### Setup RealtimeRunner Python

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/realtime/README.md

Configures and instantiates a RealtimeRunner with a starting agent and specific model settings, including voice and supported modalities for real-time communication.

```python
from agents.realtime import RealtimeRunner

runner = RealtimeRunner(
    starting_agent=agent,
    config={
        "model_settings": {
            "model_name": "gpt-4o-realtime-preview",
            "voice": "alloy",
            "modalities": ["text", "audio"]
        }
    }
)
```

--------------------------------

### Clone Repository and Install Dependencies (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/rag_tutorials/agentic_rag_with_reasoning/README.md

Instructions for cloning the project repository and installing necessary Python dependencies using pip. This is a standard setup process for Python projects.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd rag_tutorials/agentic_rag_with_reasoning
pip install -r requirements.txt
```

--------------------------------

### Run Static Voice Agent Example

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/README.md

Executes the static voice agent example. This is the recommended starting point for beginners to understand basic voice interaction.

```bash
cd static/
python agent.py
```

--------------------------------

### Setup Environment Bash Script

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/starter_ai_agents/ai_data_analysis_agent/README.md

This snippet provides bash commands to clone the project repository, navigate into the agent's directory, and install project dependencies using pip. Ensure you have Git and Python installed.

```bash
# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_data_analysis_agent

# Install dependencies
pip install -r requirements.txt
```

--------------------------------

### Install Beifong Dependencies and Demo Content (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/readme.md

This snippet outlines the steps to clone the Beifong repository, set up a Python virtual environment, install necessary dependencies, and install browser automation tools. It also includes an optional step to download demo content for initial setup.

```bash
git clone https://github.com/arun477/beifong.git
cd beifong

python -m venv venv
source venv/bin/activate

pip install -r requirements.txt

python -m playwright install

cd beifong
python bootstrap_demo.py
```

--------------------------------

### Run ADK Web Server

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/4_tool_using_agent/4_4_mcp_tools/README.md

Starts the ADK Web server from the root tutorials directory to run the examples. This is the primary command for executing the provided LLM applications.

```bash
# From the root tutorials directory
adk web
```

--------------------------------

### Install Dependencies and Run Quickstart (Cloud SDK)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/starter_ai_agents/web_scrapping_ai_agent/README.md

Installs project dependencies for the Cloud SDK version and sets the ScrapeGraph AI API key. It then runs the quickstart script to demonstrate the cloud-based scraping functionality.

```bash
cd scrapegraph_ai_sdk/
pip install -r requirements.txt
export SGAI_API_KEY='your-api-key'
python quickstart.py
```

--------------------------------

### Environment Setup with OpenAI API Key (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/README.md

This snippet shows how to set up your environment variables by creating a .env file and adding your OpenAI API key. Ensure this file is placed in each tutorial directory for the application to authenticate with the OpenAI API. The API key is essential for running any of the provided examples.

```bash
OPENAI_API_KEY=sk-your_openai_key_here
```

--------------------------------

### Start Beifong Application Services (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/readme.md

This snippet details how to activate the virtual environment and start the Beifong application. It emphasizes starting the main Python script first, especially for initial database setup, and activating the virtual environment in all terminals before launching services.

```bash
source venv/bin/activate
python main.py
```

--------------------------------

### Bash Commands for Project Setup

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/5_memory_agent/5_2_persistent_conversation_agent/README.md

These bash commands outline the steps to set up the project environment. It includes installing Python dependencies using pip and creating a .env file to store the Google API key, which is essential for running the application.

```bash
pip install -r requirements.txt
```

```bash
# Create a .env file with your Google AI API key
echo "GOOGLE_API_KEY=your_api_key_here" > .env
```

```bash
# Start the Streamlit app
streamlit run app.py
```

--------------------------------

### Install and Run Chatbot Application

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_llm_apps/chat_with_X_tutorials/streaming_ai_chatbot/README.md

Instructions to clone the repository, install Node.js dependencies, and start the development server for the AI chatbot application.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd advanced_llm_apps/chat_with_X_tutorials/chat_with_llms
npm install
npm run dev
```

--------------------------------

### Clone Repository and Install Dependencies (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_aqi_analysis_agent/README.md

Instructions to clone the project repository and install its Python dependencies using pip. This is a standard setup step for Python projects.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd ai_agent_tutorials/ai_aqi_analysis_agent
pip install -r requirements.txt
```

--------------------------------

### Start Beifong Frontend Development Server (Node.js)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/readme.md

Steps to set up and run the Beifong frontend in development mode. This involves navigating to the web directory, installing Node.js dependencies, and starting the development server. Requires Node.js and npm.

```bash
cd web
npm install
npm start
```

--------------------------------

### Start Beifong Backend Services (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/readme.md

Commands to start the main backend, scheduler, and chat workers for the Beifong application. The first run of the main backend may take a few minutes for setup. Requires Python and Redis.

```bash
cd beifong
python main.py
```

```bash
cd beifong
python -m scheduler
```

```bash
cd beifong
python -m celery_worker
```

```bash
redis-cli ping
```

--------------------------------

### Setup and Run Multimodal AI Design Agent Team Application

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/agent_teams/multimodal_design_agent_team/README.md

Instructions for setting up the development environment, installing dependencies, obtaining an API key, and running the Streamlit application. This includes cloning the repository, creating a virtual environment, installing requirements, and executing the main Python script.

```bash
# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd advanced_ai_agents/multi_agent_apps/agent_teams/multimodal_design_agent_team

# Create and activate virtual environment (optional)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Run the Application
streamlit run design_agent_team.py
```

--------------------------------

### Filesystem Agent Example - Python

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/4_tool_using_agent/4_4_mcp_tools/README.md

Connects to a filesystem MCP server using StdioServerParameters and demonstrates how to interact with the filesystem using agent commands. Requires the '@modelcontextprotocol/server-filesystem' package.

```python
# Connect to filesystem MCP server
toolset = MCPToolset(
    connection_params=StdioServerParameters(
        command='npx',
        args=['-y', '@modelcontextprotocol/server-filesystem', '/path/to/folder']
    )
)

# Ask agent to use filesystem tools
# "List files in the current directory"
# "Read the contents of sample.txt"
```

--------------------------------

### Run Context Example

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/5_context_management/README.md

Executes a Python asynchronous example demonstrating context management. It requires the asyncio library.

```python
import asyncio
from agent import context_example

# Test context management
asyncio.run(context_example())
```

--------------------------------

### Clone Repository and Setup Environment

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/starter_ai_agents/ai_startup_trend_analysis_agent/README.md

Instructions for cloning the project repository and setting up a Python virtual environment for the AI Startup Trend Analysis Agent.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git 
cd awesome-llm-apps/ai_agent_tutorials/ai_startup_trend_analysis_agent

# For macOS/Linux
python -m venv venv
source venv/bin/activate

# For Windows
python -m venv venv
.\venv\Scripts\activate
```

--------------------------------

### Install Voice Dependencies with Pip

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/static/README.md

Installs the necessary OpenAI Agents package with voice capabilities along with required audio and numerical processing libraries. This is a prerequisite for running the voice agent example.

```bash
pip install 'openai-agents[voice]'
pip install sounddevice numpy soundfile librosa
```

--------------------------------

### Set Up Environment Variables

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/static/README.md

Copies an example environment file and instructs the user to edit it with their OpenAI API key. This step is crucial for authentication with the OpenAI API.

```bash
cp env.example .env
# Edit .env and add your OpenAI API key
```

--------------------------------

### Navigate to Project Directory (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/README.md

After cloning the repository, this command navigates you into a specific project's directory, such as 'starter_ai_agents/ai_travel_agent'. You need to be in the correct directory to install dependencies and run the application.

```bash
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent
```

--------------------------------

### Verify ADK Installation

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/adk_yaml_examples/multi_agent_web_research_team/README.md

Checks if the Google ADK command-line interface is installed and accessible by displaying its version. This helps confirm the setup.

```bash
adk --version
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/agent_teams/ai_legal_agent_team/README.md

This code snippet demonstrates the commands to set up the project environment. It includes cloning the repository, navigating to the project directory, and installing all necessary Python dependencies listed in the requirements.txt file.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd advanced_ai_apps/multi_agent_apps/agent_teams/ai_legal_agent_team
pip install -r requirements.txt
```

--------------------------------

### Google ADK Crash Course - Starter Agent (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/README.md

This snippet demonstrates the core concepts of the Google ADK for building starter agents. It covers model-agnostic design (compatible with OpenAI, Claude), structured outputs using Pydantic, and integrating various tools.

```python
# Example placeholder for Google ADK starter agent concepts
# Actual code would involve initializing an agent, defining tools, and setting up callbacks.

# from google.generativeai.agent import Agent
# from pydantic import BaseModel

# class SearchQuery(BaseModel):
#     query: str

# def search_tool(query: str):
#     # Implementation for search functionality
#     pass

# agent = Agent(
#     tools=[search_tool],
#     callbacks=None, # Add callback handlers here
#     memory=None # Add memory configuration here
# )

# agent.run("What is the capital of France?")
```

--------------------------------

### Run Manual Conversation Example (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/4_running_agents/4_2_conversation_management/README.md

Executes the manual conversation management example. This requires the OpenAI API key to be set in the .env file and the openai-agents SDK to be installed.

```python
import asyncio
from agent import manual_conversation_example, session_conversation_example

# Test manual conversation management
asyncio.run(manual_conversation_example())

```

--------------------------------

### Voice Pipeline Setup with SingleAgentVoiceWorkflow

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/static/README.md

Initializes a VoicePipeline using a SingleAgentVoiceWorkflow. This setup is suitable for straightforward, single-agent voice interactions. Dependencies include the OpenAI Agents SDK with voice support.

```python
pipeline = VoicePipeline(
    workflow=SingleAgentVoiceWorkflow(agent, callbacks=WorkflowCallbacks())
)
```

--------------------------------

### Run Agent Examples (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/7_sessions/7_1_basic_sessions/README.md

Executes example functions for in-memory and persistent sessions using the asyncio library. Requires an OpenAI API key set in the .env file.

```python
import asyncio
from agent import in_memory_session_example, persistent_session_example

# Test in-memory sessions
asyncio.run(in_memory_session_example())

# Test persistent sessions
asyncio.run(persistent_session_example())
```

--------------------------------

### Set Up API Key

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/6_callbacks/6_2_llm_interaction_callbacks/README.md

Creates a .env file to store sensitive API keys, such as the GOOGLE_API_KEY. This is a common practice for managing environment variables.

```bash
echo "GOOGLE_API_KEY=your_api_key_here" > .env
```

--------------------------------

### Clone Repository and Install Dependencies (Local)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/starter_ai_agents/web_scrapping_ai_agent/README.md

Clones the project repository from GitHub and installs the necessary Python dependencies for the local web scraping agent. This is the initial setup step for the local version.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/web_scrapping_ai_agent
pip install -r requirements.txt
```

--------------------------------

### Setup Streaming Pipeline with VoiceCallbacks (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/streamed/README.md

Demonstrates how to initialize a voice pipeline using SingleAgentVoiceWorkflow and StreamingWorkflowCallbacks for real-time event monitoring. Dependencies include the OpenAI Agents SDK.

```python
from openai_agents.voice import VoicePipeline, SingleAgentVoiceWorkflow, StreamingWorkflowCallbacks

# Assuming 'agent' is a pre-configured agent object
pipeline = VoicePipeline(
    workflow=SingleAgentVoiceWorkflow(agent, callbacks=StreamingWorkflowCallbacks())
)
```

--------------------------------

### Basic Agent Handoff Setup in Python

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/8_handoffs_delegation/README.md

Demonstrates the basic setup of an agent handoff. It involves creating individual agents and then configuring a 'Triage Agent' to handoff to them. This automatically creates tools for each specified agent.

```python
from agents import Agent, handoff

billing_agent = Agent(name="Billing Agent")
support_agent = Agent(name="Support Agent")

triage_agent = Agent(
    name="Triage Agent",
    handoffs=[billing_agent, support_agent]  # Creates tools automatically
)
```

--------------------------------

### Basic Automatic Tracing Example (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/10_tracing_observability/10_1_default_tracing/README.md

An example showcasing basic automatic tracing. It runs an agent with a prompt and prints a link to the trace on the OpenAI platform using the obtained trace ID. No explicit tracing setup is needed.

```python
# Tracing happens automatically - no setup required!
result = await Runner.run(agent, "Explain machine learning")
print(f"View trace: https://platform.openai.com/traces/{result.run_id}")
```

--------------------------------

### Install Dependencies and Set Up

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_ai_agents/multi_agent_apps/ai_domain_deep_research_agent/README.md

Installs project dependencies and adds necessary Composio tools for integration with Google Docs and Perplexity AI. This setup is crucial for the agent's functionality, enabling it to interact with external services for research and report generation.

```bash
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd advanced_ai_agents/single_agent_apps/ai_domain_deep_research_agent
pip install -r requirements.txt
composio add googledocs
composio add perplexityai
```

--------------------------------

### Bash: Set up project environment

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/4_tool_using_agent/4_2_function_tools/README.md

Sets up the project environment by navigating to the correct directory, copying an environment template, and instructing the user to add their Google AI API key.

```bash
cd 4_2_function_tools

# Copy the environment template
cp env.example .env

# Edit .env and add your Google AI API key
# Get your API key from: https://aistudio.google.com/
```

--------------------------------

### Run Streamlit App

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/rag_tutorials/autonomous_rag/README.md

Launches the AutoRAG Streamlit application. This command requires Streamlit to be installed and will start the web server for the application.

```bash
streamlit run autorag.py
```

--------------------------------

### Set Up Environment Variables

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/1_starter_agent/1_personal_assistant_agent/README.md

Copies an example environment file and instructs the user to add their OpenAI API key. This is crucial for authenticating with the OpenAI API.

```bash
cp ../env.example .env
# Edit .env and add your OpenAI API key
```

--------------------------------

### Start Session and Handle Events Python

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/realtime/README.md

Initiates a real-time session using the configured runner and processes events asynchronously, such as printing audio transcripts as they are completed.

```python
session = await runner.run()

async with session:
    async for event in session:
        if event.type == "response.audio_transcript.done":
            print(f"Assistant: {event.transcript}")
```

--------------------------------

### Setup and Run Medical Imaging Agent (Bash)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/starter_ai_agents/ai_medical_imaging_agent/README.md

This snippet outlines the steps to set up and run the Medical Imaging Diagnosis Agent. It includes cloning the repository, navigating to the project directory, installing Python dependencies, and running the Streamlit application. Ensure you have Python and pip installed.

```bash
# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd ai_agent_tutorials/ai_medical_imaging_agent

# Install dependencies
pip install -r requirements.txt

# Run the Application
streamlit run ai_medical_imaging.py
```

--------------------------------

### Setup Google API Key

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/google_adk_crash_course/6_callbacks/6_1_agent_lifecycle_callbacks/README.md

Configures the Google API key by creating a .env file. This key is essential for interacting with Google services used by the application.

```bash
# Create .env file
echo "GOOGLE_API_KEY=your_api_key_here" > .env
```

--------------------------------

### Chat API Initial Response

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_llm_apps/chat_with_X_tutorials/streaming_ai_chatbot/README.md

Example JSON response from the chat API indicating that the message has been received and the AI is starting to respond. It includes a conversation ID, a status message, and the current status.

```json
{
  "conversationId": "uuid-v4",
  "message": "Message received, AI is responding...",
  "status": "streaming"
}
```

--------------------------------

### Run Basic Sessions Example

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/7_sessions/README.md

Executes a Python script to test basic session functionality. This script demonstrates fundamental interactions with the agent and session.

```bash
python 7_1_basic_sessions/agent.py
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/mcp_ai_agents/multi_mcp_agent/README.md

Example .env file content for setting up API keys required by the assistant. Includes OpenAI, GitHub, and Perplexity API keys.

```env
OPENAI_API_KEY=your-openai-api-key
GITHUB_PERSONAL_ACCESS_TOKEN=your-github-token
PERPLEXITY_API_KEY=your-perplexity-api-key
```

--------------------------------

### Run Qdrant Vector Database - Bash

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/advanced_llm_apps/llm_apps_with_memory_tutorials/local_chatgpt_with_memory/README.md

Installs and starts the Qdrant vector database locally using Docker. Qdrant is used for storing and retrieving user memory embeddings.

```bash
docker pull qdrant/qdrant
docker run -p 6333:6333 qdrant/qdrant
```

--------------------------------

### Run memory operations examples in Python

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/7_sessions/7_2_memory_operations/README.md

Executes Python scripts to demonstrate basic memory operations and conversation corrections. It requires the OpenAI Agents SDK to be installed and the environment variables to be set.

```python
import asyncio
from agent import basic_memory_operations, conversation_corrections

# Test memory operations
asyncio.run(basic_memory_operations())

# Test conversation corrections
asyncio.run(conversation_corrections())
```

--------------------------------

### Run Realtime Voice Agent Example

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/ai_agent_framework_crash_course/openai_sdk_crash_course/11_voice/README.md

Executes the realtime voice agent example. This option is for ultra-low latency voice processing.

```bash
cd realtime/
python agent.py
```

--------------------------------

### OpenAI Agents SDK Crash Course - Starter Agent (Python)

Source: https://github.com/shubhamsaboo/awesome-llm-apps/blob/main/README.md

This snippet illustrates key features of the OpenAI Agents SDK for creating starter agents. It highlights function calling, structured outputs, built-in and third-party tool integrations, and memory management.

```python
# Example placeholder for OpenAI Agents SDK starter agent concepts
# Actual code would involve defining tools, setting up an agent, and handling function calls.

# from openai import OpenAI
# from pydantic import BaseModel

# class WeatherInput(BaseModel):
#     location: str

# def get_weather(location: str):
#     # Implementation for fetching weather data
#     return f"The weather in {location} is sunny."

# client = OpenAI()

# agent = client.beta.assistants.create_from_tool(
#     name="WeatherAssistant",
#     tools=[{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}}}],
#     # Add memory, callbacks, and other configurations here
# )

# thread = client.beta.threads.create()
# message = client.beta.threads.messages.create(
#     thread.id,
#     role="user",
#     content="What is the weather in London?"
# )
# run = client.beta.threads.runs.create(thread.id, assistant_id=agent.id)

```