feat: add llm timeout

api/core/llm/streamable_azure_chat_open_ai.py

@@ -2,7 +2,7 @@ from langchain.callbacks.manager import Callbacks, CallbackManagerForLLMRun
 from langchain.chat_models.openai import _convert_dict_to_message
 from langchain.schema import BaseMessage, LLMResult, ChatResult, ChatGeneration
 from langchain.chat_models import AzureChatOpenAI
-from typing import Optional, List, Dict, Any
+from typing import Optional, List, Dict, Any, Tuple, Union
 
 from pydantic import root_validator
 
@@ -10,6 +10,11 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 
 
 class StreamableAzureChatOpenAI(AzureChatOpenAI):
+    request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 120.0)
+    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
+    max_retries: int = 2
+    """Maximum number of retries to make when generating."""
+
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""

api/core/llm/streamable_azure_open_ai.py

 from langchain.callbacks.manager import Callbacks
 from langchain.llms import AzureOpenAI
 from langchain.schema import LLMResult
-from typing import Optional, List, Dict, Mapping, Any
+from typing import Optional, List, Dict, Mapping, Any, Union, Tuple
 
 from pydantic import root_validator
 
@@ -11,6 +11,10 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 class StreamableAzureOpenAI(AzureOpenAI):
     openai_api_type: str = "azure"
     openai_api_version: str = ""
+    request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 120.0)
+    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
+    max_retries: int = 2
+    """Maximum number of retries to make when generating."""
 
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:

api/core/llm/streamable_chat_anthropic.py

 from typing import List, Optional, Any, Dict
 
+from httpx import Timeout
 from langchain.callbacks.manager import Callbacks
 from langchain.chat_models import ChatAnthropic
 from langchain.schema import BaseMessage, LLMResult, SystemMessage, AIMessage, HumanMessage, ChatMessage
@@ -13,6 +14,8 @@ class StreamableChatAnthropic(ChatAnthropic):
     Wrapper around Anthropic's large language model.
     """
 
+    default_request_timeout: Optional[float] = Timeout(timeout=120.0, connect=5.0)
+
     @root_validator()
     def prepare_params(cls, values: Dict) -> Dict:
         values['model_name'] = values.get('model')

api/core/llm/streamable_chat_open_ai.py

@@ -3,7 +3,7 @@ import os
 from langchain.callbacks.manager import Callbacks
 from langchain.schema import BaseMessage, LLMResult
 from langchain.chat_models import ChatOpenAI
-from typing import Optional, List, Dict, Any
+from typing import Optional, List, Dict, Any, Union, Tuple
 
 from pydantic import root_validator
 
@@ -11,6 +11,10 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 
 
 class StreamableChatOpenAI(ChatOpenAI):
+    request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 120.0)
+    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
+    max_retries: int = 2
+    """Maximum number of retries to make when generating."""
 
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:

api/core/llm/streamable_open_ai.py

@@ -2,7 +2,7 @@ import os
 
 from langchain.callbacks.manager import Callbacks
 from langchain.schema import LLMResult
-from typing import Optional, List, Dict, Any, Mapping
+from typing import Optional, List, Dict, Any, Mapping, Union, Tuple
 from langchain import OpenAI
 from pydantic import root_validator
 
@@ -10,6 +10,10 @@ from core.llm.wrappers.openai_wrapper import handle_openai_exceptions
 
 
 class StreamableOpenAI(OpenAI):
+    request_timeout: Optional[Union[float, Tuple[float, float]]] = (5.0, 120.0)
+    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
+    max_retries: int = 2
+    """Maximum number of retries to make when generating."""
 
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict: