🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
Auto-update documentation after merge
camel-docs-bot390fe286b93d
diff --git a/docs/mintlify/reference/camel.models.aiml_model.mdx b/docs/mintlify/reference/camel.models.aiml_model.mdxindex f263dfb3d..a24abc416 100644--- a/docs/mintlify/reference/camel.models.aiml_model.mdx+++ b/docs/mintlify/reference/camel.models.aiml_model.mdx@@ -18,6 +18,7 @@ AIML API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The URL to the AIML service. If not provided, :obj:`https://api.aimlapi.com/v1` will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.aiml_model.AIMLModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.anthropic_model.mdx b/docs/mintlify/reference/camel.models.anthropic_model.mdxindex 3b6ebd37d..b2d3565c1 100644--- a/docs/mintlify/reference/camel.models.anthropic_model.mdx+++ b/docs/mintlify/reference/camel.models.anthropic_model.mdx@@ -18,6 +18,7 @@ Anthropic API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Anthropic service. (default: :obj:`https://api.anthropic.com/v1/`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`AnthropicTokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.anthropic_model.AnthropicModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.aws_bedrock_model.mdx b/docs/mintlify/reference/camel.models.aws_bedrock_model.mdxindex fdba95d19..ce9f1b9ad 100644--- a/docs/mintlify/reference/camel.models.aws_bedrock_model.mdx+++ b/docs/mintlify/reference/camel.models.aws_bedrock_model.mdx@@ -19,6 +19,7 @@ AWS Bedrock API in a unified OpenAICompatibleModel interface.- **url** (str, optional): The url to the AWS Bedrock service.- **token_counter** (BaseTokenCounter, optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.- **References**:- **https**: //docs.aws.amazon.com/bedrock/latest/APIReference/welcome.html@@ -34,7 +35,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.azure_openai_model.mdx b/docs/mintlify/reference/camel.models.azure_openai_model.mdxindex faeba4bb3..eecf690b5 100644--- a/docs/mintlify/reference/camel.models.azure_openai_model.mdx+++ b/docs/mintlify/reference/camel.models.azure_openai_model.mdx@@ -22,6 +22,7 @@ Azure OpenAI API in a unified BaseModelBackend interface.- **azure_ad_token_provider** (Optional[AzureADTokenProvider], optional): A function that returns an Azure Active Directory token, will be invoked on every request. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.- **References**:- **https**: //learn.microsoft.com/en-us/azure/ai-services/openai/@@ -41,7 +42,9 @@ def __init__(api_version: Optional[str] = None,azure_deployment_name: Optional[str] = None,azure_ad_token_provider: Optional['AzureADTokenProvider'] = None,- azure_ad_token: Optional[str] = None+ azure_ad_token: Optional[str] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.base_model.mdx b/docs/mintlify/reference/camel.models.base_model.mdxindex 40e30a733..92738c10f 100644--- a/docs/mintlify/reference/camel.models.base_model.mdx+++ b/docs/mintlify/reference/camel.models.base_model.mdx@@ -48,6 +48,7 @@ It may be OpenAI API, a local LLM, a stub for unit tests, etc.- **url** (Optional[str], optional): The url to the model service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`)<a id="camel.models.base_model.BaseModelBackend.__init__"></a>@@ -61,7 +62,8 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3):```diff --git a/docs/mintlify/reference/camel.models.cohere_model.mdx b/docs/mintlify/reference/camel.models.cohere_model.mdxindex 31e8f0b4b..ccf742b0a 100644--- a/docs/mintlify/reference/camel.models.cohere_model.mdx+++ b/docs/mintlify/reference/camel.models.cohere_model.mdx@@ -17,7 +17,7 @@ Cohere API in a unified BaseModelBackend interface.- **api_key** (Optional[str], optional): The API key for authenticating with the Cohere service. (default: :obj:`None`)- **url** (Optional[str], optional): The url to the Cohere service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)-- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.cohere_model.CohereModel.__init__"></a>@@ -31,7 +31,8 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.crynux_model.mdx b/docs/mintlify/reference/camel.models.crynux_model.mdxindex d5b0edc74..68e816dc6 100644--- a/docs/mintlify/reference/camel.models.crynux_model.mdx+++ b/docs/mintlify/reference/camel.models.crynux_model.mdx@@ -18,6 +18,7 @@ Constructor for Crynux backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the Crynux service. If not provided, "https://bridge.crynux.ai/v1/llm" will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.crynux_model.CrynuxModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.deepseek_model.mdx b/docs/mintlify/reference/camel.models.deepseek_model.mdxindex d502c9e10..3dbdb4f68 100644--- a/docs/mintlify/reference/camel.models.deepseek_model.mdx+++ b/docs/mintlify/reference/camel.models.deepseek_model.mdx@@ -18,6 +18,7 @@ DeepSeek API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the DeepSeek service. (default: :obj:`https://api.deepseek.com`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.- **References**:- **https**: //api-docs.deepseek.com/@@ -33,7 +34,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.gemini_model.mdx b/docs/mintlify/reference/camel.models.gemini_model.mdxindex 5f75f4653..8480c014f 100644--- a/docs/mintlify/reference/camel.models.gemini_model.mdx+++ b/docs/mintlify/reference/camel.models.gemini_model.mdx@@ -18,6 +18,7 @@ Gemini API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Gemini service. (default: :obj:`https://generativelanguage.googleapis.com/v1beta/ openai/`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.gemini_model.GeminiModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.groq_model.mdx b/docs/mintlify/reference/camel.models.groq_model.mdxindex 58a000882..89ad2a47c 100644--- a/docs/mintlify/reference/camel.models.groq_model.mdx+++ b/docs/mintlify/reference/camel.models.groq_model.mdx@@ -19,6 +19,7 @@ LLM API served by Groq in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Groq service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.groq_model.GroqModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.internlm_model.mdx b/docs/mintlify/reference/camel.models.internlm_model.mdxindex 297603fb0..8fcf83c48 100644--- a/docs/mintlify/reference/camel.models.internlm_model.mdx+++ b/docs/mintlify/reference/camel.models.internlm_model.mdx@@ -18,6 +18,7 @@ InternLM API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the InternLM service. (default: :obj:`https://internlm-chat.intern-ai.org.cn/puyu/api/v1`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.internlm_model.InternLMModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.litellm_model.mdx b/docs/mintlify/reference/camel.models.litellm_model.mdxindex ca859fdae..9d51e0e65 100644--- a/docs/mintlify/reference/camel.models.litellm_model.mdx+++ b/docs/mintlify/reference/camel.models.litellm_model.mdx@@ -17,7 +17,7 @@ Constructor for LiteLLM backend with OpenAI compatibility.- **api_key** (Optional[str], optional): The API key for authenticating with the model service. (default: :obj:`None`)- **url** (Optional[str], optional): The url to the model service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`LiteLLMTokenCounter` will be used. (default: :obj:`None`)-- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.litellm_model.LiteLLMModel.__init__"></a>@@ -31,7 +31,8 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.lmstudio_model.mdx b/docs/mintlify/reference/camel.models.lmstudio_model.mdxindex edf530d12..9e2dbbf78 100644--- a/docs/mintlify/reference/camel.models.lmstudio_model.mdx+++ b/docs/mintlify/reference/camel.models.lmstudio_model.mdx@@ -19,6 +19,7 @@ LLM served by LMStudio in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the LMStudio service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.lmstudio_model.LMStudioModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.mistral_model.mdx b/docs/mintlify/reference/camel.models.mistral_model.mdxindex 7d8bd288e..7e1605fcd 100644--- a/docs/mintlify/reference/camel.models.mistral_model.mdx+++ b/docs/mintlify/reference/camel.models.mistral_model.mdx@@ -19,6 +19,7 @@ Mistral API in a unified BaseModelBackend interface.- **url** (Optional[str], optional): The url to the mistral service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.mistral_model.MistralModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.model_factory.mdx b/docs/mintlify/reference/camel.models.model_factory.mdxindex 2103f5b81..2fdcb8a15 100644--- a/docs/mintlify/reference/camel.models.model_factory.mdx+++ b/docs/mintlify/reference/camel.models.model_factory.mdx@@ -21,6 +21,7 @@ def create(api_key: Optional[str] = None,url: Optional[str] = None,timeout: Optional[float] = None,+ max_retries: int = 3,**kwargs):```@@ -35,7 +36,8 @@ Creates an instance of `BaseModelBackend` of the specified type.- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter(ModelType.GPT_4O_MINI)` will be used if the model platform didn't provide official token counter. (default: :obj:`None`)- **api_key** (Optional[str], optional): The API key for authenticating with the model service. (default: :obj:`None`)- **url** (Optional[str], optional): The url to the model service. (default: :obj:`None`)-- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. (default: :obj:`None`) **kwargs: Additional model-specific parameters that will be passed to the model constructor. For example, Azure OpenAI models may require `api_version`, `azure_deployment_name`, `azure_ad_token_provider`, and `azure_ad_token`.+- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs: Additional model-specific parameters that will be passed to the model constructor. For example, Azure OpenAI models may require `api_version`, `azure_deployment_name`, `azure_ad_token_provider`, and `azure_ad_token`.**Returns:**diff --git a/docs/mintlify/reference/camel.models.modelscope_model.mdx b/docs/mintlify/reference/camel.models.modelscope_model.mdxindex 8f14665ce..2d05996bd 100644--- a/docs/mintlify/reference/camel.models.modelscope_model.mdx+++ b/docs/mintlify/reference/camel.models.modelscope_model.mdx@@ -19,6 +19,7 @@ ModelScope API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the ModelScope service. (default: :obj:`https://api-inference.modelscope.cn/v1/`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.modelscope_model.ModelScopeModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.moonshot_model.mdx b/docs/mintlify/reference/camel.models.moonshot_model.mdxindex 9e2251afe..dcff7a54b 100644--- a/docs/mintlify/reference/camel.models.moonshot_model.mdx+++ b/docs/mintlify/reference/camel.models.moonshot_model.mdx@@ -18,6 +18,7 @@ Moonshot API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Moonshot service. (default: :obj:`https://api.moonshot.cn/v1`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.moonshot_model.MoonshotModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.nemotron_model.mdx b/docs/mintlify/reference/camel.models.nemotron_model.mdxindex c16b5069d..2dd8f6e7c 100644--- a/docs/mintlify/reference/camel.models.nemotron_model.mdx+++ b/docs/mintlify/reference/camel.models.nemotron_model.mdx@@ -16,6 +16,7 @@ Nemotron model API backend with OpenAI compatibility.- **api_key** (Optional[str], optional): The API key for authenticating with the Nvidia service. (default: :obj:`None`)- **url** (Optional[str], optional): The url to the Nvidia service. (default: :obj:`https://integrate.api.nvidia.com/v1`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.**Note:**@@ -31,7 +32,9 @@ def __init__(model_type: Union[ModelType, str],api_key: Optional[str] = None,url: Optional[str] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.netmind_model.mdx b/docs/mintlify/reference/camel.models.netmind_model.mdxindex f4dfabb87..820907256 100644--- a/docs/mintlify/reference/camel.models.netmind_model.mdx+++ b/docs/mintlify/reference/camel.models.netmind_model.mdx@@ -19,6 +19,7 @@ Constructor for Netmind backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the Netmind service. If not provided, "https://api.netmind.ai/inference-api/openai/v1" will be used.(default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.netmind_model.NetmindModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.novita_model.mdx b/docs/mintlify/reference/camel.models.novita_model.mdxindex f70a70044..96b09a471 100644--- a/docs/mintlify/reference/camel.models.novita_model.mdx+++ b/docs/mintlify/reference/camel.models.novita_model.mdx@@ -19,6 +19,7 @@ Constructor for Novita backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the Novita service. If not provided, "https://api.novita.ai/v3/openai" will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.novita_model.NovitaModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.nvidia_model.mdx b/docs/mintlify/reference/camel.models.nvidia_model.mdxindex 9e691dac5..d24fdc65e 100644--- a/docs/mintlify/reference/camel.models.nvidia_model.mdx+++ b/docs/mintlify/reference/camel.models.nvidia_model.mdx@@ -18,6 +18,7 @@ NVIDIA API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the NVIDIA service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.nvidia_model.NvidiaModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.ollama_model.mdx b/docs/mintlify/reference/camel.models.ollama_model.mdxindex 0772c8e8e..ff854878a 100644--- a/docs/mintlify/reference/camel.models.ollama_model.mdx+++ b/docs/mintlify/reference/camel.models.ollama_model.mdx@@ -19,6 +19,7 @@ Ollama service interface.- **url** (Optional[str], optional): The url to the model service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.- **References**:- **https**: //github.com/ollama/ollama/blob/main/docs/openai.md@@ -34,7 +35,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.openai_compatible_model.mdx b/docs/mintlify/reference/camel.models.openai_compatible_model.mdxindex 29c063db5..6d432901a 100644--- a/docs/mintlify/reference/camel.models.openai_compatible_model.mdx+++ b/docs/mintlify/reference/camel.models.openai_compatible_model.mdx@@ -18,6 +18,7 @@ Constructor for model backend supporting OpenAI compatibility.- **url** (str): The url to the model service.- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the OpenAI client initialization. These can include parameters like 'organization', 'default_headers', 'http_client', etc.<a id="camel.models.openai_compatible_model.OpenAICompatibleModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.openai_model.mdx b/docs/mintlify/reference/camel.models.openai_model.mdxindex 585268113..2a6032e9c 100644--- a/docs/mintlify/reference/camel.models.openai_model.mdx+++ b/docs/mintlify/reference/camel.models.openai_model.mdx@@ -18,6 +18,7 @@ OpenAI API in a unified BaseModelBackend interface.- **url** (Optional[str], optional): The url to the OpenAI service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the OpenAI client initialization. These can include parameters like 'organization', 'default_headers', 'http_client', etc.<a id="camel.models.openai_model.OpenAIModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.openrouter_model.mdx b/docs/mintlify/reference/camel.models.openrouter_model.mdxindex ec0c26100..23b44bb61 100644--- a/docs/mintlify/reference/camel.models.openrouter_model.mdx+++ b/docs/mintlify/reference/camel.models.openrouter_model.mdx@@ -20,6 +20,7 @@ interface.- **url** (Optional[str], optional): The url to the OpenRouter service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.openrouter_model.OpenRouterModel.__init__"></a>@@ -33,7 +34,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.ppio_model.mdx b/docs/mintlify/reference/camel.models.ppio_model.mdxindex 44c005aa5..f1b5c028d 100644--- a/docs/mintlify/reference/camel.models.ppio_model.mdx+++ b/docs/mintlify/reference/camel.models.ppio_model.mdx@@ -19,6 +19,7 @@ Constructor for PPIO backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the PPIO service. If not provided, "https://api.ppinfra.com/v3/openai" will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.ppio_model.PPIOModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.qianfan_model.mdx b/docs/mintlify/reference/camel.models.qianfan_model.mdxindex fa63e6213..84d61d43f 100644--- a/docs/mintlify/reference/camel.models.qianfan_model.mdx+++ b/docs/mintlify/reference/camel.models.qianfan_model.mdx@@ -19,6 +19,7 @@ Constructor for Qianfan backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the Qianfan service. If not provided, "https://qianfan.baidubce.com/v2/chat/completions" will be used.(default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (Optional[int], optional): Maximum number of retries for API calls. (default: :obj:`None`) **kwargs: Additional model-specific parameters that will be passed to the model constructor.<a id="camel.models.qianfan_model.QianfanModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs):```diff --git a/docs/mintlify/reference/camel.models.qwen_model.mdx b/docs/mintlify/reference/camel.models.qwen_model.mdxindex f8f32c65f..b742edc57 100644--- a/docs/mintlify/reference/camel.models.qwen_model.mdx+++ b/docs/mintlify/reference/camel.models.qwen_model.mdx@@ -18,6 +18,7 @@ Qwen API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Qwen service. (default: :obj:`https://dashscope.aliyuncs.com/compatible-mode/v1`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.qwen_model.QwenModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.reka_model.mdx b/docs/mintlify/reference/camel.models.reka_model.mdxindex fb28dad1b..9bd08abf2 100644--- a/docs/mintlify/reference/camel.models.reka_model.mdx+++ b/docs/mintlify/reference/camel.models.reka_model.mdx@@ -17,7 +17,7 @@ Reka API in a unified OpenAICompatibleModel interface.- **api_key** (Optional[str], optional): The API key for authenticating with the Reka service. (default: :obj:`None`)- **url** (Optional[str], optional): The url to the Reka service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)-- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.reka_model.RekaModel.__init__"></a>@@ -31,7 +31,8 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.samba_model.mdx b/docs/mintlify/reference/camel.models.samba_model.mdxindex 345bf47d2..066760543 100644--- a/docs/mintlify/reference/camel.models.samba_model.mdx+++ b/docs/mintlify/reference/camel.models.samba_model.mdx@@ -18,6 +18,7 @@ SambaNova service interface.- **url** (Optional[str], optional): The url to the SambaNova service. Current support SambaVerse API: :obj:`"https://sambaverse.sambanova.ai/api/predict"` and SambaNova Cloud: :obj:`"https://api.sambanova.ai/v1"` (default: :obj:`https://api. sambanova.ai/v1`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.samba_model.SambaModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.sglang_model.mdx b/docs/mintlify/reference/camel.models.sglang_model.mdxindex cae4d49e2..d1ee93e7f 100644--- a/docs/mintlify/reference/camel.models.sglang_model.mdx+++ b/docs/mintlify/reference/camel.models.sglang_model.mdx@@ -18,7 +18,8 @@ SGLang service interface.- **url** (Optional[str], optional): The url to the model service. If not provided, :obj:`"http://127.0.0.1:30000/v1"` will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)-- **Reference**: https://sgl-project.github.io/backend/openai_api_completions.html+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.+- **Reference**: https://sgl-project.github.io/backend/openai_api_completions. html<a id="camel.models.sglang_model.SGLangModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.siliconflow_model.mdx b/docs/mintlify/reference/camel.models.siliconflow_model.mdxindex d062a1b7d..144e398e2 100644--- a/docs/mintlify/reference/camel.models.siliconflow_model.mdx+++ b/docs/mintlify/reference/camel.models.siliconflow_model.mdx@@ -18,6 +18,7 @@ SiliconFlow API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The URL to the SiliconFlow service. If not provided, :obj:`https://api.siliconflow.cn/v1/` will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.siliconflow_model.SiliconFlowModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.stub_model.mdx b/docs/mintlify/reference/camel.models.stub_model.mdxindex 5c5c1472d..f449869e7 100644--- a/docs/mintlify/reference/camel.models.stub_model.mdx+++ b/docs/mintlify/reference/camel.models.stub_model.mdx@@ -85,7 +85,8 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3):```diff --git a/docs/mintlify/reference/camel.models.togetherai_model.mdx b/docs/mintlify/reference/camel.models.togetherai_model.mdxindex 1cddf376d..8304fb876 100644--- a/docs/mintlify/reference/camel.models.togetherai_model.mdx+++ b/docs/mintlify/reference/camel.models.togetherai_model.mdx@@ -19,6 +19,7 @@ Constructor for Together AI backend with OpenAI compatibility.- **url** (Optional[str], optional): The url to the Together AI service. If not provided, "https://api.together.xyz/v1" will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used.- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.togetherai_model.TogetherAIModel.__init__"></a>@@ -32,7 +33,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.vllm_model.mdx b/docs/mintlify/reference/camel.models.vllm_model.mdxindex 6c0e1ba45..abc0af92c 100644--- a/docs/mintlify/reference/camel.models.vllm_model.mdx+++ b/docs/mintlify/reference/camel.models.vllm_model.mdx@@ -18,6 +18,7 @@ vLLM service interface.- **url** (Optional[str], optional): The url to the model service. If not provided, :obj:`"http://localhost:8000/v1"` will be used. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.- **References**:- **https**: //docs.vllm.ai/en/latest/serving/openai_compatible_server.html@@ -33,7 +34,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.volcano_model.mdx b/docs/mintlify/reference/camel.models.volcano_model.mdxindex 7952de18c..68c09fee0 100644--- a/docs/mintlify/reference/camel.models.volcano_model.mdx+++ b/docs/mintlify/reference/camel.models.volcano_model.mdx@@ -18,6 +18,7 @@ Volcano Engine API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Volcano Engine service. (default: :obj:`https://ark.cn-beijing.volces.com/api/v3`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.volcano_model.VolcanoModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.watsonx_model.mdx b/docs/mintlify/reference/camel.models.watsonx_model.mdxindex a6bb86edd..b5a84549e 100644--- a/docs/mintlify/reference/camel.models.watsonx_model.mdx+++ b/docs/mintlify/reference/camel.models.watsonx_model.mdx@@ -19,7 +19,7 @@ WatsonX API in a unified BaseModelBackend interface.- **url** (Optional[str], optional): The url to the WatsonX service. (default: :obj:`None`)- **project_id** (Optional[str], optional): The project ID authenticating with the WatsonX service. (default: :obj:`None`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)-- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.watsonx_model.WatsonXModel.__init__"></a>@@ -34,7 +34,8 @@ def __init__(url: Optional[str] = None,project_id: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.yi_model.mdx b/docs/mintlify/reference/camel.models.yi_model.mdxindex 0f5a72823..9488004ec 100644--- a/docs/mintlify/reference/camel.models.yi_model.mdx+++ b/docs/mintlify/reference/camel.models.yi_model.mdx@@ -18,6 +18,7 @@ Yi API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the Yi service. (default: :obj:`https://api.lingyiwanwu.com/v1`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.yi_model.YiModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```diff --git a/docs/mintlify/reference/camel.models.zhipuai_model.mdx b/docs/mintlify/reference/camel.models.zhipuai_model.mdxindex b5368afba..8b78fd2a3 100644--- a/docs/mintlify/reference/camel.models.zhipuai_model.mdx+++ b/docs/mintlify/reference/camel.models.zhipuai_model.mdx@@ -18,6 +18,7 @@ ZhipuAI API in a unified OpenAICompatibleModel interface.- **url** (Optional[str], optional): The url to the ZhipuAI service. (default: :obj:`https://open.bigmodel.cn/api/paas/v4/`)- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter( ModelType.GPT_4O_MINI)` will be used. (default: :obj:`None`)- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`)+- **max_retries** (int, optional): Maximum number of retries for API calls. (default: :obj:`3`) **kwargs (Any): Additional arguments to pass to the client initialization.<a id="camel.models.zhipuai_model.ZhipuAIModel.__init__"></a>@@ -31,7 +32,9 @@ def __init__(api_key: Optional[str] = None,url: Optional[str] = None,token_counter: Optional[BaseTokenCounter] = None,- timeout: Optional[float] = None+ timeout: Optional[float] = None,+ max_retries: int = 3,+ **kwargs: Any):```