From efc4d1da1b4ad9d981844f9d097edfb517175127 Mon Sep 17 00:00:00 2001 From: donalevans Date: Wed, 3 Sep 2025 14:57:51 -0700 Subject: [PATCH] Document thinking_config in GoogleVertexAITaskSettings --- output/openapi/elasticsearch-openapi.json | 20 ++++ .../elasticsearch-serverless-openapi.json | 20 ++++ output/schema/schema.json | 98 +++++++++++++------ output/typescript/types.ts | 5 + specification/_doc_ids/table.csv | 1 + specification/inference/_types/CommonTypes.ts | 13 +++ 6 files changed, 126 insertions(+), 31 deletions(-) diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json index 27f21b7d7e..09df19a9ce 100644 --- a/output/openapi/elasticsearch-openapi.json +++ b/output/openapi/elasticsearch-openapi.json @@ -102892,6 +102892,26 @@ "top_n": { "description": "For a `rerank` task, the number of the top N documents that should be returned.", "type": "number" + }, + "thinking_config": { + "externalDocs": { + "url": "https://ai.google.dev/gemini-api/docs/thinking#set-budget" + }, + "description": "For a `completion` or `chat_completion` task, allows configuration of the thinking features for the model.\nRefer to the Google documentation for the allowable configurations for each model type.", + "allOf": [ + { + "$ref": "#/components/schemas/inference._types.ThinkingConfig" + } + ] + } + } + }, + "inference._types.ThinkingConfig": { + "type": "object", + "properties": { + "thinking_budget": { + "description": "Indicates the desired thinking budget in tokens.", + "type": "number" } } }, diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json index bd40ab5370..9abc66cf84 100644 --- a/output/openapi/elasticsearch-serverless-openapi.json +++ b/output/openapi/elasticsearch-serverless-openapi.json @@ -66492,6 +66492,26 @@ "top_n": { "description": "For a `rerank` task, the number of the top N documents that should be returned.", "type": "number" + }, + "thinking_config": { + "externalDocs": { + "url": "https://ai.google.dev/gemini-api/docs/thinking#set-budget" + }, + "description": "For a `completion` or `chat_completion` task, allows configuration of the thinking features for the model.\nRefer to the Google documentation for the allowable configurations for each model type.", + "allOf": [ + { + "$ref": "#/components/schemas/inference._types.ThinkingConfig" + } + ] + } + } + }, + "inference._types.ThinkingConfig": { + "type": "object", + "properties": { + "thinking_budget": { + "description": "Indicates the desired thinking budget in tokens.", + "type": "number" } } }, diff --git a/output/schema/schema.json b/output/schema/schema.json index da18d82f73..f2fc92a22d 100644 --- a/output/schema/schema.json +++ b/output/schema/schema.json @@ -172417,7 +172417,7 @@ "name": "GoogleVertexAIServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1389-L1391" + "specLocation": "inference/_types/CommonTypes.ts#L1402-L1404" }, { "kind": "interface", @@ -172449,9 +172449,23 @@ "namespace": "_types" } } + }, + { + "description": "For a `completion` or `chat_completion` task, allows configuration of the thinking features for the model.\nRefer to the Google documentation for the allowable configurations for each model type.", + "extDocId": "googlevertexai-thinking", + "extDocUrl": "https://ai.google.dev/gemini-api/docs/thinking#set-budget", + "name": "thinking_config", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "ThinkingConfig", + "namespace": "inference._types" + } + } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1371-L1380" + "specLocation": "inference/_types/CommonTypes.ts#L1371-L1386" }, { "kind": "enum", @@ -172473,7 +172487,7 @@ "name": "GoogleVertexAITaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1382-L1387" + "specLocation": "inference/_types/CommonTypes.ts#L1395-L1400" }, { "kind": "interface", @@ -172535,7 +172549,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1393-L1425" + "specLocation": "inference/_types/CommonTypes.ts#L1406-L1438" }, { "kind": "enum", @@ -172548,7 +172562,7 @@ "name": "HuggingFaceServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1446-L1448" + "specLocation": "inference/_types/CommonTypes.ts#L1459-L1461" }, { "kind": "interface", @@ -172582,7 +172596,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1427-L1437" + "specLocation": "inference/_types/CommonTypes.ts#L1440-L1450" }, { "kind": "enum", @@ -172604,7 +172618,7 @@ "name": "HuggingFaceTaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1439-L1444" + "specLocation": "inference/_types/CommonTypes.ts#L1452-L1457" }, { "kind": "interface", @@ -173796,7 +173810,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1450-L1479" + "specLocation": "inference/_types/CommonTypes.ts#L1463-L1492" }, { "kind": "enum", @@ -173809,7 +173823,7 @@ "name": "JinaAIServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1509-L1511" + "specLocation": "inference/_types/CommonTypes.ts#L1522-L1524" }, { "kind": "enum", @@ -173828,7 +173842,7 @@ "name": "JinaAISimilarityType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1513-L1517" + "specLocation": "inference/_types/CommonTypes.ts#L1526-L1530" }, { "kind": "interface", @@ -173874,7 +173888,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1481-L1502" + "specLocation": "inference/_types/CommonTypes.ts#L1494-L1515" }, { "kind": "enum", @@ -173890,7 +173904,7 @@ "name": "JinaAITaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1504-L1507" + "specLocation": "inference/_types/CommonTypes.ts#L1517-L1520" }, { "kind": "enum", @@ -173912,7 +173926,7 @@ "name": "JinaAITextEmbeddingTask", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1519-L1524" + "specLocation": "inference/_types/CommonTypes.ts#L1532-L1537" }, { "kind": "interface", @@ -173984,7 +173998,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1526-L1556" + "specLocation": "inference/_types/CommonTypes.ts#L1539-L1569" }, { "kind": "enum", @@ -173997,7 +174011,7 @@ "name": "LlamaServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1564-L1566" + "specLocation": "inference/_types/CommonTypes.ts#L1577-L1579" }, { "kind": "enum", @@ -174016,7 +174030,7 @@ "name": "LlamaSimilarityType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1568-L1572" + "specLocation": "inference/_types/CommonTypes.ts#L1581-L1585" }, { "kind": "enum", @@ -174035,7 +174049,7 @@ "name": "LlamaTaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1558-L1562" + "specLocation": "inference/_types/CommonTypes.ts#L1571-L1575" }, { "kind": "interface", @@ -174193,7 +174207,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1574-L1601" + "specLocation": "inference/_types/CommonTypes.ts#L1587-L1614" }, { "kind": "enum", @@ -174206,7 +174220,7 @@ "name": "MistralServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1609-L1611" + "specLocation": "inference/_types/CommonTypes.ts#L1622-L1624" }, { "kind": "enum", @@ -174225,7 +174239,7 @@ "name": "MistralTaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1603-L1607" + "specLocation": "inference/_types/CommonTypes.ts#L1616-L1620" }, { "kind": "interface", @@ -174312,7 +174326,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1613-L1655" + "specLocation": "inference/_types/CommonTypes.ts#L1626-L1668" }, { "kind": "enum", @@ -174325,7 +174339,7 @@ "name": "OpenAIServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1671-L1673" + "specLocation": "inference/_types/CommonTypes.ts#L1684-L1686" }, { "kind": "interface", @@ -174347,7 +174361,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1657-L1663" + "specLocation": "inference/_types/CommonTypes.ts#L1670-L1676" }, { "kind": "enum", @@ -174366,7 +174380,7 @@ "name": "OpenAITaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1665-L1669" + "specLocation": "inference/_types/CommonTypes.ts#L1678-L1682" }, { "kind": "interface", @@ -175173,6 +175187,28 @@ ], "specLocation": "inference/_types/Results.ts#L60-L65" }, + { + "kind": "interface", + "name": { + "name": "ThinkingConfig", + "namespace": "inference._types" + }, + "properties": [ + { + "description": "Indicates the desired thinking budget in tokens.", + "name": "thinking_budget", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + } + ], + "specLocation": "inference/_types/CommonTypes.ts#L1388-L1393" + }, { "kind": "interface", "description": "A tool call generated by the model.", @@ -175317,7 +175353,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1675-L1706" + "specLocation": "inference/_types/CommonTypes.ts#L1688-L1719" }, { "kind": "enum", @@ -175330,7 +175366,7 @@ "name": "VoyageAIServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1739-L1741" + "specLocation": "inference/_types/CommonTypes.ts#L1752-L1754" }, { "kind": "interface", @@ -175390,7 +175426,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1708-L1732" + "specLocation": "inference/_types/CommonTypes.ts#L1721-L1745" }, { "kind": "enum", @@ -175406,7 +175442,7 @@ "name": "VoyageAITaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1734-L1737" + "specLocation": "inference/_types/CommonTypes.ts#L1747-L1750" }, { "kind": "interface", @@ -175494,7 +175530,7 @@ } } ], - "specLocation": "inference/_types/CommonTypes.ts#L1743-L1781" + "specLocation": "inference/_types/CommonTypes.ts#L1756-L1794" }, { "kind": "enum", @@ -175507,7 +175543,7 @@ "name": "WatsonxServiceType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1789-L1791" + "specLocation": "inference/_types/CommonTypes.ts#L1802-L1804" }, { "kind": "enum", @@ -175526,7 +175562,7 @@ "name": "WatsonxTaskType", "namespace": "inference._types" }, - "specLocation": "inference/_types/CommonTypes.ts#L1783-L1787" + "specLocation": "inference/_types/CommonTypes.ts#L1796-L1800" }, { "kind": "request", diff --git a/output/typescript/types.ts b/output/typescript/types.ts index e7de8ead24..1bea18a6f8 100644 --- a/output/typescript/types.ts +++ b/output/typescript/types.ts @@ -14080,6 +14080,7 @@ export type InferenceGoogleVertexAIServiceType = 'googlevertexai' export interface InferenceGoogleVertexAITaskSettings { auto_truncate?: boolean top_n?: integer + thinking_config?: InferenceThinkingConfig } export type InferenceGoogleVertexAITaskType = 'rerank' | 'text_embedding' | 'completion' | 'chat_completion' @@ -14404,6 +14405,10 @@ export interface InferenceTextEmbeddingResult { embedding: InferenceDenseVector } +export interface InferenceThinkingConfig { + thinking_budget?: integer +} + export interface InferenceToolCall { id: Id function: InferenceToolCallFunction diff --git a/specification/_doc_ids/table.csv b/specification/_doc_ids/table.csv index 33b64d6604..cbf54e5ec3 100644 --- a/specification/_doc_ids/table.csv +++ b/specification/_doc_ids/table.csv @@ -271,6 +271,7 @@ get-transform,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operat get-trial-status,https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-license-get-trial-status,https://www.elastic.co/guide/en/elasticsearch/reference/8.18/get-trial-status.html, googlevertexai-locations,https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations,, googlevertexai-models,https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api,, +googlevertexai-thinking,https://ai.google.dev/gemini-api/docs/thinking#set-budget,, googleaistudio-models,https://ai.google.dev/gemini-api/docs/models,, graph,https://www.elastic.co/docs/explore-analyze/visualize/graph,, graph-explore-api,https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-graph,https://www.elastic.co/guide/en/elasticsearch/reference/8.18/graph-explore-api.html, diff --git a/specification/inference/_types/CommonTypes.ts b/specification/inference/_types/CommonTypes.ts index bd1e6e8006..07d5d374c8 100644 --- a/specification/inference/_types/CommonTypes.ts +++ b/specification/inference/_types/CommonTypes.ts @@ -1377,6 +1377,19 @@ export class GoogleVertexAITaskSettings { * For a `rerank` task, the number of the top N documents that should be returned. */ top_n?: integer + /** + * For a `completion` or `chat_completion` task, allows configuration of the thinking features for the model. + * Refer to the Google documentation for the allowable configurations for each model type. + * @ext_doc_id googlevertexai-thinking + */ + thinking_config?: ThinkingConfig +} + +export class ThinkingConfig { + /** + * Indicates the desired thinking budget in tokens. + */ + thinking_budget?: integer } export enum GoogleVertexAITaskType {