Vellum AI website screenshot

Vellum AI

Vellum AI is an LLM development platform that helps product and engineering teams build, evaluate, deploy, and monitor LLM-powered applications. The platform centers on prompt engineering, a visual Workflows builder for agentic and multi-step pipelines, evaluation suites with dataset management, retrieval-augmented generation, and production observability with logs, traces, and metrics. Target customers are AI product teams at startups and enterprises that need version control, collaboration, and vendor-neutral access across OpenAI, Anthropic, Google, Mistral, and open models. Vellum exposes a REST API plus Python and TypeScript SDKs, runs in cloud and self-hosted deployments, and offers tiered pricing for Pro/Business/Enterprise. Note: as of 2026 the vellum.ai marketing surface has been refocused on a personal AI assistant product; the developer platform documented here remains the LLM application stack.

1 APIs 0 Features
LLM PlatformPrompt EngineeringWorkflowsEvaluationsLLM OpsRAGObservabilityDatasetsDeploymentsMulti-ProviderAgent BuilderSelf-Hosted

APIs

Vellum LLM Platform API

The Vellum REST API exposes prompts, workflows, evaluations, datasets, document indexes, deployments, and execution endpoints so developers can run versioned LLM pipelines from ...

Collections

Client SDK

OPEN

Pricing Plans

Vellum Plans Pricing

1 plans

PLANS

Rate Limits

Vellum Rate Limits

2 limits

RATE LIMITS

FinOps

Vellum Finops

FINOPS

Resources

🔗
Website
Website
🔗
Documentation
Documentation
📰
Blog
Blog
👥
GitHubOrganization
GitHubOrganization
💰
Pricing
Pricing
📝
Signup
Signup
🔗
Login
Login
📜
TermsOfService
TermsOfService
📜
PrivacyPolicy
PrivacyPolicy
🔗
Twitter
Twitter
🔗
LinkedIn
LinkedIn
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Client SDK
  version: 1.0.0
items:
- info:
    name: ''
    type: folder
  items:
  - info:
      name: Execute Prompt
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/execute-prompt
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Prompt and returns the result.
  - info:
      name: Execute Prompt Stream
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/execute-prompt-stream
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Prompt and streams back the results.
  - info:
      name: Submit Completion Actuals
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/submit-completion-actuals
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Used to submit feedback regarding the quality of previously generated completions.
  - info:
      name: Execute Workflow
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/execute-workflow
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Workflow and returns its outputs.
  - info:
      name: Execute Workflow Async
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/execute-workflow-async
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Workflow asynchronously and returns the execution ID.
  - info:
      name: Execute Workflow Stream
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/execute-workflow-stream
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Workflow and streams back its results.
  - info:
      name: Submit Workflow Execution Actuals
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/submit-workflow-execution-actuals
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: "    Used to submit feedback regarding the quality of previous workflow execution and its outputs.\n\n    **Note:**\
      \ Uses a base url of `https://predict.vellum.ai`.    "
  - info:
      name: Search
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/search
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Perform a search against a document index.
- info:
    name: subpackage_deployments
    type: folder
  items:
  - info:
      name: Retrieve Provider Payload
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/deployments/provider-payload
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: 'Given a set of input variable values, compile the exact payload that Vellum would send to the configured model
      provider

      for execution if the execute-prompt endpoint had been invoked. Note that this endpoint does not actually execute the

      prompt or make an API call to the model provider.


      This endpoint is useful if you don''t want to proxy LLM provider requests through Vellum and prefer to send them directly

      to the provider yourself. Note that no guarantees are made on the format of this API''s resp'
  - info:
      name: List
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
      - name: status
        value: ''
        type: query
        description: status
    docs: Used to list all Prompt Deployments.
  - info:
      name: Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
    docs: Used to retrieve a Prompt Deployment given its ID or name.
  - info:
      name: Retrieve Prompt Deployment Release
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments/:id/releases/:release_id_or_release_tag
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
      - name: release_id_or_release_tag
        value: ''
        type: path
        description: Either the UUID of Prompt Deployment Release you'd like to retrieve, or the name of a Release Tag that's
          pointing to the Prompt Deployment Release you'd like to retrieve.
    docs: Retrieve a specific Prompt Deployment Release by either its UUID or the name of a Release Tag that points to it.
  - info:
      name: Retrieve Deployment Release Tag
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments/:id/release-tags/:name
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
      - name: name
        value: ''
        type: path
        description: The name of the Release Tag associated with this Deployment that you'd like to retrieve.
    docs: Retrieve a Deployment Release Tag by tag name, associated with a specified Deployment.
  - info:
      name: Update Deployment Release Tag
      type: http
    http:
      method: PATCH
      url: https://predict.vellum.ai/v1/deployments/:id/release-tags/:name
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
      - name: name
        value: ''
        type: path
        description: The name of the Release Tag associated with this Deployment that you'd like to update.
      body:
        type: json
        data: '{}'
    docs: Updates an existing Release Tag associated with the specified Prompt Deployment.
  - info:
      name: List Deployment Release Tags
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments/:id/release-tags
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
      - name: source
        value: ''
        type: query
    docs: List Release Tags associated with the specified Prompt Deployment
  - info:
      name: Deployment History Item Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/deployments/:id/history/:history_id_or_release_tag
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: history_id_or_release_tag
        value: ''
        type: path
        description: Either the UUID of Deployment History Item you'd like to retrieve, or the name of a Release Tag that's
          pointing to the Deployment History Item you'd like to retrieve.
      - name: id
        value: ''
        type: path
        description: Either the Prompt Deployment's ID or its unique name
    docs: 'DEPRECATED: This endpoint is deprecated and will be removed in a future release. Please use the

      `retrieve_prompt_deployment_release` xendpoint instead.'
- info:
    name: subpackage_sandboxes
    type: folder
  items:
  - info:
      name: Deploy Prompt
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/sandboxes/:id/prompts/:prompt_variant_id/deploy
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: A UUID string identifying this sandbox.
      - name: prompt_variant_id
        value: ''
        type: path
        description: An ID identifying the Prompt you'd like to deploy.
      body:
        type: json
        data: '{}'
    docs: Deploy Prompt
  - info:
      name: Upsert Sandbox Scenario
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/sandboxes/:id/scenarios
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: A UUID string identifying this sandbox.
      body:
        type: json
        data: '{}'
    docs: 'Upserts a new scenario for a sandbox, keying off of the optionally provided scenario id.


      If an id is provided and has a match, the scenario will be updated. If no id is provided or no match

      is found, a new scenario will be appended to the end.


      Note that a full replacement of the scenario is performed, so any fields not provided will be removed

      or overwritten with default values.'
  - info:
      name: Delete Sandbox Scenario
      type: http
    http:
      method: DELETE
      url: https://predict.vellum.ai/v1/sandboxes/:id/scenarios/:scenario_id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: A UUID string identifying this sandbox.
      - name: scenario_id
        value: ''
        type: path
        description: An id identifying the scenario that you'd like to delete
    docs: Deletes an existing scenario from a sandbox, keying off of the provided scenario id.
- info:
    name: subpackage_workflows
    type: folder
  items:
  - info:
      name: Workflow Execution Status
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflows/executions/:execution_id/status
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: execution_id
        value: ''
        type: path
    docs: 'Checks if a workflow execution is currently executing (not fulfilled, not rejected, and has no end time).

      Uses the ClickHouse Prime summary materialized view.'
- info:
    name: subpackage_workflowSandboxes
    type: folder
  items:
  - info:
      name: Deploy Workflow
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/workflow-sandboxes/:id/deploy
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: A UUID string identifying this workflow sandbox.
      body:
        type: json
        data: '{}'
    docs: Deploy Workflow
- info:
    name: subpackage_workflowDeployments
    type: folder
  items:
  - info:
      name: Execute Stream
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/execute-stream
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      body:
        type: json
        data: '{}'
    docs: Executes a deployed Workflow and streams back its results.
  - info:
      name: List
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: has_story_config
        value: ''
        type: query
        description: has_story_config
      - name: is_public
        value: ''
        type: query
        description: is_public
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: 'Specifies the ordering of the returned Workflow Deployments. Valid values are:

          - `created` - Orders by creation time in ascending order.

          - `-created` - Orders by creation time in descending order. (default)

          - `name` - Orders by name in ascending order.

          - `-name` - Orders by name in descending order.


          Compound orderings are supported by separating fields with commas, e.g., `-created,name`.

          '
      - name: owned_by
        value: ''
        type: query
        description: owned_by
      - name: status
        value: ''
        type: query
        description: status
    docs: Used to list all Workflow Deployments.
  - info:
      name: List Workflow Deployment Releases
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/releases
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
    docs: List the Releases of the specified Workflow Deployment for the current Environment.
  - info:
      name: Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
    docs: Used to retrieve a workflow deployment given its ID or name.
  - info:
      name: Retrieve Workflow Deployment Release
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/releases/:release_id_or_release_tag
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      - name: release_id_or_release_tag
        value: ''
        type: path
        description: Either the UUID of Workflow Deployment Release you'd like to retrieve, or the name of a Release Tag that's
          pointing to the Workflow Deployment Release you'd like to retrieve.
    docs: Retrieve a specific Workflow Deployment Release by either its UUID or the name of a Release Tag that points to it.
  - info:
      name: Retrieve Workflow Release Tag
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/release-tags/:name
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      - name: name
        value: ''
        type: path
        description: The name of the Release Tag associated with this Workflow Deployment that you'd like to retrieve.
    docs: Retrieve a Workflow Release Tag by tag name, associated with a specified Workflow Deployment.
  - info:
      name: Update Workflow Release Tag
      type: http
    http:
      method: PATCH
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/release-tags/:name
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      - name: name
        value: ''
        type: path
        description: The name of the Release Tag associated with this Workflow Deployment that you'd like to update.
      body:
        type: json
        data: '{}'
    docs: Updates an existing Release Tag associated with the specified Workflow Deployment.
  - info:
      name: List Workflow Release Tags
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/release-tags
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
      - name: source
        value: ''
        type: query
    docs: List Release Tags associated with the specified Workflow Deployment
  - info:
      name: Workflow Deployment History Item Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/history/:history_id_or_release_tag
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: history_id_or_release_tag
        value: ''
        type: path
        description: Either the UUID of Workflow Deployment History Item you'd like to retrieve, or the name of a Release
          Tag that's pointing to the Workflow Deployment History Item you'd like to retrieve.
      - name: id
        value: ''
        type: path
        description: Either the Workflow Deployment's ID or its unique name
    docs: 'DEPRECATED: This endpoint is deprecated and will be removed in a future release. Please use the

      `retrieve_workflow_deployment_release` endpoint instead.'
  - info:
      name: List Workflow Deployment Event Executions
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/execution-events
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
      - name: filters
        value: ''
        type: query
      - name: limit
        value: ''
        type: query
        description: Number of executions to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the executions.
      - name: ordering
        value: ''
        type: query
    docs: List Workflow Deployment Event Executions
  - info:
      name: Workflow Deployment Event Execution
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-deployments/:id/execution-events/:execution_id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: execution_id
        value: ''
        type: path
      - name: id
        value: ''
        type: path
    docs: Workflow Deployment Event Execution
- info:
    name: subpackage_workflowExecutions
    type: folder
  items:
  - info:
      name: Retrieve Workflow Execution Detail
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/workflow-executions/:execution_id/detail
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: execution_id
        value: ''
        type: path
      - name: prev_span_id
        value: ''
        type: query
        description: Optional keyset cursor span_id to continue from (exclusive)
      - name: span_limit
        value: ''
        type: query
        description: Maximum number of spans to return (for lazy loading)
    docs: Retrieve Workflow Execution Detail
- info:
    name: subpackage_events
    type: folder
  items:
  - info:
      name: Create
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/monitoring/v1/events
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Accept an event or list of events and publish them to ClickHouse for analytics processing.
- info:
    name: subpackage_documentIndexes
    type: folder
  items:
  - info:
      name: Add Document
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/document-indexes/:id/documents/:document_id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: document_id
        value: ''
        type: path
        description: Either the Vellum-generated ID or the originally supplied external_id that uniquely identifies the Document
          you'd like to add.
      - name: id
        value: ''
        type: path
        description: Either the Vellum-generated ID or the originally specified name that uniquely identifies the Document
          Index to which you'd like to add the Document.
    docs: Adds a previously uploaded Document to the specified Document Index.
  - info:
      name: Remove Document
      type: http
    http:
      method: DELETE
      url: https://predict.vellum.ai/v1/document-indexes/:id/documents/:document_id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: document_id
        value: ''
        type: path
        description: Either the Vellum-generated ID or the originally supplied external_id that uniquely identifies the Document
          you'd like to remove.
      - name: id
        value: ''
        type: path
        description: Either the Vellum-generated ID or the originally specified name that uniquely identifies the Document
          Index from which you'd like to remove a Document.
    docs: Removes a Document from a Document Index without deleting the Document itself.
  - info:
      name: List
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/document-indexes
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
      - name: search
        value: ''
        type: query
        description: Search for document indices by name or label
      - name: status
        value: ''
        type: query
        description: 'Filter down to only document indices that have a status matching the status specified


          * `ACTIVE` - Active

          * `ARCHIVED` - Archived

          * `PENDING_DELETION` - Pending Deletion'
    docs: Used to retrieve a list of Document Indexes.
  - info:
      name: Create
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/document-indexes
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: json
        data: '{}'
    docs: Creates a new document index.
  - info:
      name: Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/document-indexes/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Document Index's ID or its unique name
      - name: mask_indexing_config
        value: ''
        type: query
        description: Whether to mask the indexing configuration in the response
    docs: Used to retrieve a Document Index given its ID or name.
  - info:
      name: Update
      type: http
    http:
      method: PUT
      url: https://predict.vellum.ai/v1/document-indexes/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Document Index's ID or its unique name
      body:
        type: json
        data: '{}'
    docs: Used to fully update a Document Index given its ID or name.
  - info:
      name: Partial Update
      type: http
    http:
      method: PATCH
      url: https://predict.vellum.ai/v1/document-indexes/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Document Index's ID or its unique name
      body:
        type: json
        data: '{}'
    docs: Used to partial update a Document Index given its ID or name.
  - info:
      name: Destroy
      type: http
    http:
      method: DELETE
      url: https://predict.vellum.ai/v1/document-indexes/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: Either the Document Index's ID or its unique name
    docs: Used to delete a Document Index given its ID or name.
- info:
    name: subpackage_documents
    type: folder
  items:
  - info:
      name: Upload
      type: http
    http:
      method: POST
      url: https://predict.vellum.ai/v1/upload-document
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      body:
        type: multipart-form
        data:
        - name: add_to_index_names
          type: text
          value: ''
        - name: external_id
          type: text
          value: ''
        - name: label
          type: text
          value: ''
        - name: contents
          type: text
          value: ''
        - name: url
          type: text
          value: ''
        - name: keywords
          type: text
          value: ''
        - name: metadata
          type: text
          value: ''
    docs: 'Upload a document to be indexed and used for search.


      **Note:** Uses a base url of `https://documents.vellum.ai`.

      '
  - info:
      name: Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/documents/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
    docs: Retrieve a Document, keying off of either its Vellum-generated ID or its external ID.
  - info:
      name: Partial Update
      type: http
    http:
      method: PATCH
      url: https://predict.vellum.ai/v1/documents/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
      body:
        type: multipart-form
        data:
        - name: label
          type: text
          value: ''
        - name: status
          type: text
          value: ''
        - name: keywords
          type: text
          value: ''
        - name: metadata
          type: text
          value: ''
    docs: Update a Document, keying off of either its Vellum-generated ID or its external ID. Particularly useful for updating
      its metadata.
  - info:
      name: Destroy
      type: http
    http:
      method: DELETE
      url: https://predict.vellum.ai/v1/documents/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
    docs: Delete a Document, keying off of either its Vellum-generated ID or its external ID.
  - info:
      name: List
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/documents
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: document_index_id
        value: ''
        type: query
        description: 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.
      - name: limit
        value: ''
        type: query
        description: Number of results to return per page.
      - name: offset
        value: ''
        type: query
        description: The initial index from which to return the results.
      - name: ordering
        value: ''
        type: query
        description: Which field to use when ordering the results.
      - name: search
        value: ''
        type: query
        description: A search term.
    docs: Used to list documents. Optionally filter on supported fields.
- info:
    name: subpackage_uploadedFiles
    type: folder
  items:
  - info:
      name: Retrieve
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/uploaded-files/:id
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
        description: A UUID string identifying this uploaded file.
      - name: expiry_seconds
        value: ''
        type: query
        description: The number of seconds until the signed URL expires. Must be > 0 and <= 2592000 (30 days). Non-numeric
          or out-of-range values fall back to the default (604800 seconds or 7 days).
    docs: Retrieve a previously uploaded file by its ID
- info:
    name: subpackage_testSuites
    type: folder
  items:
  - info:
      name: List Test Suite Test Cases
      type: http
    http:
      method: GET
      url: https://predict.vellum.ai/v1/test-suites/:id/test-cases
      headers:
      - name: X-API-KEY
        value: ''
      - name: X-API-Version
        value: ''
      params:
      - name: id
        value: ''
        type: path
     

# --- truncated at 32 KB (39 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/vellum/refs/heads/main/apis.yml