Quick start demonstration

Main function with command-line argument support

Main entry point.

Run all tests.

Main entry point for the experiment.

Main menu for the demo.

Main test runner

Run all tests

Quick start demonstration

独立运行示例，演示基本用法

主函数

主函数 Args: api_key: 可选的 API key

运行所有示例

Main demonstration

Run all demos

Main entry point

Run the example client.

Run all tests.

Run all tests.

Run all language tests.

Run the MCP server.

Run all tests.

Run all examples.

Main entry point

Main entry point

Run a simple demo of the event-triggered agent

Main example function

Main entry point

Generate all remaining test cases

Main entry point.

Run all UI improvement demonstrations

Run the demonstration

Run all tests

Main entry point

Main entry point

Run all logging tests

Main function with command-line argument support

Run all tests.

Run the server.

Run the demonstration.

Main function

Main function for standalone chunking and indexing

Quick demonstration of contextual retrieval

Main function

Run the interactive demo

Main evaluation function

Run a quick demo of the service.

Main entry point.

Run all tests

Run the complete demo

Main function for standalone chunking and indexing

Main function

Main quickstart function

Run all tests

Main function

Main evaluation function

Run all quickstart tests

Main entry point

Run all demos

Run all UI improvement demonstrations

Run the demonstration

Run all tests

Main entry point

Main entry point

Run all logging tests

Make a GPT-5 request using the exact format from the Go implementation This matches the GPT5OpenRouterRequest structure from the Go code

Manage advanced memory cards

Monitor a website and notify on changes. Args: url: Website URL to monitor check_interval: Check interval in

Optimize DataFrame memory usage by downcasting numeric types. Args: df: Input DataFrame Returns: Optimized

Create a parameterized copy of this workflow with specific values. Args: parameters: Dictionary mapping paramete

Parse command line arguments.

Parse the final answer from the model response. For Thinking models, extract from <think>...</think> tags or after them.

Parse and understand image content. Args: image_path: Path to image file or URL use_llm: Whether to use LLM for image un

Extract the language label from model response.

Parse page range string into list of page numbers. Args: page_range: String like "1-5" or "1,3,5" or "1-3,7,9-11" total_

Download and parse a PDF from URL or local file Args: url: URL or file path of the PDF to parse

Parse tool calls from agent response using Qwen3 format

Parse and extract information from video files. Args: video_path: Path to video file or URL extract_frames: Whether to e

Perform various search queries to demonstrate the engine

Phase 1: Learn how to send an email.

Phase 2: Replay learned workflow with different parameters.

Let the user play the game manually.

Plot static leaderboard bar chart. Args: leaderboard_data: List of (model, rating, matches, wins) tuples top_n: Number o

Plot distribution of ratings across all models. Args: leaderboard_data: List of (model, rating, matches, wins) tuples sa

Plot heatmap of win rate matrix. Args: win_rate_df: DataFrame with win rates (rows beat columns) top_n: Number of models

Predict win rates between all model pairs using Elo ratings. Args: elo_ratings: Dictionary of model names to Elo ratings