Skip to main content
VLM Run logo
  • Category: ai document extraction
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 11
  • Triggers: 0
  • Slug: VLM_RUN
  • Version: 00000000_00

Tools

Slug: VLM_RUN_CREATE_SKILLCreate a reusable skill from exactly one uploaded zip, prompt, or chat session.

Input Parameters

string
Skill name; required with file_id and optional for prompt or session sources.
string
Prompt that becomes SKILL.md; provide exactly one skill source.
string
Uploaded skill zip ID; provide exactly one of file_id, prompt, or session_id.
boolean
Whether the new skill is publicly accessible.
string
Chat session whose history becomes the skill source; provide exactly one skill source.
string
Skill description; required with file_id and optional for prompt or session sources.
object
Optional output JSON schema; allowed only with a prompt source.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_DISCOVER_EXTRACTION_SCHEMASList supported structured-extraction domains, or return the full JSON schema for one domain when domain is provided.

Input Parameters

object
Typed generation options to apply when resolving a domain schema. Used only when domain is provided.
string
Domain identifier to resolve, such as document.invoice. Omit it to list all supported extraction domains.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_EXECUTE_AGENTStart a VLM Run agent execution from an existing agent name or inline configuration over multimodal inputs. Execution may consume credits and is asynchronous by default; poll the returned ID with VLM_RUN_GET_RUN.

Input Parameters

boolean
Run asynchronously when true.
string
Orion model override; omit to use the skill or agent default.
object
Inline execution behavior used to identify or configure the agent.
object
Named typed media content or plain JSON values matching the agent input schema.
object
Caller metadata and data-governance settings.
string
Name and optional version of an existing agent, such as agent-name:latest.
string
Caller-selected unique request identifier.
string
HTTPS URL called when asynchronous execution completes.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_EXTRACT_STRUCTURED_JSONStart structured JSON extraction from images, a document, a video, or audio using a domain, custom schema, or skill. Extraction may consume credits; document, video, and audio runs are asynchronous by default, so poll the returned prediction ID with VLM_RUN_GET_RUN.

Input Parameters

string
Public media URL; for document, video, or audio use exactly one of url or file_id.
boolean
Override asynchronous processing; omit to preserve the modality-specific provider default.
string
Structured-extraction model or quality variant, such as vlm-1:fast.
object
Generation, schema, skill, quality, and media options.
string
Extraction domain; required for audio and optional for other modalities when config supplies a skill or custom schema.
array
Image URLs or base64-encoded images; required only for image modality.
string
Uploaded file ID; for document, video, or audio use exactly one of file_id or url.
object
Metadata and data-handling preferences for the prediction.
string ("image" | "document" | "video" | "audio")
required
Media type to process; selects the matching generation endpoint.
string
Caller-selected request identifier, sent upstream as id.
string
Callback URL for asynchronous completion delivery.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_FIND_FILESList uploaded files or find one by file ID or MD5 hash. In list mode, use offset and limit until has_more is false.

Input Parameters

integer
Maximum files in list mode (1-1000).
integer
Zero-based list offset; sent upstream as skip and used only when no selector is supplied.
string
Exact uploaded file ID; mutually exclusive with md5_hash.
string
Exact 32-character MD5 hex digest used for deduplication lookup; mutually exclusive with file_id.
boolean
Whether ID lookup should generate a temporary public URL.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_FIND_SKILLSList VLM Run skills or find one exact skill by ID, name, and optional version. In list mode, continue from next_offset while has_more is true.

Input Parameters

string
Exact skill name; mutually exclusive with skill_id.
integer
Maximum skills to return in list mode (1-1000).
integer
Zero-based list offset; used only when no selector is supplied.
boolean
Request grouped skill results in list mode.
string
Optional exact skill version used only with name.
string ("created_at" | "updated_at" | "name")
Sort field in list mode.
string
Exact skill ID; mutually exclusive with name.
boolean
Sort descending in list mode.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_GET_RUNGet the current status and result of one structured-extraction prediction or agent execution; call repeatedly to poll asynchronous work.

Input Parameters

string
required
Prediction or agent execution ID returned by a run or list tool.
string ("prediction" | "agent_execution")
required
Kind of run to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_LIST_AGENTSReturn agents available to the connected account for selection before execution.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_LIST_ARTIFACTSList artifact metadata belonging to exactly one chat session or agent execution. Use offset and limit to traverse pages until has_more is false.

Input Parameters

integer
Maximum artifacts to return (1-1000).
integer
Zero-based artifact offset sent upstream as offset.
string
Parent chat session ID; provide exactly one of session_id or execution_id.
string
Parent agent execution ID; provide exactly one of execution_id or session_id.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_LIST_RUNSList structured-extraction predictions or agent executions for the connected account. Use offset and limit to traverse pages until has_more is false.

Input Parameters

integer
Maximum runs to return (1-1000).
integer
Zero-based number of runs to skip; sent upstream as skip.
string ("prediction" | "agent_execution")
required
Kind of run to list.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: VLM_RUN_UPLOAD_FILEUpload a local file to VLM Run for extraction, agent input, or skill creation. Retain the returned file ID for tools that consume uploaded files.

Input Parameters

object
required
Local file to upload through Composio’s file store.
string ("assistants" | "batch" | "fine-tune" | "vision" | "datasets")
Provider purpose assigned to the uploaded file.
boolean
Whether to include a temporary public URL in the response.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not