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/aiplatform_v1.endpoints.html
+26-8
Original file line number
Diff line number
Diff line change
@@ -383,6 +383,10 @@ <h3>Method Details</h3>
383
383
},
384
384
],
385
385
"googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
386
+
"dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
387
+
"dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
388
+
"mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
389
+
},
386
390
},
387
391
"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
388
392
"disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
@@ -652,6 +656,10 @@ <h3>Method Details</h3>
652
656
},
653
657
],
654
658
"googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
659
+
"dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
660
+
"dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
661
+
"mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
662
+
},
655
663
},
656
664
"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
657
665
"disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
@@ -769,6 +777,9 @@ <h3>Method Details</h3>
769
777
},
770
778
},
771
779
],
780
+
"retrievalMetadata": { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
781
+
"googleSearchDynamicRetrievalScore": 3.14, # Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range `[0, 1]`, where 0 is the least likely and 1 is the most likely. This score is only populated when Google Search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger Google Search.
782
+
},
772
783
"searchEntryPoint": { # Google search entry point. # Optional. Google search entry for the following-up web searches.
773
784
"renderedContent": "A String", # Optional. Web content snippet that can be embedded in a web page or an app webview.
"chosenCandidates": [ # Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
783
794
{ # Candidate for the logprobs token and score.
784
795
"logProbability": 3.14, # The candidate's log probability.
785
-
"token": "A String", # The candidate’s token string value.
786
-
"tokenId": 42, # The candidate’s token id value.
796
+
"token": "A String", # The candidate's token string value.
797
+
"tokenId": 42, # The candidate's token id value.
787
798
},
788
799
],
789
800
"topCandidates": [ # Length = total number of decoding steps.
790
801
{ # Candidates with top log probabilities at each decoding step.
791
802
"candidates": [ # Sorted by log probability in descending order.
792
803
{ # Candidate for the logprobs token and score.
793
804
"logProbability": 3.14, # The candidate's log probability.
794
-
"token": "A String", # The candidate’s token string value.
795
-
"tokenId": 42, # The candidate’s token id value.
805
+
"token": "A String", # The candidate's token string value.
806
+
"tokenId": 42, # The candidate's token id value.
796
807
},
797
808
],
798
809
},
@@ -1062,6 +1073,10 @@ <h3>Method Details</h3>
1062
1073
},
1063
1074
],
1064
1075
"googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
1076
+
"dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
1077
+
"dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
1078
+
"mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
1079
+
},
1065
1080
},
1066
1081
"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
1067
1082
"disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
@@ -1179,6 +1194,9 @@ <h3>Method Details</h3>
1179
1194
},
1180
1195
},
1181
1196
],
1197
+
"retrievalMetadata": { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
1198
+
"googleSearchDynamicRetrievalScore": 3.14, # Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range `[0, 1]`, where 0 is the least likely and 1 is the most likely. This score is only populated when Google Search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger Google Search.
1199
+
},
1182
1200
"searchEntryPoint": { # Google search entry point. # Optional. Google search entry for the following-up web searches.
1183
1201
"renderedContent": "A String", # Optional. Web content snippet that can be embedded in a web page or an app webview.
<pre>Exposes an OpenAI-compatible endpoint for chat completions.
92
+
93
+
Args:
94
+
endpoint: string, Required. The name of the endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
95
+
body: object, The request body.
96
+
The object takes the form of:
97
+
98
+
{ # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
99
+
"contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
100
+
"data": "A String", # The HTTP request/response body as raw binary.
101
+
"extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
102
+
{
103
+
"a_key": "", # Properties of the object. Contains field @type with type URL.
104
+
},
105
+
],
106
+
}
107
+
108
+
x__xgafv: string, V1 error format.
109
+
Allowed values
110
+
1 - v1 error format
111
+
2 - v2 error format
112
+
113
+
Returns:
114
+
An object of the form:
115
+
116
+
{ # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
117
+
"contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
118
+
"data": "A String", # The HTTP request/response body as raw binary.
119
+
"extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
120
+
{
121
+
"a_key": "", # Properties of the object. Contains field @type with type URL.
0 commit comments