Delete a memory item

Run a quick demo with a simple test case

Run a quick demo with sample data

Demonstrate complete workflow.

Detect communities in the knowledge graph.

Generate a tree structure of directory contents. Args: directory_path: Path to directory max_depth:

Display current configuration (hiding sensitive data)

Display a summary of all test cases. Args: show_full_titles: If True, show complete titles without truncation

Encode a single text into embeddings. Args: text: Input text to encode return_sparse: Whether to ret

Evaluate the agent's performance using accumulated experiences. Args: num_episodes: Number of episodes to evalua

Evaluate multiple test cases in batch. Args: agent_responses: Dictionary mapping test_id to agent response

Evaluate multiple test cases Args: test_ids: List of test IDs to evaluate (evaluates all if None) ca

Execute code in the specified language. Args: code: Code to execute language: Programming language

Execute a task with experience learning/application. Args: task: The task to execute Return

Execute a task using React pattern with tool calls and streaming support Args: task: The task/message from user

从 #### number 格式中提取答案

Extract and parse CSV file content. Args: file_path: Path to CSV file max_rows: Maximum rows to read Return

Extract content from DOCX file. Args: file_path: Path to DOCX file Returns: TextContent with extracted cont

Extract content from PPTX file. Args: file_path: Path to PPTX file Returns: TextContent with extracted cont

Fetch a webpage and convert HTML to text Args: url: URL of the webpage to fetch Returns:

Filter voting data based on various criteria (following official Chatbot Arena method). Args: df: Input DataFrame min_da

Find the best matching workflow for a given task. Args: task_description: Natural language description of the ta

Create from a basic ConversationChunk

Create workflow from dictionary

Create event from dictionary

Generate a semantically meaningful document ID from file name. Examples: - "宪法.md" -> "宪法" - "劳动法（2018-12-29

Generate evaluation report. Args: results: Dictionary of evaluation results output_file: Optional fi

Generate and save evaluation report

Generate text while tracking attention weights Args: prompt: Input prompt text max_new_tokens: Maxim

Get all available test cases

Get API key for the specified provider.

Get API key from environment

Get API key from environment

Get all test cases in a specific category.

Get OpenAI client configuration

Get surrounding context for a specific chunk Args: chunk_id: The chunk ID to get context for context

Get surrounding context for a specific chunk Args: chunk_id: The chunk ID to get context for context

Get conversation history in OpenAI format

Get default model for the specified provider Args: provider: Provider name (defaults to LLM_PROVIDER)

Retrieve the entire document from the knowledge base. Args: doc_id: Document ID Returns:

Retrieve the entire document from the knowledge base. Args: doc_id: Document ID Returns:

Get the dimension of the embeddings.

Get Excel file metadata. Args: file_path: Path to Excel file Returns: Dictionary with metadata

Get detailed information about a file. Args: file_path: Path to the file Returns:

Retrieve all chunks from a specific conversation Args: conversation_id: Conversation identifier test

Retrieve all chunks from a specific conversation Args: conversation_id: Conversation identifier test

Get only Layer 3 test cases (most complex)

Get the sample task for summarizing week1 and week2 projects

Get sample tasks for demonstration

Get service statistics.

Get agent status

Get detailed conversation histories for a specific test case

Get status of a specific timer. Args: timer_id: ID of the timer to check Returns: Dictionary with timer status

Get OpenAI function calling tool definitions Returns: List of tool definitions for OpenAI API

Get OpenAI function calling tool definitions Returns: List of tool definitions for OpenAI API

Get OpenAI-compatible tool schemas

Get current weather information for a location using Open-Meteo API. Args: location: City name for display purposes lati

Search for pattern in files (similar to Unix grep command) Args: pattern: Regular expression pattern to search f

Create hierarchical summaries of communities.

Index contextual chunks for both BM25 and semantic search. Educational Note: This demonstrates the dual indexing str

Index all files in a directory. Args: dir_path: Directory path extensions: File extensions to includ

Index all files in a directory. Args: dir_path: Directory path extensions: File extensions to includ

Index a document.

Index a document.

Index a document.

Index the GAIA validation file for experience retrieval. Args: validation_file: Path to gaia-validation.jsonl

Check if server is running

Search the knowledge base with a natural language query. Args: query: Natural language query string

Search the knowledge base with a natural language query. Args: query: Natural language query string

List all pending approval requests. Returns: Dictionary with list of pending requests

List all timers, optionally filtered by status. Args: status: Optional status filter (active, expired, cancelled) Return

Load a saved Q-table and parameters.

Load and preprocess Chatbot Arena voting data. Expected columns: - model_a: Identifier for first model - model_b: Identifier for

Load RAPTOR tree index from disk.

Load knowledge graph index from disk.

Load memory from storage

Load pre-generated randomized wiki for the specified environment Args: env: Environment name ('airline' or 'retail') Re

Load test cases from YAML files Args: category: Optional category filter (layer1, layer2, layer3)

Log embedding vector details for educational purposes.

Main function

Main function

Move or rename a file/directory. Args: source: Source path destination: Destination path

标准化数字格式：去除逗号、空格、LaTeX 符号等

Print CLI header

Print a section header