> 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/jina-ai.md).

# Jina AI

Create text embeddings, rerank documents, classify text, read public web pages, and search the web with Jina AI.

### Connectors

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

| Connector | Authentication |
| --------- | -------------- |
| Jina AI   | API Key        |

#### Jina AI

Connect to Jina AI to create text embeddings, rerank documents, classify text, read public web pages, and search the web.

**Set up in Jina AI**

1. Prepare the Jina AI account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create a Jina AI API key, then paste it here.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Jina AI**.
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 a Jina AI API key, then paste it here. [Provider instructions](https://jina.ai/api-dashboard/). |

#### 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 **Jina AI** 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

#### Generate Text Embeddings

Turn one or more text passages into numeric vectors.

**Inputs**

| Field                | Type            | Required | Description                                                                                                              |
| -------------------- | --------------- | -------- | ------------------------------------------------------------------------------------------------------------------------ |
| Texts                | array           | Yes      | Text passages to embed, one complete passage per list item.                                                              |
| Model                | select (string) | No       | Jina embedding model used to create the vectors. Options load from the selected connection. Default: jina-embeddings-v3. |
| Task                 | select (string) | No       | How Jina should optimize compatible embeddings. Options load from the selected connection.                               |
| Dimensions           | integer         | No       | Optional vector length for models that support flexible dimensions. Minimum: 1. Maximum: 2048.                           |
| Truncate Long Inputs | boolean         | No       | Trim text over the model token limit instead of failing. Default: false.                                                 |

**Outputs**

| Field        | Type    | Description                                    |
| ------------ | ------- | ---------------------------------------------- |
| Embeddings   | array   | Float vectors aligned with the input passages. |
| Model        | string  | Model that generated the vectors.              |
| Total Tokens | integer | Tokens Jina reports for the request.           |

#### Rerank Documents

Order text documents by relevance to a query.

**Inputs**

| Field             | Type            | Required | Description                                                                                                             |
| ----------------- | --------------- | -------- | ----------------------------------------------------------------------------------------------------------------------- |
| Query             | string          | Yes      | Question or search phrase used to judge relevance.                                                                      |
| Documents         | array           | Yes      | Documents to rank. Each list item is one complete document.                                                             |
| Model             | select (string) | No       | Jina reranking model used to score the documents. Options load from the selected connection. Default: jina-reranker-v3. |
| Maximum Results   | integer         | No       | Highest-ranked documents to return.                                                                                     |
| Return Embeddings | boolean         | No       | Include document embeddings when the selected model supports them. Default: false.                                      |

**Outputs**

| Field            | Type          | Description                                                      |
| ---------------- | ------------- | ---------------------------------------------------------------- |
| Ranked Documents | object\_array | Documents ordered by relevance with scores and original indexes. |
| Model            | string        | Model that scored the documents.                                 |
| Total Tokens     | integer       | Tokens Jina reports for the request.                             |

#### Read Web Page as Markdown

Fetch a public web page and return clean Markdown.

**Inputs**

| Field               | Type    | Required | Description                                                             |
| ------------------- | ------- | -------- | ----------------------------------------------------------------------- |
| Public Page URL     | string  | Yes      | Public HTTP or HTTPS page to read.                                      |
| Maximum Tokens      | integer | No       | Limit the returned page content size. Minimum: 500.                     |
| Target CSS Selector | string  | No       | CSS selector for the part of the page to retain.                        |
| Bypass Cache        | boolean | No       | Request a fresh page instead of a cached Reader result. Default: false. |

**Outputs**

| Field            | Type     | Description                                         |
| ---------------- | -------- | --------------------------------------------------- |
| Source URL       | string   | Canonical source URL returned by Reader.            |
| Title            | string   | Page title when Reader finds one.                   |
| Description      | string   | Page description when available.                    |
| Markdown Content | textarea | Clean Markdown extracted from the page.             |
| Published Time   | datetime | Page publication time when available.               |
| Warning          | string   | Reader warning about incomplete or unusual content. |

#### Search the Web

Search public web pages and return structured content.

**Inputs**

| Field           | Type    | Required | Description                                                                |
| --------------- | ------- | -------- | -------------------------------------------------------------------------- |
| Query           | string  | Yes      | Words or question to search for on the public web.                         |
| Site Filter     | string  | No       | Limit results to one site or domain.                                       |
| Starting Page   | integer | No       | Search results page to request. Minimum: 1. Default: 1.                    |
| Maximum Results | integer | No       | Number of search results to request. Minimum: 1. Maximum: 20. Default: 10. |

**Outputs**

| Field          | Type          | Description                                                      |
| -------------- | ------------- | ---------------------------------------------------------------- |
| Search Results | object\_array | Public pages matching the query with source details and content. |
| Next Page      | integer       | Page number to request next when more results may be available.  |

#### Classify Text

Classify text against candidate labels without training a classifier.

**Inputs**

| Field            | Type            | Required | Description                                                                                                                |
| ---------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------- |
| Text             | textarea        | Yes      | Text to classify.                                                                                                          |
| Candidate Labels | array           | Yes      | Possible labels. Each list item is one complete label.                                                                     |
| Model            | select (string) | No       | Jina text model used for zero-shot classification. Options load from the selected connection. Default: jina-embeddings-v3. |

**Outputs**

| Field           | Type          | Description                                         |
| --------------- | ------------- | --------------------------------------------------- |
| Predicted Label | string        | Highest-scoring candidate label.                    |
| Confidence      | number        | Score for the predicted label.                      |
| Label Scores    | object\_array | All candidate labels with their scores.             |
| Total Tokens    | integer       | Tokens Jina reports for the classification request. |

### 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/jina-ai.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.
