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
<pclass="firstline">Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`.</p>
79
+
<pclass="firstline">Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`.</p>
<pre>Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`.
98
+
<pre>Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`.
99
99
100
100
Args:
101
101
name: string, The name of the operation resource to be cancelled. (required)
Copy file name to clipboardExpand all lines: docs/dyn/aiplatform_v1.endpoints.html
+28-9Lines changed: 28 additions & 9 deletions
Original file line number
Diff line number
Diff line change
@@ -395,9 +395,6 @@ <h3>Method Details</h3>
395
395
"datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
396
396
},
397
397
"vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
398
-
"ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
399
-
"A String",
400
-
],
401
398
"ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
407
+
"filter": { # Config for filters. # Optional. Config for filters.
408
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
409
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
410
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
411
+
},
412
+
"topK": 42, # Optional. The number of contexts to retrieve.
413
+
},
409
414
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
410
415
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
411
416
},
@@ -438,6 +443,7 @@ <h3>Method Details</h3>
438
443
The object takes the form of:
439
444
440
445
{ # Request message for [PredictionService.GenerateContent].
446
+
"cachedContent": "A String", # Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: `projects/{project}/locations/{location}/cachedContents/{cachedContent}`
441
447
"contents": [ # Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
442
448
{ # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
443
449
"parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
@@ -669,9 +675,6 @@ <h3>Method Details</h3>
669
675
"datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
670
676
},
671
677
"vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
672
-
"ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
673
-
"A String",
674
-
],
675
678
"ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
687
+
"filter": { # Config for filters. # Optional. Config for filters.
688
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
689
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
690
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
691
+
},
692
+
"topK": 42, # Optional. The number of contexts to retrieve.
693
+
},
683
694
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
684
695
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
685
696
},
@@ -840,6 +851,7 @@ <h3>Method Details</h3>
840
851
],
841
852
},
842
853
"usageMetadata": { # Usage metadata about response(s). # Usage metadata about the response(s).
854
+
"cachedContentTokenCount": 42, # Output only. Number of tokens in the cached part in the input (the cached content).
843
855
"candidatesTokenCount": 42, # Number of tokens in the response(s).
844
856
"promptTokenCount": 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
845
857
"totalTokenCount": 42, # Total token count for prompt and response candidates.
@@ -857,6 +869,7 @@ <h3>Method Details</h3>
857
869
The object takes the form of:
858
870
859
871
{ # Request message for [PredictionService.GenerateContent].
872
+
"cachedContent": "A String", # Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: `projects/{project}/locations/{location}/cachedContents/{cachedContent}`
860
873
"contents": [ # Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
861
874
{ # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
862
875
"parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
@@ -1088,9 +1101,6 @@ <h3>Method Details</h3>
1088
1101
"datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
1089
1102
},
1090
1103
"vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
1091
-
"ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
1092
-
"A String",
1093
-
],
1094
1104
"ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
1113
+
"filter": { # Config for filters. # Optional. Config for filters.
1114
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
1115
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
1116
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
1117
+
},
1118
+
"topK": 42, # Optional. The number of contexts to retrieve.
1119
+
},
1102
1120
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
1103
1121
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
1104
1122
},
@@ -1259,6 +1277,7 @@ <h3>Method Details</h3>
1259
1277
],
1260
1278
},
1261
1279
"usageMetadata": { # Usage metadata about response(s). # Usage metadata about the response(s).
1280
+
"cachedContentTokenCount": 42, # Output only. Number of tokens in the cached part in the input (the cached content).
1262
1281
"candidatesTokenCount": 42, # Number of tokens in the response(s).
1263
1282
"promptTokenCount": 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
1264
1283
"totalTokenCount": 42, # Total token count for prompt and response candidates.
0 commit comments