> 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/upstage.md).

# Upstage

Parse documents, extract structured data, chat with Solar, and create embeddings.

## Connectors

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

| Connector | Authentication |
| --------- | -------------- |
| Upstage   | API Key        |

### Upstage

Connect to Upstage for document AI, Solar chat, and embeddings.

#### Set up in Upstage

1. Prepare the Upstage account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create an API key in the Upstage Console and paste it here.

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **Upstage**.
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 Key       | Yes      | Create an API key in the Upstage Console and paste it here. [Provider instructions](https://console.upstage.ai/api-keys). |

### 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 **Upstage** 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

### Parse Document

Parse a document into structured content.

#### Inputs

| Field               | Type            | Required | Description                                                                                               |
| ------------------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------- |
| Document URL        | string          | Yes      | Public HTTPS URL of a document no larger than 50 MiB.                                                     |
| Output Format       | select (string) | No       | Format for the parsed document content. Available values: Markdown, HTML, Plain Text. Default: markdown.  |
| OCR                 | select (string) | No       | Whether OCR is automatic or forced for every page. Available values: Automatic, Force OCR. Default: auto. |
| Include Coordinates | boolean         | No       | Include detected element coordinates. Default: false.                                                     |

#### Outputs

| Field        | Type    | Description                           |
| ------------ | ------- | ------------------------------------- |
| Content      | string  | Parsed document content.              |
| Elements     | array   | Detected document elements.           |
| Model        | string  | Model returned by Upstage.            |
| Billed Pages | integer | Number of billed pages when returned. |

### Run OCR

Recognize text in a document with OCR.

#### Inputs

| Field        | Type   | Required | Description                                           |
| ------------ | ------ | -------- | ----------------------------------------------------- |
| Document URL | string | Yes      | Public HTTPS URL of a document no larger than 50 MiB. |

#### Outputs

| Field        | Type    | Description                           |
| ------------ | ------- | ------------------------------------- |
| Text         | string  | Combined OCR text.                    |
| Pages        | array   | OCR results by page.                  |
| Billed Pages | integer | Number of billed pages when returned. |

### Extract Key Information

Extract schema-shaped data from a document.

#### Inputs

| Field              | Type    | Required | Description                                                      |
| ------------------ | ------- | -------- | ---------------------------------------------------------------- |
| Document URL       | string  | Yes      | Public HTTPS URL of the document.                                |
| JSON Schema        | object  | Yes      | JSON Schema describing the fields to extract.                    |
| Schema Name        | string  | No       | Short name for the extraction schema. Default: document\_schema. |
| Include Locations  | boolean | No       | Include source locations for extracted fields. Default: false.   |
| Include Confidence | boolean | No       | Include confidence for extracted fields. Default: false.         |
| Split Pages        | boolean | No       | Return extraction grouped by page. Default: false.               |
| Pages per Chunk    | integer | No       | Optional chunk size for long documents.                          |

#### Outputs

| Field          | Type   | Description                                   |
| -------------- | ------ | --------------------------------------------- |
| Extracted Data | object | Structured data matching the supplied schema. |
| Model          | string | Model used for extraction.                    |
| Usage          | object | Token usage when returned.                    |

### Generate Chat Completion

Generate a response with an Upstage Solar model.

#### Inputs

| Field                 | Type            | Required | Description                                                                                                         |
| --------------------- | --------------- | -------- | ------------------------------------------------------------------------------------------------------------------- |
| Prompt                | textarea        | Yes      | User prompt sent to Solar.                                                                                          |
| System Prompt         | textarea        | No       | Optional instructions for the model.                                                                                |
| Model                 | select (string) | No       | Current Solar chat model. Available values: Solar Pro 4, Solar Pro 3, Solar Pro 2, Solar Mini. Default: solar-pro4. |
| Temperature           | number          | No       | Randomness of the response. Default: 0.2.                                                                           |
| Maximum Output Tokens | integer         | No       | Maximum tokens generated. Default: 1024.                                                                            |
| Reasoning Effort      | select (string) | No       | Amount of reasoning used by supported models. Available values: Low, Medium, High. Default: medium.                 |

#### Outputs

| Field     | Type   | Description                        |
| --------- | ------ | ---------------------------------- |
| Content   | string | Generated response.                |
| Reasoning | string | Model reasoning when returned.     |
| Model     | string | Model that generated the response. |
| Choices   | array  | All generated choices.             |
| Usage     | object | Token usage when returned.         |

### Create Embeddings

Create an Embed 2 vector for text.

#### Inputs

| Field   | Type            | Required | Description                                                                                                                 |
| ------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------------- |
| Text    | textarea        | Yes      | Text to convert into an embedding.                                                                                          |
| Purpose | select (string) | No       | Whether the text is indexed content or a search query. Available values: Passage / Content, Search Query. Default: passage. |

#### Outputs

| Field      | Type   | Description                       |
| ---------- | ------ | --------------------------------- |
| Embeddings | array  | Embedding vectors in input order. |
| Model      | string | Embedding model used.             |
| Usage      | object | Token usage when returned.        |

## 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/upstage.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.
