tooluniverse.llm_clients 模块

class tooluniverse.llm_clients.BaseLLMClient

基类：object

test_api()

infer(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

infer_stream(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

默认流式实现将回退到常规推理。

class tooluniverse.llm_clients.AzureOpenAIClient

基类：BaseLLMClient

DEFAULT_MODEL_LIMITS: Dict[str, Dict[str, int]] = {'embedding-ada': {'context_window': 8192, 'max_output': 8192}, 'gpt-4.1': {'context_window': 1047576, 'max_output': 32768}, 'gpt-4.1-mini': {'context_window': 1047576, 'max_output': 32768}, 'gpt-4.1-nano': {'context_window': 1047576, 'max_output': 32768}, 'gpt-4o': {'context_window': 128000, 'max_output': 16384}, 'gpt-4o-0806': {'context_window': 128000, 'max_output': 16384}, 'gpt-4o-1120': {'context_window': 128000, 'max_output': 16384}, 'gpt-4o-mini-0718': {'context_window': 128000, 'max_output': 16384}, 'o3-mini': {'context_window': 200000, 'max_output': 100000}, 'o3-mini-0131': {'context_window': 200000, 'max_output': 100000}, 'o4-mini': {'context_window': 200000, 'max_output': 100000}, 'o4-mini-0416': {'context_window': 200000, 'max_output': 100000}, 'text-embedding-3-large': {'context_window': 8192, 'max_output': 8192}, 'text-embedding-3-small': {'context_window': 8192, 'max_output': 8192}}

__init__(model_id, api_version, logger)

test_api()

infer(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

infer_stream(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

默认流式实现将回退到常规推理。

class tooluniverse.llm_clients.GeminiClient

基类：BaseLLMClient

__init__(model_name, logger)

test_api()

infer(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

infer_stream(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

默认流式实现将回退到常规推理。

class tooluniverse.llm_clients.OpenRouterClient

基类：BaseLLMClient

OpenRouter 客户端，使用带有自定义基础 URL 的 OpenAI SDK。支持来自 OpenAI、Anthropic、Google、Qwen 及众多其他提供商的模型。

DEFAULT_MODEL_LIMITS: Dict[str, Dict[str, int]] = {'anthropic/claude-sonnet-4.5': {'context_window': 1000000, 'max_output': 16384}, 'google/gemini-2.5-flash': {'context_window': 1000000, 'max_output': 65536}, 'google/gemini-2.5-pro': {'context_window': 1000000, 'max_output': 65536}, 'openai/gpt-5': {'context_window': 400000, 'max_output': 128000}, 'openai/gpt-5-codex': {'context_window': 400000, 'max_output': 128000}}

__init__(model_id, logger)

test_api()

使用最少的令牌测试 API 连接。

infer(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)

使用 OpenRouter 执行推理。

class tooluniverse.llm_clients.VLLMClient

基类：BaseLLMClient

__init__(model_name, server_url, logger)

test_api()

infer(messages, temperature, max_tokens, return_json, custom_format=None, max_retries=5, retry_delay=5)