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`.
95
+
<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`.
96
96
97
97
Args:
98
98
name: string, The name of the operation resource to be cancelled. (required)
Copy file name to clipboardExpand all lines: docs/dyn/firebaseml_v2beta.projects.locations.publishers.models.html
+57Lines changed: 57 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -348,6 +348,25 @@ <h3>Method Details</h3>
348
348
],
349
349
},
350
350
],
351
+
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
352
+
"filter": { # Config for filters. # Optional. Config for filters.
353
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
354
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
355
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
356
+
},
357
+
"hybridSearch": { # Config for Hybrid Search. # Optional. Config for Hybrid Search.
358
+
"alpha": 3.14, # Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.
359
+
},
360
+
"ranking": { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
361
+
"llmRanker": { # Config for LlmRanker. # Optional. Config for LlmRanker.
362
+
"modelName": "A String", # Optional. The model name used for ranking. Format: `gemini-1.5-pro`
363
+
},
364
+
"rankService": { # Config for Rank Service. # Optional. Config for Rank Service.
365
+
"modelName": "A String", # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
366
+
},
367
+
},
368
+
"topK": 42, # Optional. The number of contexts to retrieve.
369
+
},
351
370
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
352
371
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
353
372
},
@@ -641,6 +660,25 @@ <h3>Method Details</h3>
641
660
],
642
661
},
643
662
],
663
+
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
664
+
"filter": { # Config for filters. # Optional. Config for filters.
665
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
666
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
667
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
668
+
},
669
+
"hybridSearch": { # Config for Hybrid Search. # Optional. Config for Hybrid Search.
670
+
"alpha": 3.14, # Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.
671
+
},
672
+
"ranking": { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
673
+
"llmRanker": { # Config for LlmRanker. # Optional. Config for LlmRanker.
674
+
"modelName": "A String", # Optional. The model name used for ranking. Format: `gemini-1.5-pro`
675
+
},
676
+
"rankService": { # Config for Rank Service. # Optional. Config for Rank Service.
677
+
"modelName": "A String", # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
678
+
},
679
+
},
680
+
"topK": 42, # Optional. The number of contexts to retrieve.
681
+
},
644
682
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
645
683
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
646
684
},
@@ -1091,6 +1129,25 @@ <h3>Method Details</h3>
1091
1129
],
1092
1130
},
1093
1131
],
1132
+
"ragRetrievalConfig": { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
1133
+
"filter": { # Config for filters. # Optional. Config for filters.
1134
+
"metadataFilter": "A String", # Optional. String for metadata filtering.
1135
+
"vectorDistanceThreshold": 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
1136
+
"vectorSimilarityThreshold": 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
1137
+
},
1138
+
"hybridSearch": { # Config for Hybrid Search. # Optional. Config for Hybrid Search.
1139
+
"alpha": 3.14, # Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.
1140
+
},
1141
+
"ranking": { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
1142
+
"llmRanker": { # Config for LlmRanker. # Optional. Config for LlmRanker.
1143
+
"modelName": "A String", # Optional. The model name used for ranking. Format: `gemini-1.5-pro`
1144
+
},
1145
+
"rankService": { # Config for Rank Service. # Optional. Config for Rank Service.
1146
+
"modelName": "A String", # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
1147
+
},
1148
+
},
1149
+
"topK": 42, # Optional. The number of contexts to retrieve.
1150
+
},
1094
1151
"similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
1095
1152
"vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
Copy file name to clipboardExpand all lines: googleapiclient/discovery_cache/documents/firebaseml.v1.json
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -108,7 +108,7 @@
108
108
"operations": {
109
109
"methods": {
110
110
"cancel": {
111
-
"description": "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`.",
111
+
"description": "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`.",
"description": "Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally.",
0 commit comments