Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Python agentagentopsagents-sdkaianthropicautogencost-estimationcrewaievalsevaluation-metricsgroqlangchainllmmistralollamaopenaiopenai-agents
Increasing max_queue_size (#442)
Howard Gil806106533456
diff --git a/agentops/__init__.py b/agentops/__init__.pyindex 5a054f75..4c8f8dae 100755--- a/agentops/__init__.py+++ b/agentops/__init__.py@@ -59,7 +59,7 @@ def init(be read from the AGENTOPS_API_ENDPOINT environment variable. Defaults to 'https://api.agentops.ai'.max_wait_time (int, optional): The maximum time to wait in milliseconds before flushing the queue.Defaults to 5,000 (5 seconds)- max_queue_size (int, optional): The maximum size of the event queue. Defaults to 100.+ max_queue_size (int, optional): The maximum size of the event queue. Defaults to 512.tags (List[str], optional): [Deprecated] Use `default_tags` instead.default_tags (List[str], optional): Default tags for the sessions that can be used for grouping or sorting later (e.g. ["GPT-4"]).instrument_llm_calls (bool): Whether to instrument LLM calls and emit LLMEvents.diff --git a/agentops/config.py b/agentops/config.pyindex d14c8502..7dfb574d 100644--- a/agentops/config.py+++ b/agentops/config.py@@ -10,7 +10,7 @@ class Configuration:self.parent_key: Optional[str] = Noneself.endpoint: str = "https://api.agentops.ai"self.max_wait_time: int = 5000- self.max_queue_size: int = 100+ self.max_queue_size: int = 512self.default_tags: set[str] = set()self.instrument_llm_calls: bool = Trueself.auto_start_session: bool = True