Create configuration from environment variables

Deserialize workflow from JSON string

Create test case from YAML data

Generate a single conversation round based on scenario

Generate prompt distillation training data. Args: input_file: Path to file containing sentences to classify (one per line)

Generate standalone HTML file with D3.js bar chart race animation. Args: animation_data: Dictionary from prepare_animation_data

OpenAI Images API. Uses gpt-image-1 if available, else dall-e-3.

Generate a comprehensive report of the ablation study Args: results: List of test results analysis:

Generate a summary report of evaluation results.

Generate and save evaluation report.

Generate evaluation report Args: output_file: Optional file path to save report Returns:

Generate evaluation report

生成多语言推理响应 Args: model: 训练好的模型 tokenizer: 分词器 reasoning_language: 推理使用的语言 user_prompt: 用户提问 max_n

Generate speech from text. Args: model: The loaded model processor: The processor text: Text to convert to speec

Generate speech for multiple texts.

Generate and log a summary of all results

Generate a comprehensive summary report

Generate a complete test case structure

Generate text without streaming

Generate text with streaming output while tracking attention, returning GenerationResult format Args: prompt: In

Generate text with token-by-token streaming and stop at EOS Args: prompt: Input prompt max_new_token

* Get current provider information * @returns {Object} Current provider information

Get all legal documents from local laws directory

Get all legal documents from local laws directory

Get API configuration from environment.

Get API key for the specified provider Args: provider: Provider name (defaults to LLM_PROVIDER)

Get content from archived webpage. Args: url: URL to retrieve timestamp: Wayback timestamp (YYYYMMDDhhmmss)

Get categories for Wikipedia article. Args: title: Article title language: Language code Returns: T

Get full Wikipedia article content. Args: title: Article title language: Language code Returns: Tex

Get historical version of Wikipedia article. Args: title: Article title date: Target date (YYYY/MM/DD) language:

Get links from Wikipedia article. Args: title: Article title language: Language code Returns: TextC

Get list of ArXiv subject categories. Returns: TextContent with categories

Convert cached data into AttentionStep objects

Compute bootstrap confidence intervals for Elo ratings. Args: battles: DataFrame with battle data func_compute_elo: Func

Get a specific test case by ID.

Get events from Google Calendar. Args: start_date: Start date (ISO format, defaults to today) end_date: End date (ISO fo

Return the capability of the model, a float between 0.0 and 1.0.

Get OpenAI client configuration

Get OpenAI client configuration

Get recent command history. Args: count: Number of recent commands Returns: Dic

Get cryptocurrency price information using CoinGecko API (free, no API key required). Args: symbol: Cryptocurrency symbol or ID

Get the current working directory. Returns: Dictionary with current directory path

Retrieve multiple documents by their IDs. Args: doc_ids: List of document IDs Returns:

Get configuration for the specified evaluator.

Get the current conversation history

Get detailed image metadata including EXIF data. Args: image_path: Path to image file Returns: TextContent

Get comprehensive information about the index

Get a visualization-friendly representation of the index

Get LLM configuration based on provider.

Read output non-blocking to avoid hanging.

Get detailed information about an ArXiv paper. Args: paper_id: ArXiv paper ID (e.g., '2301.07041') Returns:

Get recent conversation turns Args: limit: Maximum number of turns to return Returns:

Get detailed retrieval metrics for analysis

Get the current session ID

Get pipeline statistics. Returns: Statistics dictionary

Get store statistics.

Get stock price information. Args: symbol: Stock ticker symbol (e.g., AAPL, TSLA) interval: Data interval (1d, 1h, etc.)

Get OpenAI-format tool definitions

Get OpenAI-format tool definitions

Get user input with a nice prompt

Search Google using Custom Search API. Args: query: Search query num_results: Number of results (1-10) safe_sear

Return a friendly greeting for the given name.

Search for a pattern in files using grep-like functionality. Args: pattern: Regular expression pattern to search for dir

Handle special commands. Returns True if it was a command, False otherwise.

* Check if audio buffer has sufficient content for transcription * @param {Buffer} audioBuffer - Audio buffer to check * @returns {boolean} True

Index multiple documents at once

Index a contextual chunk in the retrieval pipeline

Index a chunk in the retrieval pipeline

Index a conversation turn in Dify Args: turn: Conversation turn to index

Index a document in the dense embedding service.

Index a document in the sparse embedding service.

Index documents into knowledge base

Index a collection of sample documents

Initialize the agent with optional MCP tools

Initialize the agent with optional MCP tools

* Initialize LLM provider based on configuration

* Initialize ASR provider based on configuration

* Initialize the Silero VAD ONNX model

Initialize the agent

Insert content at specific line in file. Args: file_path: File path content: Content to insert