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
Copy file name to clipboardexpand all lines: docs/dyn/firebaseml_v2beta.projects.locations.publishers.models.html
+19-5
Original file line number
Diff line number
Diff line change
@@ -266,7 +266,7 @@ <h3>Method Details</h3>
266
266
},
267
267
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
268
268
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
269
-
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services.
269
+
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
270
270
},
271
271
"functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
272
272
{ # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
@@ -610,7 +610,7 @@ <h3>Method Details</h3>
610
610
},
611
611
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
612
612
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
613
-
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services.
613
+
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
614
614
},
615
615
"functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
616
616
{ # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
@@ -927,7 +927,14 @@ <h3>Method Details</h3>
927
927
"tokenCount": 42, # Number of tokens.
928
928
},
929
929
],
930
-
"totalTokenCount": 42, # Total token count for prompt and response candidates.
930
+
"toolUsePromptTokenCount": 42, # Output only. Number of tokens present in tool-use prompt(s).
931
+
"toolUsePromptTokensDetails": [ # Output only. List of modalities that were processed for tool-use request inputs.
932
+
{ # Represents token counting info for a single modality.
933
+
"modality": "A String", # The modality associated with this token count.
934
+
"tokenCount": 42, # Number of tokens.
935
+
},
936
+
],
937
+
"totalTokenCount": 42, # Total token count for prompt, response candidates, and tool-use prompts (if present).
931
938
},
932
939
}</pre>
933
940
</div>
@@ -1128,7 +1135,7 @@ <h3>Method Details</h3>
1128
1135
},
1129
1136
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
1130
1137
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
1131
-
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services.
1138
+
"codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
1132
1139
},
1133
1140
"functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
1134
1141
{ # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
@@ -1445,7 +1452,14 @@ <h3>Method Details</h3>
1445
1452
"tokenCount": 42, # Number of tokens.
1446
1453
},
1447
1454
],
1448
-
"totalTokenCount": 42, # Total token count for prompt and response candidates.
1455
+
"toolUsePromptTokenCount": 42, # Output only. Number of tokens present in tool-use prompt(s).
1456
+
"toolUsePromptTokensDetails": [ # Output only. List of modalities that were processed for tool-use request inputs.
1457
+
{ # Represents token counting info for a single modality.
1458
+
"modality": "A String", # The modality associated with this token count.
1459
+
"tokenCount": 42, # Number of tokens.
1460
+
},
1461
+
],
1462
+
"totalTokenCount": 42, # Total token count for prompt, response candidates, and tool-use prompts (if present).
"description": "Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services."
1777
+
"description": "Optional. CodeExecution tool type. Enables the model to execute code as part of generation."
1764
1778
},
1765
1779
"functionDeclarations": {
1766
1780
"description": "Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.",
0 commit comments