Run full evaluation

Run evaluation mode using the evaluation framework

Run complete email demo with learning and replay phases.

Run full comparison experiment. Args: rl_episodes: Number of episodes for RL training llm_episodes:

运行多个推理示例 Args: model: 训练好的模型 tokenizer: 分词器

Run a simple integration test

Run an interactive demonstration.

交互式模式 - 持续与 Agent 对话 Args: agent: WebSearchAgent 实例

Run interactive query mode

Run interactive query mode

Run interactive mode for testing.

Run an interactive evaluation session.

Run a simplified LLM demo with just a few episodes.

Run experiment with LLM-based in-context learning agent. Args: num_training_episodes: Number of episodes to trai

Run a performance test.

Run a quick demonstration

Run a quick demonstration

Run agent in a single mode Args: api_key: API key for Kimi mode: KV cache mode to use task: Custom task (optiona

单个问题模式 - 回答一个问题后退出 Args: agent: WebSearchAgent 实例 question: 要回答的问题

Run experiment with a single compression strategy Args: strategy: Compression strategy to test verbo

Run a single task with optional streaming

Run a single task with the agent Args: api_key: API key for the LLM provider task: Task description context_mode

Run a single ablation test Args: task: Task to execute context_mode: Context mode to test

Run a single test case.

Run a single test case Args: agent: User memory agent test_case: Test case definition

Run a single compression strategy Args: strategy: The compression strategy to test Returns:

Run a complete test case.

Run a single test case

Run a single test case

Run various test scenarios

Run all tests

Run tau-bench with ablation modifications

Main execution function with experience learning.

Replace PII values with [REDACTED] in the text Returns: - Sanitized text - Number of replacements ma

保存模型并可选择推送到 Hugging Face Hub Args: trainer: 训练好的 trainer 对象 output_dir: 输出目录 push_to_hub: 是否推送到 Hub hub_

Save individual chunk to document store immediately (compatible with tools.py)

Save document summary information to local store

Save document information to local store

Save document store to disk

Save document store to disk

Save the chunks and metadata to disk Args: path: Path to save index (uses config default if not specified)

Save the chunks and metadata to disk Args: path: Path to save index (uses config default if not specified)

Save results to JSON file

Save the ReAct trajectory with all steps Args: query: The initial query steps: List of ReAct steps

Save evaluation results to JSON Args: output_file: Output file path (defaults to timestamped file)

Save evaluation results to JSON Args: output_file: Output file path (defaults to timestamped file)

Save evaluation results to file

Save a trajectory to frontend/public/ with unique filename

Simple text similarity search Args: query: Search query documents: List of documents to search

Search for top-k similar items in the HNSW index.

Search ArXiv for academic papers. Args: query: Search query max_results: Maximum number of results sort_by: Sort

Search conversations using Dify vector search Args: query: Search query user_id: User identifier

Search using dense embeddings.

When using the search tool provided by Moonshot AI, you just need to return the arguments as they are, without any additional processing logi

Search a local knowledge base using simple text matching. Args: query: Search query knowledge_base_path: Path to knowled

Search for locations using Nominatim (OpenStreetMap) API (free, no API key required). Args: query: Location query (e.g., "Eiffel

Search Notion workspace or specific database. Args: query: Search query database_id: Optional specific database ID

Search for Points of Interest (POI) near a location using Overpass API (OpenStreetMap). Free, no API key required. Args: que

Search using sparse embeddings (BM25).

Search Wayback Machine for archived versions of a URL. Args: url: URL to search for year: Optional year to filter result

Search the web using Serper API Args: query: Search query num_results: Number of results to return

带上下文的搜索 Args: question: 用户问题 context: 额外的上下文信息 Returns: 答案

Search both contextual chunks and memory cards. Args: query: Search query top_k: Number of results

Interactively prompt the user to select an execution mode Returns: Selected mode string ('evaluation', 'interactive', or 'demo')

Let user select a compression strategy

Send a Discord message via webhook. Args: message: Message text to send webhook_url: Optional Discord webhook URL (uses defau

Set a recurring timer that repeats at intervals. Args: interval_seconds: Time between occurrences max_occurrences: Maximum nu

Create demo documents if they don't exist

Setup environment and check requirements

Setup environment and check requirements

Setup environment and directories.

Set up a colorful and informative logger for educational purposes. Args: name: Logger name level: Logging level (DEBUG,

Setup logging configuration.

Configure logging to file and console

Show results for a specific category

Show the optimal solution to the game.

Display help information

Reveal the hidden game mechanics.

Display the internal structure of the index

Show knowledge base statistics.

Display the main menu

Show main menu

Display the main menu

Show test results summary.

Display index statistics

Show knowledge base statistics.

Show performance statistics

Show system statistics

Simulate how messages are handled in different modes

Start the background memory processing thread

Stop the background memory processing thread

Stop system monitoring