Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

LlamaCloud (LlamaParse)

Parse documents with LlamaParse and retrieve content from synced LlamaCloud Index v2 indexes.

Connectors

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

Connector
Authentication

LlamaCloud (LlamaParse)

API Key

LlamaCloud (LlamaParse)

Connect to LlamaCloud to parse documents and retrieve content from synced indexes.

Set up in LlamaCloud (LlamaParse)

  1. Prepare the LlamaCloud (LlamaParse) account or service that the workflow will access. Grant access to the required resources and operations.

  2. API Key: Create or copy an API key from the LlamaCloud dashboard.

Set up in StackAI

  1. Open Settings → Connections, add a connection, and select LlamaCloud (LlamaParse).

  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 or copy an API key from the LlamaCloud dashboard. Provider instructions.

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 LlamaCloud (LlamaParse) 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

Upload document for parsing

Download a document from a public URL, upload it to LlamaParse, and start an asynchronous parsing job.

Inputs

Field
Type
Required
Description

Document URL

string

Yes

Public HTTPS URL of the document to download and parse.

Parsing tier

select (string)

No

Quality and cost tier used to parse the document. Available values: Fast, Cost effective, Agentic, Agentic Plus. Default: agentic.

Parser version

string

No

LlamaParse parser version; keep latest unless reproducibility requires a dated version. Default: latest.

Organization ID

select (string)

No

Organization containing the target project when explicit organization scoping is needed. Options load from the selected connection.

Project ID

select (string)

No

Project that should own the parsing job when the API key can access more than one project. Options load from the selected connection.

Outputs

Field
Type
Description

Job ID

string

Identifier for checking status and retrieving results.

Project ID

string

Project that owns the parsing job.

Status

string

Initial parsing status.

Get parsing job status

Check the current state of a LlamaParse job without downloading its parsed content.

Inputs

Field
Type
Required
Description

Job ID

string

Yes

Parse job to inspect.

Organization ID

select (string)

No

Organization containing the job when explicit organization scoping is needed. Options load from the selected connection.

Project ID

select (string)

No

Project containing the job when explicit project scoping is needed. Options load from the selected connection.

Outputs

Field
Type
Description

Job ID

string

Identifier of the checked parse job.

Project ID

string

Project containing the parse job.

Status

string

Current parsing state.

Is terminal

boolean

Whether the job has finished and will not change state again.

Is successful

boolean

Whether parsing completed successfully.

Error message

string

Sanitized guidance when the job failed or was cancelled.

Get parsed result as markdown

Retrieve the complete markdown produced by a completed LlamaParse job.

Inputs

Field
Type
Required
Description

Job ID

string

Yes

Completed parse job whose markdown should be returned.

Organization

select (string)

No

Organization containing the job when explicit organization scoping is needed. Options load from the selected connection.

Project

select (string)

No

Project containing the job when explicit scoping is needed. Options load from the selected connection.

Outputs

Field
Type
Description

Job ID

string

Identifier of the completed parse job.

Status

string

Parsing state associated with the markdown.

Markdown

string

Complete parsed document in markdown format.

Retrieve from index

Search a pre-created and synced LlamaCloud Index V2 index without changing it.

Inputs

Field
Type
Required
Description

Organization ID

select (string)

No

Organization containing the index when explicit organization scoping is needed. Options load from the selected connection.

Project ID

select (string)

No

Project containing the index when explicit project scoping is needed. Options load from the selected connection.

Index

select (string)

Yes

Pre-created and synced LlamaCloud Index V2 index to search. Options load from the selected connection.

Query

textarea

Yes

Natural-language question or search query.

Maximum results

integer

No

Maximum number of relevant chunks to return. Default: 10.

Score threshold

number

No

Optional minimum relevance score for returned chunks.

Outputs

Field
Type
Description

Results

object_array

Retrieved chunks and their relevance data.

Count

integer

Number of chunks returned.

Get parsed result as JSON

Retrieve structured page and item data from a completed LlamaParse job.

Inputs

Field
Type
Required
Description

Job ID

string

Yes

Completed parse job whose structured output should be returned.

Organization

select (string)

No

Organization containing the job when explicit organization scoping is needed. Options load from the selected connection.

Project

select (string)

No

Project containing the job when explicit scoping is needed. Options load from the selected connection.

Outputs

Field
Type
Description

Job ID

string

Identifier of the completed parse job.

Status

string

Parsing state associated with the structured result.

Pages

object_array

Structured page records with parsed items or page-level errors.

Job metadata

object

Optional structured metadata returned for the parse job.

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.

Last updated

Was this helpful?