> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/vlm.md).

# Vlm

Connect to VLM Run to manage files, run chat completions and image generation, and work with domain schemas from your AI workflows.

* Knowledge base source

## Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector | Authentication |
| --------- | -------------- |
| VLM       | API Token      |

### VLM

Connect to VLM for document processing, OCR, and document extraction.

#### Set up in Vlm

1. Create or sign in to your VLM account and open the API keys / dashboard section.
2. Generate an API key and copy it (store it securely).

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **VLM**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                                               |
| ------------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| API Token     | Yes      | The API token for VLM (vlm.run). You can create one in your VLM account settings. [Provider instructions](https://app.vlm.run/dashboard/settings/api_keys). |

**Provider documentation:** [Setup reference](https://docs.vlm.run/).

### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

## Use an action

1. Add the required **Vlm** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

## Actions

### Get Files

Get all files uploaded by the user with pagination.

#### Inputs

| Field | Type    | Required | Description                                        |
| ----- | ------- | -------- | -------------------------------------------------- |
| Skip  | integer | No       | Number of items to skip. Minimum: 0.0. Default: 0. |
| Limit | string  | No       | Maximum number of items to return. Default: 10.    |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Upload File

Upload a file.

#### Inputs

| Field        | Type   | Required | Description          |
| ------------ | ------ | -------- | -------------------- |
| Purpose      | string | No       | Default: assistants. |
| Request Body | object | No       |                      |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get File

Get a file by ID.

#### Inputs

| Field   | Type   | Required | Description |
| ------- | ------ | -------- | ----------- |
| File Id | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get File By Hash

Check if a file exists by its md5 hash.

#### Inputs

| Field     | Type   | Required | Description |
| --------- | ------ | -------- | ----------- |
| File Hash | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Generate Presigned Url

Generate a presigned URL for file upload.

#### Inputs

| Field        | Type   | Required | Description                                             |
| ------------ | ------ | -------- | ------------------------------------------------------- |
| Request Body | object | No       | Request for generating a presigned URL for file upload. |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Verify File Upload

Verify file upload after presigned URL upload.

#### Inputs

| Field   | Type   | Required | Description |
| ------- | ------ | -------- | ----------- |
| File Id | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Health

Use this tool to get health

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Chat Completions

Use this tool to post chat completions

#### Inputs

| Field        | Type   | Required | Description |
| ------------ | ------ | -------- | ----------- |
| Request Body | object | No       |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Models

List all available models.

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Model Info

Get model information.

#### Inputs

| Field | Type   | Required | Description |
| ----- | ------ | -------- | ----------- |
| Model | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Info

Use this tool to get info

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### List Domains

Get the list of supported domains.

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Domain Schema

Get the JSON schema for a given domain (document.invoice, document.receipt, etc).

#### Inputs

| Field        | Type   | Required | Description                                       |
| ------------ | ------ | -------- | ------------------------------------------------- |
| Request Body | object | No       | Request model for the hub schema: /v1/hub/schema. |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Image Generate

Generate structured prediction for the given image.

#### Inputs

| Field        | Type   | Required | Description                                          |
| ------------ | ------ | -------- | ---------------------------------------------------- |
| Request Body | object | No       | Request to the VLM API (i.e. structured prediction). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Schema Generate Image

Generate structured schema for the given image or images.

#### Inputs

| Field        | Type   | Required | Description                                                   |
| ------------ | ------ | -------- | ------------------------------------------------------------- |
| Request Body | object | No       | Request to the VLM API using an image (jpeg, png, gif, webp). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Document Generate

Generate structured prediction for the given document.

#### Inputs

| Field        | Type   | Required | Description                                                     |
| ------------ | ------ | -------- | --------------------------------------------------------------- |
| Request Body | object | No       | Request to the VLM API using a document (doc, docx, pptx, pdf). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Document Execute

Generate structured prediction for the given document using a custom agent.

#### Inputs

| Field        | Type   | Required | Description                  |
| ------------ | ------ | -------- | ---------------------------- |
| Request Body | object | No       | Request to execute an agent. |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Schema Generate Document

Generate structured schema for the given document.

#### Inputs

| Field        | Type   | Required | Description                                                     |
| ------------ | ------ | -------- | --------------------------------------------------------------- |
| Request Body | object | No       | Request to the VLM API using a document (doc, docx, pptx, pdf). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Video Generate

Generate structured prediction for the given video file.

#### Inputs

| Field        | Type   | Required | Description                                            |
| ------------ | ------ | -------- | ------------------------------------------------------ |
| Request Body | object | No       | Request to the Video API (i.e. structured prediction). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Audio Generate

Generate structured prediction for the given audio file.

#### Inputs

| Field        | Type   | Required | Description                                            |
| ------------ | ------ | -------- | ------------------------------------------------------ |
| Request Body | object | No       | Request to the Audio API (i.e. structured prediction). |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Agent Execute

Execute an agent.

#### Inputs

| Field        | Type   | Required | Description                  |
| ------------ | ------ | -------- | ---------------------------- |
| Request Body | object | No       | Request to execute an agent. |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Predictions

Get all predictions uploaded by the user with pagination.

#### Inputs

| Field | Type    | Required | Description                                        |
| ----- | ------- | -------- | -------------------------------------------------- |
| Skip  | integer | No       | Number of items to skip. Minimum: 0.0. Default: 0. |
| Limit | string  | No       | Maximum number of items to return. Default: 10.    |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Prediction

Get prediction JSON by request ID.

#### Inputs

| Field | Type   | Required | Description |
| ----- | ------ | -------- | ----------- |
| Id    | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Prediction Domain

Get the domain name and additional info for a prediction by its ID.

#### Inputs

| Field | Type   | Required | Description |
| ----- | ------ | -------- | ----------- |
| Id    | string | Yes      |             |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Health

Health check endpoint.

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Models

Get the list of supported models.

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Domains

Get the list of supported domains.

#### Inputs

No input fields are required in this catalog entry.

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

### Get Schema

Get the JSON schema for a given domain (document.invoice, document.receipt, etc).

#### Inputs

| Field        | Type   | Required | Description                                            |
| ------------ | ------ | -------- | ------------------------------------------------------ |
| Request Body | object | No       | Schema request model for internal schemas: /v1/schema. |

#### Outputs

| Field       | Type    | Description                  |
| ----------- | ------- | ---------------------------- |
| Status Code | integer | Status code of the response. |
| Headers     | dict    | Headers of the response.     |
| Body        | object  | Body of the response.        |

## Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/vlm.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
