Initialize the agent Args: api_key: API key for Moonshot/Kimi mode: KV cache optimization mode

Initialize the sanitization agent

Initialize the context compressor Args: strategy: Compression strategy to use api_key: API key for L

Initialize the research agent Args: api_key: API key for Moonshot/Kimi compression_strategy: Strateg

Initialize the strategy runner Args: log_dir: Directory to save log files

Initialize the experiment runner Args: api_key: API key for Kimi/Moonshot

Initialize web tools

Initialize the agent with Qwen3 model Args: model_name: Hugging Face model name device: Device to ru

Initialize with a model that supports tool calling

Initialize using Ollama's OpenAI-compatible API This provides better compatibility with tool calling

Initialize the agent with vLLM server connection Args: api_base: Base URL for vLLM server api_key: A

Initialize server manager with configuration

Initialize with automatic backend detection Args: backend: Force a specific backend ('vllm', 'ollama', or None f

Initialize the agent Args: api_key: API key for the LLM provider provider: LLM provider ('kimi' for

Initialize LLM agent with Kimi K2 API. Args: api_key: Kimi API key (or set MOONSHOT_API_KEY env var)

Initialize experiment runner.

Initialize Q-learning agent. Args: learning_rate: Alpha parameter for Q-value updates discount_facto

Initialize DQN agent with neural network. Note: Simplified implementation for demonstration.

Initialize the agent Args: api_key: API key for the LLM provider context_mode: Context mode for abla

Initialize test suite Args: api_key: API key for the LLM provider provider: LLM provider to use

初始化 Agent Args: api_key: Kimi API key (如果不提供，从环境变量获取) base_url: API 基础 URL

Initialize the GPT-5 agent with OpenRouter API Args: api_key: OpenRouter API key base_url: OpenRoute

Initialize the agent chain Args: agent: GPT5NativeAgent instance

Initialize test suite

Initialize the CLI

Initialize execution tools with LLM helper.

Initialize executor.

Initialize external tools with LLM helper.

Initialize the LLM client based on configuration.

Initialize file tools with LLM helper.

Initialize the client Args: server_url: URL of the event server

Initialize the event-triggered agent Args: api_key: API key for the LLM provider provider: LLM provi

Initialize the evaluator with specified LLM.

Initialize the batch evaluator.

Initialize the framework. Args: test_cases_dir: Directory containing test case YAML files

Initialize the indexer Args: config: Index configuration

Initialize the evaluator Args: config: Configuration object

Initialize the agent Args: indexer: The memory indexer with loaded conversations config: Configurati

Initialize memory tools Args: indexer: The memory indexer instance

Initialize the chunker Args: config: Chunking configuration

Initialize the interactive evaluator

Initialize LOCOMO benchmark Args: dataset_path: Path to LOCOMO dataset

Initialize the background memory processor Args: user_id: Unique user identifier api_key: API key (d

Initialize the agent Args: user_id: Unique user identifier api_key: API key (defaults to env based o

Initialize conversation history manager Args: user_id: User identifier

Initialize Dify client

Initialize simple embedding search

Initialize the conversational agent Args: user_id: Unique user identifier api_key: API key (defaults

Initialize the reranker. Args: model_name: HuggingFace model name device: Device to use (mps for Mac, cuda fo

Initialize the contextual chunker. Args: chunking_config: Configuration for chunking parameters llm_

Initialize the agent

Initialize contextual agent. Args: config: Configuration object kb_tools: Contextual knowledge base

Initialize contextual knowledge base tools. Args: config: Knowledge base configuration use_contextua