{4ehPUsC=rDgVRM_kT*g|6gQfvX_H{gWXh+o8(`%
zKi6e-ldJRB-21QGbNoM){h#^OiCINh(7vJSuQNR^r}L<&aZv}VE8koBd*We*^948@
z4qTj^v-ysU%tcF0?e&Ubg7!ZL_5a;1_4D9XG1St66o{V-lKF$uUuq<*tk};lmn_Z2
z{u$C-)_1&+p*_JmOY~3S>i@)e`a5+y<&(X%dS>PRzA){YZ<~cU1P7LBo|YSQy!G2i&UYA+RAe5`$lyG3J{mK~$QV6?H1!jwgONw(?=uuYKaU
z$EuSAUau5@BHcl}i|tqEqJB3i%c%SLDYm-+l&W`1_-3QpLnP$`9XjnLaBUTQR0(?@
z%)4}!^RpE%spXokqHSh|Zokf0bgUv4_wY+y4c<~KJUS{W4%bWBuHV+Gu%t2V0!7qP
zVr@A@ie1s&Fb|K9Fb4x0c|B1i`#k)UjpA+zyuAyl
znCP#d(X0(w5-4ZY^kL&ocQ9Q`HQ_6-ci~0tWH^NII3YmAZv-|wJE$?_KSCTQU
zsv>L%+M8o#ncExVG*JK+W|5xdqj8~WV_RKOO%JY<;dF$ZzBlP0-Q*{WR
zon6RUsVy>1gec36Z+~ruJU^IWefUAVr}7$
zjyW-}t4j|%(lB4uVm~Rx#_yix_`WnfmLS~re>HEYvDQ{>ik&H1yRnh8Q-b}x<-?ok
z`st9yd94NFPUp?f;Z*WkaCn1#x2^H??!wUMSyt(SFBAbPITbgs;RB}+5RVWvpp3v&
zaoap@2&N&;;sFnh)8`9@0ygkfFPv-!ROPkFnAYW8$<8#y5B)`N=tBDH^CfkeYGox>
z@N$Cn@wXBOZ*%n@Fw6;hhqI!@RmcdB=yAUyyM;;52m@V^+TYf
zc7~)+5O*$dwb%{_zfW?xOtpBgm{*d8(|k<{M!qg5yR{Q;Mq?Ct`-^jXXkF{)K~9vRb-qPi8_!b6}5
zQqdoU0HdUa%oUiyjgSf~ru`-gRJ>(s5a_`qA3m{@!Mt~t!KeJpD)^Nbdl*S*RHY7m
z_0NYs7p4CprNKe-a&|oyi10vdTwFAl+2XrMMphFZ54_A$O2luhrQFch(~EEH3b8X0
z7O4WtlOun40vBCVF!m}@+bt_6iLTkP<`ooNw<}d!VE|G&_M8*93I>KJCxK$xM|Zq&
zPusUuETru1>lnp-z5}J_YjW&Yh-@%9Z6dJOeY;2l8@krddRGN^<64ueeP$cwR+pEr
z3U(t9amk-I2vMeuHKP`oak6oHS`iWZSt)Q~bv)kE(=%`hZkU^sL+&c?mJ}$=
z4#a<@uu4gyRK$fE0js(SKN6a~940y@>?}C8oKVR#$1;>xiHL^RN9x)kiRvzPnwlA(
zK!Z9tHfzg$H;1Q03e|J>cqJbiEMVIrQMpQQ
zbol4Z(0EBee05vM$YddV=8~G%RWfrL`29?KsJP`NpMc|^i*8S0i9<@ZOmQP>%}4waLn
zN$nim^9(W`)*+-0y*}Y#8Kh#-+tOCn?+Ah58|A3ePj=JtR=K>SeiBJ16Ff&k_$n49
zQv#`I_K)J#q*+c_^v;I%R%-m(Jb>mu)Y(KdvT~Uit>9UF;u1?v-&!I|Anv}tb;xF+
z;ly|G=tl+??If6RD@zq|cRGRu4Ad3bSC%P|!xU=Ou|Flf--e4+)l+*_&R$mUlAklJ
z0fQutmo65Y!8ULHsMV-{ZZ$|^4R;HGs_%AWD+`9DEf_6^b(*Og4d1Fe9Ri^}_^mpB
z1f9%aXx6THJVZd;jf{}U9wmGFL~@wJ?ox9Rs@g{N(%T&6MdxKBl}#UcSa}}V)YQ~1
zTt3dajCC6S5lY)#I^3Jz{evjA9no8uVSR{Bd>12ipW4;>n!YMY0Tf_yll
z7~5|GU+|Hy;#^ryc|C%stX@p-J)U_gcyXLqn@Mw=IUbx`Bs(j|Vn4ooY*oz{RvFS5
znchzfW>ijvxPOrmC&ZL>FJFZ^%j*`_T5D~Xn=`Dn|+%nPP7vD
z0zu%S8c$Gw;80iBN2>g(m$CbeOp4gGk{CnmoZ#EF;lV*mPHi4iqR+V7Jx7){B6cL8
za)N}6#q!f34hPh+VQC^ejgUm+^@B2ehn`Gh`#3o&aPw+d9M1X)wAGX114}o9
zki)&G%KP^lfF3x+Kmvv%h1J0P)getBL(BjW=}tlS&sSB0E_ncj8;17ENt@L=xB4?M
z0vl})QMm$rgp3%&twRY|_;7@HE-KmsFdFLB$P8C>ZEQs7un1BbNTLmVDG{WB29gM<
z(Sl{cK-*g>%da_!xj`HrOmqi63kdI*oANhZHNWOgetJT$4`h<>Gi~D6qDI!JlF%GB
zc3SkJ({e;~A%io$q`cW=Q#APc!`2k2UWny?J
zWuxQ#2OJy@eIc++Fb?(9Oi0{JFe0S9R&*Ka;N958ucaFuxs<=z{dj#M4ww^eZC%1X
zqp~KT2&A$IoIxt6hgFP&@P4=fpq0?~%E9+blo#fKBJp|HX2Z)TdaqtdSt_FpTdSbG
z7b8ZA#hLK+agR7{8v<}D>x;3FvU<&MT#|g`tJPIaaRm1B{jMKV92^AUub!kD!*C|jg@AQwpjAgC+sNRaJ7HlG%2(dAy8DdR
zE#}Q>UUv-{`btyW(@M|%+6Zu59AJ8JhU2DYhP3znrAvU_@Loo0)Ri2L<3&rqeCp4*
z(!^mO!vnh_DP>h!FY?5|Wx1EHZg0-SAILEZgt$++AXqM<>SSS{Ayu4(4JslC*{kE+%quy4S7nA)g=P*2PlRiX7+Y-1K}PvfOo^s%7
zarP~9c$qemL6x%h$ztrz%}_Daw1x|!nZmg)tBG9A($i9upie(>^jaIO%d{TpVuaXF
zIRsiKoZMlPsZup^>cSe+xLLN_Pe_{u9-0V*Wxl-#$SJ0De!&esy~Kw@NFeYBGE2bD
z$VtjU#$04B~8@8qIZQP3pVQc|MKMHBq1
z7I++^APP$FBOdvZe}Q7KAY(6`noK^041EL#*xTPjl&@8OKb7=Ex5MoR;9BAKTd^~M
zA8F`Q8Xzp-?7aR=93_a54-kz6O=;5(1tbr
zJr>ffX&y*r?vR`~Yw+HD5(!Xp^kSi^1j&Uf*uL3?)#d#1+cRn2E`uP)zHUS;!Ke6On_fLx)ReT>R@9E9L`q_!?Z~~mJbJ)du_$SqA$!!J
z!8Xefi`tP0aDbap#YJRg^(B>T9G=^vCcoxU7l)hN1OAvp8v^1|1=>6koaU#z|
z+nmu+MO*hsdzvG&L8AU%4}_DRdSA6JScoUeeAWKy?;zJ_$`6daVznP%8qpdLb8N-U
zM0`*2Bdo92KIlzJzB4&$lg01ydER?DvoAGR#ICLpIELduS$?umA6Cz02?8ptxT8mA5&x`(Xb
zH#=n?sMOHapaEP)gN*46his;`pM%y>4fW3nw-MX7R#^~?_yK|j;nP_e3)o;^IGjVg
zw73>6cx%zybnWf}d~~n33=+}!IMfOUauv?P3~Pv|J7k{@roTawQ*>vwR|s@xCDsgI
ztw&|anCbauZ*02_BpZD-vM3@~fqt+fWN|Gjl+_2{0kgp{r)ol3MPUH;uoj(G%#83#
z_R87$<=ru@%)|3Kd+nrj#!{R!9YRX$N$a1lDEx>B$7i7*5?tI?nKG9Nx6cN1n1&?K
z>uJQtwFNz^>O;Bg3_6~QBXK^%VkQ0YU*p>g+(9VlrQL^(hXTOp!UECuMPz8Nh$pf1
z9btYdG^S<=wM*Vmm;4S^^kwmWz|2wnq2klIu4j@Yn?}a8?RO}G=>d$s>6q^|!RVaz
zb)}xHBET&*)j%)!Zlv-v50exbu?(kKMODh{$;i01f~?`$U6}w?O?UmURyt6XNx<~?
zN`?-6^6HIzPOonTRAuR~d>!rPK6u~lxV$#tIl+2bk&8RQzm;~of(~4
z1&bu-b^I>a*L|0?=s=Bhz)%JK9_cabJ!fqc(wp;Lis@=k_hLL4pE-dyLASPr(Sy!>)
zCo^Jl3Cf9rh_g8Q2!OC%fd3S(756m_V)}C+)I(qzBe8)NMd78U5#mGTgC}06L(8L(
z3jF)_NlLumgn;&)_=4V{p;hrLexKWdWiUWAjoRzVX4c7)-paYAs*{UnMwADlIT2v%
z4U`zPpEc6WJK1Lw0CHS2aO?}}2pBuVkJEvUM_rMs<5EsYwe0CReF);#FFc}Rk!0Q*
zI;W#9fy7-JB4S@4y4AENV+*&~7TK;Hc2-Ox)yAa=YTItkO6tob
zVEk#_yB@Ovm(0Wx&E}Qk%m|qw^Wc*iVPt!*RjHFpelA&#z>4Sb<8topZjv{?Wkb&Z
zVh#($aQj1JM?pz|i>g_Kq_>B>2+!nmyE6s14ok$T>|R3EDLT>M3vy>i
z4S$k^`)n;y;w7tlg1s}W;knn80RQ6y;2SdKEjp9GKjgF*G*AOzy)AeiQu9fEkNsX)fQx3ey<^-jocwuCbKCnq<$Sr37NO`)yi!-41OYlydN`_SKy)IY8
zqsa%Bfy()}vov?&2?SjVbbgf{6>sk*6
z?Pzl5iDIor&achibYssYizdXHZR90d$~Uw(2Gj8F42kM}?_r-;T_9o%4J~_lzh`mL
z|4Lpb>WzF32bonLM>+q%qbx>mH3xMuT{Sga)jZc_k*XYMmy?T=Rg=_`6Wh-Z$xb<%
ziJD={haKC!j|Va`g*7;x1qB5I4W4T(W;#M&jmvT(t@kMql^z=t5sAu`R+sb=We{Mj
z7&Me$a8W%`d;yN&j4{$U+EFt=a)@+O+e}fTuI94l)(nrnplJ_R*oBsOB>s3wWh-?D
zoXuU@>UN-^r%kx)?{&Q+=uX`*?#Zc!Ppjt$+vC*)6kw$tkJ;EzL$v@G_>O3aWw`+*1+OK(EyP%DPXf4Y%svKa-Df
zh4u2#pg@C}gJIr;By|L1Ly9fXZD)5fmHNFCs#q}8%Q%U=%n5K3@o7Wjci2no7c!4%
zc*U#NirlwSdy_&$`sc@aK57$G*rrQ4s<9QADYX|xhE@Z+JP#+exwjzhP73N3!}v}T
z6sa>5K?8WJvAH&i3$j-Uw=-=owk-m*P2QoOrcrIzibvSMX(
z6)h+li(6HAb_
z8my^0tRE80Ig~UroC?HZI69m+(2g{O1#hU?UBLw+10zfpfZ3hQ$ZNChpZMs&K>www
zHViJ7xCZ_l93J`-JTWMqa|Evjl{x03+Qne^U($dPHmDLcOByqRiU?1+yNH^(@K>vO
zqO$wk6B{{`DXZLxfF%MlfkwpsbcPOCmH_DH;Yc)>)sr+t$>{^cjJx%$1$hXmX8`m*+W|wxdCI*M}1NofbT}A&~N07u!`z{TAaxN
zu#w74hG}cmyRmd>_smu}1fN~4QQmYk52y;9YMGd|6jbHJ
zP(2Mg>9y@Qz2ZUFE+srjty^sR$(LJ+1>E>p=l)VN)7*sr@sVkMYG_Dtnn
zKb*>B$LjIoWRk`Sns?VlfY9B8BT>!*Xt3Eo19&CXH2IyATpdKh1(?8aGnrQhk2ib<
z0B8*J*8THJ%xrt0j%X125yB=k^doCqm3}Zx4naj%qRFI5P@QGP#@GHsYOZ$hTP-JR
z8xbZbnx$I5Gt^XHOcdRXdS;%GjNSiE;^c59`f{eDg`Jg;0{nJq
zLH(SI*P0OPvnWft85NQkyW4oEX=b9^LMCIf%eKBIqS=&r%<@uC72Jx`7R
zvtRqZd`L$}rz2;?m`&H%PK>kI*5O@nn$Mi1*XTywWGBvAFj~f8d$bI-Z)LsVScEGO
zRxI{)ImV+P`J(w4iIF&ABK7Rt(&7@lU#GxkR`(Po3#H8iwS~BLQ2tELYF;@cRN{)k
zrFIfP&&KF}laA!Vug_>=X4@AXchwPf93pDBqO{+X9=&zt*NP}67FBx?8IL}z$kpVV
zS1lU>G`A4oN7b(CqmE@$e8OSn6}dGyZpB)4deIF(`^1tLi`M?@KK9cbZ2TEs59VPL
zehwR{5E%fDtuzxc0C@YgB5aeASl9#$48y{tN&FSyyY{k*3x%$OTw&Ip^V2+^<8eLf
z>n|2j$Gz|K0RxJ|$)zr9sFA9=pv^4@K;euKlMPuD#M)wr_NQ#Xc}3?WsZEFA;O*@K
zELqur_y)jvQNRX71e|n
z)2Pd38d|>(0Du`3NA+d7-nQ`7DGq3(d+aHw;Y4~J!s?dx2mj@<9
zl~=%(>*6)tnR*W-Id=VA8`Z%l5^TUNz26BT`>D8&{_gulWIQDrhctuDL*yYi8!fON
zNAM}CGjxtbw@{dPi4B~t0&c9$tLTV6j2nuf>L@$j$khNlyIPZ^-{~P)DXpJ#k8qt(
z`-R9+$a~~nxNfH?U^)%0yar&>s>n8lea)2+aO0_X
z4{?f-BrFY}JDvCk5w#XZJ#}k1phv;_bCw)7RL=A?YdZ?OOU&i