Service: aiplatform.googleapis.com
To call this service, we recommend that you use the Google-provided client libraries. If your application needs to use your own libraries to call this service, use the following information when you make the API requests.
Discovery document
A Discovery Document is a machine-readable specification for describing and consuming REST APIs. It is used to build client libraries, IDE plugins, and other tools that interact with Google APIs. One service may provide multiple discovery documents. This service provides the following discovery documents:
Service endpoint
A service endpoint is a base URL that specifies the network address of an API service. One service might have multiple service endpoints. This service has the following service endpoint and all URIs below are relative to this service endpoint:
REST Resource: v1.media
| Methods | |
|---|---|
upload |
POST /v1/{parent}/ragFiles:upload POST /upload/v1/{parent}/ragFiles:upload Upload a file into a RagCorpus. |
REST Resource: v1.projects
| Methods | |
|---|---|
getCacheConfig |
GET /v1/{name} Gets a GenAI cache config. |
updateCacheConfig |
PATCH /v1/{cacheConfig.name} Updates a cache config. |
REST Resource: v1.projects.locations
| Methods | |
|---|---|
augmentPrompt |
POST /v1/{parent}:augmentPrompt Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses. |
corroborateContent |
POST /v1/{parent}:corroborateContent Given an input text, it returns a score that evaluates the factuality of the text. |
evaluateInstances |
POST /v1/{location}:evaluateInstances Evaluates instances based on a given metric. |
retrieveContexts |
POST /v1/{parent}:retrieveContexts Retrieves relevant contexts for a query. |
REST Resource: v1.projects.locations.cachedContents
| Methods | |
|---|---|
create |
POST /v1/{parent}/cachedContents Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage. |
delete |
DELETE /v1/{name} Deletes cached content |
get |
GET /v1/{name} Gets cached content configurations |
list |
GET /v1/{parent}/cachedContents Lists cached contents in a project |
patch |
PATCH /v1/{cachedContent.name} Updates cached content configurations |
REST Resource: v1.projects.locations.endpoints
| Methods | |
|---|---|
fetchPredictOperation |
POST /v1/{endpoint}:fetchPredictOperation Fetch an asynchronous online prediction operation. |
generateContent |
POST /v1/{model}:generateContent Generate content with multimodal inputs. |
predict |
POST /v1/{endpoint}:predict Perform an online prediction. |
predictLongRunning |
POST /v1/{endpoint}:predictLongRunning |
serverStreamingPredict |
POST /v1/{endpoint}:serverStreamingPredict Perform a server-side streaming online prediction request for Vertex LLM streaming. |
streamGenerateContent |
POST /v1/{model}:streamGenerateContent Generate content with multimodal inputs with streaming support. |
REST Resource: v1.projects.locations.endpoints.chat
| Methods | |
|---|---|
completions |
POST /v1/{endpoint}/chat/completions Exposes an OpenAI-compatible endpoint for chat completions. |
REST Resource: v1.projects.locations.models
| Methods | |
|---|---|
getIamPolicy |
POST /v1/{resource}:getIamPolicy Gets the access control policy for a resource. |
setIamPolicy |
POST /v1/{resource}:setIamPolicy Sets the access control policy on the specified resource. |
testIamPermissions |
POST /v1/{resource}:testIamPermissions Returns permissions that a caller has on the specified resource. |
REST Resource: v1.projects.locations.operations
| Methods | |
|---|---|
cancel |
POST /v1/{name}:cancel Starts asynchronous cancellation on a long-running operation. |
delete |
DELETE /v1/{name} Deletes a long-running operation. |
get |
GET /v1/{name} Gets the latest state of a long-running operation. |
list |
GET /v1/{name}/operations Lists operations that match the specified filter in the request. |
wait |
POST /v1/{name}:wait Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. |
REST Resource: v1.projects.locations.publishers.models
| Methods | |
|---|---|
fetchPredictOperation |
POST /v1/{endpoint}:fetchPredictOperation Fetch an asynchronous online prediction operation. |
generateContent |
POST /v1/{model}:generateContent Generate content with multimodal inputs. |
predict |
POST /v1/{endpoint}:predict Perform an online prediction. |
predictLongRunning |
POST /v1/{endpoint}:predictLongRunning |
serverStreamingPredict |
POST /v1/{endpoint}:serverStreamingPredict Perform a server-side streaming online prediction request for Vertex LLM streaming. |
streamGenerateContent |
POST /v1/{model}:streamGenerateContent Generate content with multimodal inputs with streaming support. |
REST Resource: v1.projects.locations.ragCorpora
| Methods | |
|---|---|
create |
POST /v1/{parent}/ragCorpora Creates a RagCorpus. |
delete |
DELETE /v1/{name} Deletes a RagCorpus. |
get |
GET /v1/{name} Gets a RagCorpus. |
list |
GET /v1/{parent}/ragCorpora Lists RagCorpora in a Location. |
patch |
PATCH /v1/{ragCorpus.name} Updates a RagCorpus. |
REST Resource: v1.projects.locations.ragCorpora.ragFiles
| Methods | |
|---|---|
delete |
DELETE /v1/{name} Deletes a RagFile. |
get |
GET /v1/{name} Gets a RagFile. |
import |
POST /v1/{parent}/ragFiles:import Import files from Google Cloud Storage or Google Drive into a RagCorpus. |
list |
GET /v1/{parent}/ragFiles Lists RagFiles in a RagCorpus. |
REST Resource: v1.projects.locations.reasoningEngines
| Methods | |
|---|---|
create |
POST /v1/{parent}/reasoningEngines Creates a reasoning engine. |
delete |
DELETE /v1/{name} Deletes a reasoning engine. |
get |
GET /v1/{name} Gets a reasoning engine. |
list |
GET /v1/{parent}/reasoningEngines Lists reasoning engines in a location. |
patch |
PATCH /v1/{reasoningEngine.name} Updates a reasoning engine. |
query |
POST /v1/{name}:query Queries using a reasoning engine. |
streamQuery |
POST /v1/{name}:streamQuery Streams queries using a reasoning engine. |
REST Resource: v1.projects.locations.tuningJobs
| Methods | |
|---|---|
cancel |
POST /v1/{name}:cancel Cancels a TuningJob. |
create |
POST /v1/{parent}/tuningJobs Creates a TuningJob. |
get |
GET /v1/{name} Gets a TuningJob. |
list |
GET /v1/{parent}/tuningJobs Lists TuningJobs in a Location. |
rebaseTunedModel |
POST /v1/{parent}/tuningJobs:rebaseTunedModel Rebase a TunedModel. |
REST Resource: v1beta1.media
| Methods | |
|---|---|
upload |
POST /v1beta1/{parent}/ragFiles:upload POST /upload/v1beta1/{parent}/ragFiles:upload Upload a file into a RagCorpus. |
REST Resource: v1beta1.projects
| Methods | |
|---|---|
getCacheConfig |
GET /v1beta1/{name} Gets a GenAI cache config. |
updateCacheConfig |
PATCH /v1beta1/{cacheConfig.name} Updates a cache config. |
REST Resource: v1beta1.projects.locations
| Methods | |
|---|---|
augmentPrompt |
POST /v1beta1/{parent}:augmentPrompt Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses. |
corroborateContent |
POST /v1beta1/{parent}:corroborateContent Given an input text, it returns a score that evaluates the factuality of the text. |
evaluateInstances |
POST /v1beta1/{location}:evaluateInstances Evaluates instances based on a given metric. |
retrieveContexts |
POST /v1beta1/{parent}:retrieveContexts Retrieves relevant contexts for a query. |
REST Resource: v1beta1.projects.locations.cachedContents
| Methods | |
|---|---|
create |
POST /v1beta1/{parent}/cachedContents Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage. |
delete |
DELETE /v1beta1/{name} Deletes cached content |
get |
GET /v1beta1/{name} Gets cached content configurations |
list |
GET /v1beta1/{parent}/cachedContents Lists cached contents in a project |
patch |
PATCH /v1beta1/{cachedContent.name} Updates cached content configurations |
REST Resource: v1beta1.projects.locations.endpoints
| Methods | |
|---|---|
countTokens |
POST /v1beta1/{endpoint}:countTokens Perform a token counting. |
fetchPredictOperation |
POST /v1beta1/{endpoint}:fetchPredictOperation Fetch an asynchronous online prediction operation. |
generateContent |
POST /v1beta1/{model}:generateContent Generate content with multimodal inputs. |
getIamPolicy |
POST /v1beta1/{resource}:getIamPolicy Gets the access control policy for a resource. |
predict |
POST /v1beta1/{endpoint}:predict Perform an online prediction. |
predictLongRunning |
POST /v1beta1/{endpoint}:predictLongRunning |
serverStreamingPredict |
POST /v1beta1/{endpoint}:serverStreamingPredict Perform a server-side streaming online prediction request for Vertex LLM streaming. |
setIamPolicy |
POST /v1beta1/{resource}:setIamPolicy Sets the access control policy on the specified resource. |
streamGenerateContent |
POST /v1beta1/{model}:streamGenerateContent Generate content with multimodal inputs with streaming support. |
testIamPermissions |
POST /v1beta1/{resource}:testIamPermissions Returns permissions that a caller has on the specified resource. |
REST Resource: v1beta1.projects.locations.endpoints.chat
| Methods | |
|---|---|
completions |
POST /v1beta1/{endpoint}/chat/completions Exposes an OpenAI-compatible endpoint for chat completions. |
REST Resource: v1beta1.projects.locations.extensions
| Methods | |
|---|---|
delete |
DELETE /v1beta1/{name} Deletes an Extension. |
execute |
POST /v1beta1/{name}:execute Executes the request against a given extension. |
get |
GET /v1beta1/{name} Gets an Extension. |
import |
POST /v1beta1/{parent}/extensions:import Imports an Extension. |
list |
GET /v1beta1/{parent}/extensions Lists Extensions in a location. |
patch |
PATCH /v1beta1/{extension.name} Updates an Extension. |
query |
POST /v1beta1/{name}:query Queries an extension with a default controller. |
REST Resource: v1beta1.projects.locations.models
| Methods | |
|---|---|
getIamPolicy |
POST /v1beta1/{resource}:getIamPolicy Gets the access control policy for a resource. |
setIamPolicy |
POST /v1beta1/{resource}:setIamPolicy Sets the access control policy on the specified resource. |
testIamPermissions |
POST /v1beta1/{resource}:testIamPermissions Returns permissions that a caller has on the specified resource. |
REST Resource: v1beta1.projects.locations.operations
| Methods | |
|---|---|
cancel |
POST /v1beta1/{name}:cancel Starts asynchronous cancellation on a long-running operation. |
delete |
DELETE /v1beta1/{name} Deletes a long-running operation. |
get |
GET /v1beta1/{name} Gets the latest state of a long-running operation. |
list |
GET /v1beta1/{name}/operations Lists operations that match the specified filter in the request. |
wait |
POST /v1beta1/{name}:wait Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. |
REST Resource: v1beta1.projects.locations.publishers
| Methods | |
|---|---|
getIamPolicy |
POST /v1beta1/{resource}:getIamPolicy Gets the access control policy for a resource. |
REST Resource: v1beta1.projects.locations.publishers.models
| Methods | |
|---|---|
countTokens |
POST /v1beta1/{endpoint}:countTokens Perform a token counting. |
fetchPredictOperation |
POST /v1beta1/{endpoint}:fetchPredictOperation Fetch an asynchronous online prediction operation. |
generateContent |
POST /v1beta1/{model}:generateContent Generate content with multimodal inputs. |
getIamPolicy |
POST /v1beta1/{resource}:getIamPolicy Gets the access control policy for a resource. |
predict |
POST /v1beta1/{endpoint}:predict Perform an online prediction. |
predictLongRunning |
POST /v1beta1/{endpoint}:predictLongRunning |
serverStreamingPredict |
POST /v1beta1/{endpoint}:serverStreamingPredict Perform a server-side streaming online prediction request for Vertex LLM streaming. |
streamGenerateContent |
POST /v1beta1/{model}:streamGenerateContent Generate content with multimodal inputs with streaming support. |
REST Resource: v1beta1.projects.locations.ragCorpora
| Methods | |
|---|---|
create |
POST /v1beta1/{parent}/ragCorpora Creates a RagCorpus. |
delete |
DELETE /v1beta1/{name} Deletes a RagCorpus. |
get |
GET /v1beta1/{name} Gets a RagCorpus. |
list |
GET /v1beta1/{parent}/ragCorpora Lists RagCorpora in a Location. |
patch |
PATCH /v1beta1/{ragCorpus.name} Updates a RagCorpus. |
REST Resource: v1beta1.projects.locations.ragCorpora.ragFiles
| Methods | |
|---|---|
delete |
DELETE /v1beta1/{name} Deletes a RagFile. |
get |
GET /v1beta1/{name} Gets a RagFile. |
import |
POST /v1beta1/{parent}/ragFiles:import Import files from Google Cloud Storage or Google Drive into a RagCorpus. |
list |
GET /v1beta1/{parent}/ragFiles Lists RagFiles in a RagCorpus. |
REST Resource: v1beta1.projects.locations.reasoningEngines
| Methods | |
|---|---|
create |
POST /v1beta1/{parent}/reasoningEngines Creates a reasoning engine. |
delete |
DELETE /v1beta1/{name} Deletes a reasoning engine. |
get |
GET /v1beta1/{name} Gets a reasoning engine. |
list |
GET /v1beta1/{parent}/reasoningEngines Lists reasoning engines in a location. |
patch |
PATCH /v1beta1/{reasoningEngine.name} Updates a reasoning engine. |
query |
POST /v1beta1/{name}:query Queries using a reasoning engine. |
streamQuery |
POST /v1beta1/{name}:streamQuery Streams queries using a reasoning engine. |
REST Resource: v1beta1.projects.locations.tuningJobs
| Methods | |
|---|---|
cancel |
POST /v1beta1/{name}:cancel Cancels a TuningJob. |
create |
POST /v1beta1/{parent}/tuningJobs Creates a TuningJob. |
get |
GET /v1beta1/{name} Gets a TuningJob. |
list |
GET /v1beta1/{parent}/tuningJobs Lists TuningJobs in a Location. |
rebaseTunedModel |
POST /v1beta1/{parent}/tuningJobs:rebaseTunedModel Rebase a TunedModel. |