Executes a deployed Prompt and returns the result.

The list of inputs defined in the Prompt's deployment with their corresponding values.

Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment

"Optionally include a unique identifier for tracking purposes. Must be unique for a given prompt deployment.

Execute Prompt

Executes a deployed Prompt and streams back the results.

Execute Prompt Stream

Executes a deployed Workflow and returns its outputs.

The list of inputs defined in the Workflow's Deployment with their corresponding values.

Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment

Optionally include a unique identifier for tracking purposes. Must be unique for a given workflow deployment.

Execute Workflow

Executes a deployed Workflow and streams back its results.

Optionally specify which events you want to receive. Defaults to only WORKFLOW events. Note that the schema of non-WORKFLOW events is unstable and should be used with caution.

Execute Workflow Stream

The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.

Additional configuration that can be used to control what's included in the response.

Generate

Generate Stream

Search

Feedback regarding the quality of previously generated completions

Submit Completion Actuals

Feedback regarding the quality of an output on a previously executed workflow.

Submit Workflow Execution Actuals

The initial index from which to return the results.

Which field to use when ordering the results.

List

Used to retrieve a deployment given its ID or name.

Either the Deployment's ID or its unique name

Retrieve

Retrieve Provider Payload

Deployments

Used to retrieve a list of Document Indexes.

Index Using Instructor Model

Index Using a Sentence Transformers Model

Index Using OpenAI Model

Create

Used to retrieve a Document Index given its ID or name.

Either the Document Index's ID or its unique name

Used to fully update a Document Index given its ID.

A UUID string identifying this document index.

Update

Used to delete a Document Index given its ID.

Destroy

Used to partial update a Document Index given its ID.

Partial Update

Document Indexes

Used to list documents. Optionally filter on supported fields.

Filter down to only those documents that are included in the specified index. You may provide either the Vellum-generated ID or the unique name of the index specified upon initial creation.

Retrieve a Document, keying off of either its Vellum-generated ID or its external ID.

Delete a Document, keying off of either its Vellum-generated ID or its external ID.

Update a Document, keying off of either its Vellum-generated ID or its external ID. Particularly useful for updating its metadata.

UploadDocumentBodyRequest

Upload

Documents

Add Entity To Folder

Folder Entities

Basic Example

Chat History Example

Upsert Sandbox Scenario

Deletes an existing scenario from a sandbox, keying off of the provided scenario id.

An id identifying the scenario that you'd like to delete

Delete Sandbox Scenario

Sandboxes

Trigger a Test Suite and create a new Test Suite Run

A UUID string identifying this test suite run.

List Executions

Test Suite Runs

List the Test Cases associated with a Test Suite

A UUID string identifying this test suite.

List Test Suite Test Cases

Upsert Test Suite Test Case

Deletes an existing test case for a test suite, keying off of the test case id.

An id identifying the test case that you'd like to delete

Delete Test Suite Test Case

Test Suites

Used to retrieve a workflow deployment given its ID or name.

Either the Workflow Deployment's ID or its unique name

Workflow Deployments

A Node Result Event emitted from an API Node.

ApiNodeResult

ApiNodeResultData

ArrayChatMessageContent

ArrayChatMessageContentItem

ArrayChatMessageContentItemRequest

ArrayChatMessageContentRequest

ArrayEnum

ArrayVariableValueItem

ChatHistoryEnum

A user input representing a list of chat messages

ChatHistoryInputRequest

The variable's name, as defined in the deployment.

ChatHistoryVariableValue

ChatMessage

An optional identifier representing who or what generated this message.

ChatMessageContent

ChatMessageContentRequest

ChatMessageRequest

ChatMessageRole

CodeExecutionNodeArrayResult

CodeExecutionNodeChatHistoryResult

CodeExecutionNodeErrorResult

CodeExecutionNodeFunctionCallResult

CodeExecutionNodeJsonResult

CodeExecutionNodeNumberResult

A Node Result Event emitted from a Code Execution Node.

CodeExecutionNodeResult

CodeExecutionNodeResultData

CodeExecutionNodeResultOutput

CodeExecutionNodeSearchResultsResult

CodeExecutionNodeStringResult

A Node Result Event emitted from a Conditional Node.

ConditionalNodeResult

ConditionalNodeResultData

DeploymentProviderPayloadResponse

DeploymentRead

A human-readable label for the deployment

A name that uniquely identifies this deployment within its workspace

DocumentDocumentToDocumentIndex

Vellum-generated ID that uniquely identifies this link.

Vellum-generated ID that uniquely identifies the index this document is included in.

DocumentIndexRead

A human-readable label for the document index

A name that uniquely identifies this index within its workspace

Configuration representing how documents should be indexed

DocumentRead

The unique id of this document as it exists in the user's system.

A human-readable label for the document. Defaults to the originally uploaded file's file name.

A previously supplied JSON object containing metadata that can be filtered on when searching.

DocumentStatus

EnrichedNormalizedCompletion

The Vellum-generated ID of the completion.

The external ID that was originally provided along with the generation request, which uniquely identifies this generation in an external system.

The logprobs of the completion. Only present if specified in the original request options.

The ID of the model version used to generate this completion.

EntityStatus

EnvironmentEnum

ErrorEnum

ErrorVariableValue

ErrorVellumValue

ExecutePromptApiErrorResponse

ExecutePromptEvent

ExecutePromptResponse

ExecuteWorkflowErrorResponse

ExecuteWorkflowResponse

ExecuteWorkflowStreamErrorResponse

ExecuteWorkflowWorkflowResultEvent

ExecutionArrayVellumValue

The variable's uniquely identifying internal id.

ExecutionChatHistoryVellumValue

ExecutionErrorVellumValue

ExecutionFunctionCallVellumValue

ExecutionJsonVellumValue

ExecutionNumberVellumValue

ExecutionSearchResultsVellumValue

ExecutionStringVellumValue

ExecutionVellumValue

ExternalTestCaseExecution

The output values of a callable that was executed against a Test Case outside of Vellum

ExternalTestCaseExecutionRequest

FinishReasonEnum

FulfilledEnum

The final data event returned indicating that the stream has ended and all final resolved values from the model can be found.

FulfilledExecutePromptEvent

The successful response from the model containing all of the resolved values generated by the prompt.

FulfilledExecutePromptResponse

The successful response from the Workflow execution containing the produced outputs.

FulfilledExecuteWorkflowWorkflowResultEvent

FulfilledFunctionCall

FulfilledFunctionCallRequest

FulfilledPromptExecutionMeta

An event that indicates that the node has fulfilled its execution.

FulfilledWorkflowNodeResultEvent

FunctionCall

A function call value that is used in a chat message.

FunctionCallChatMessageContent

FunctionCallChatMessageContentRequest

FunctionCallChatMessageContentValue

FunctionCallChatMessageContentValueRequest

FunctionCallEnum

FunctionCallVariableValue

FunctionCallVellumValue

GenerateErrorResponse

GenerateOptionsRequest

GenerateRequest

Key/value pairs for each template variable defined in the deployment's prompt.

Optionally include a unique identifier for each generation, as represented outside of Vellum. Note that this should generally be a list of length one.

GenerateResponse

GenerateResult

An object containing the resulting generation. This key will be absent if the LLM provider experienced an error.

An object containing details about the error that occurred. This key will be absent if the LLM provider did not experience an error.

Introduction

API Reference

Delete Test Suite Test Case

Path parameters

1	curl -X DELETE https://api.vellum.ai/v1/test-suites/id/test-cases/test_case_id \
2	-H "X_API_KEY: <apiKey>"