You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|link:https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/time/Duration.html[Duration] link:#duration-note-anchor-quarkus-langchain4j-ai-gemini_quarkus-langchain4j[icon:question-circle[title=More information about the Duration format]]
Controls whether thought summaries are enabled. Thought summaries are synthesized versions of the model's raw thoughts and offer insights into the model's internal reasoning process.
The thinkingBudget parameter guides the model on the number of thinking tokens to use when generating a response. A higher token count generally allows for more detailed reasoning, which can be beneficial for tackling more complex tasks. If latency is more important, use a lower budget or disable thinking by setting thinkingBudget to 0. Setting the thinkingBudget to -1 turns on dynamic thinking, meaning the model will adjust the budget based on the complexity of the request.
415
+
416
+
The thinkingBudget is only supported in Gemini 2.5 Flash, 2.5 Pro, and 2.5 Flash-Lite. Depending on the prompt, the model might overflow or underflow the token budget. See link:https://ai.google.dev/gemini-api/docs/thinking#set-budget[Gemini API docs] for more details.
|link:https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/time/Duration.html[Duration] link:#duration-note-anchor-quarkus-langchain4j-ai-gemini_quarkus-langchain4j[icon:question-circle[title=More information about the Duration format]]
Controls whether thought summaries are enabled. Thought summaries are synthesized versions of the model's raw thoughts and offer insights into the model's internal reasoning process.
The thinkingBudget parameter guides the model on the number of thinking tokens to use when generating a response. A higher token count generally allows for more detailed reasoning, which can be beneficial for tackling more complex tasks. If latency is more important, use a lower budget or disable thinking by setting thinkingBudget to 0. Setting the thinkingBudget to -1 turns on dynamic thinking, meaning the model will adjust the budget based on the complexity of the request.
922
+
923
+
The thinkingBudget is only supported in Gemini 2.5 Flash, 2.5 Pro, and 2.5 Flash-Lite. Depending on the prompt, the model might overflow or underflow the token budget. See link:https://ai.google.dev/gemini-api/docs/thinking#set-budget[Gemini API docs] for more details.
|link:https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/time/Duration.html[Duration] link:#duration-note-anchor-quarkus-langchain4j-ai-gemini_quarkus-langchain4j[icon:question-circle[title=More information about the Duration format]]
Controls whether thought summaries are enabled. Thought summaries are synthesized versions of the model's raw thoughts and offer insights into the model's internal reasoning process.
The thinkingBudget parameter guides the model on the number of thinking tokens to use when generating a response. A higher token count generally allows for more detailed reasoning, which can be beneficial for tackling more complex tasks. If latency is more important, use a lower budget or disable thinking by setting thinkingBudget to 0. Setting the thinkingBudget to -1 turns on dynamic thinking, meaning the model will adjust the budget based on the complexity of the request.
415
+
416
+
The thinkingBudget is only supported in Gemini 2.5 Flash, 2.5 Pro, and 2.5 Flash-Lite. Depending on the prompt, the model might overflow or underflow the token budget. See link:https://ai.google.dev/gemini-api/docs/thinking#set-budget[Gemini API docs] for more details.
|link:https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/time/Duration.html[Duration] link:#duration-note-anchor-quarkus-langchain4j-ai-gemini_quarkus-langchain4j[icon:question-circle[title=More information about the Duration format]]
Controls whether thought summaries are enabled. Thought summaries are synthesized versions of the model's raw thoughts and offer insights into the model's internal reasoning process.
The thinkingBudget parameter guides the model on the number of thinking tokens to use when generating a response. A higher token count generally allows for more detailed reasoning, which can be beneficial for tackling more complex tasks. If latency is more important, use a lower budget or disable thinking by setting thinkingBudget to 0. Setting the thinkingBudget to -1 turns on dynamic thinking, meaning the model will adjust the budget based on the complexity of the request.
922
+
923
+
The thinkingBudget is only supported in Gemini 2.5 Flash, 2.5 Pro, and 2.5 Flash-Lite. Depending on the prompt, the model might overflow or underflow the token budget. See link:https://ai.google.dev/gemini-api/docs/thinking#set-budget[Gemini API docs] for more details.
0 commit comments