# LlamaParse

> LlamaParse v2 jobs, files, saved configurations and webhook configurations.

App · 20 actions. Web page: https://docs.lodol.com/docs/integrations/llamaparse

## Actions

### Cancel parse job

Cancel parse job.

**Inputs**

- Job id (`job_id`, text, required): Job id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "error_message": "example",
    "id": "example",
    "name": "example",
    "project_id": "example",
    "status": "CANCELLED",
    "tier": "example",
    "updated_at": "example",
    "usage": {
      "credits": 1.0,
      "parse_credits": 1.0
    },
    "user_metadata": {}
  }
}
```

### Create configuration

Create configuration.

**Inputs**

- Name (`name`, text, required): Human-readable name for this configuration.
- Parameters (`parameters`, object, required): Product-specific configuration parameters.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "name": "example",
    "parameters": {},
    "product_type": "classify_v2",
    "updated_at": "example",
    "version": "example"
  }
}
```

### Create parse job

Create parse job.

**Inputs**

- Tier (`tier`, text, required): Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy). One of: `fast`, `cost_effective` (Cost effective), `agentic`, `agentic_plus` (Agentic plus).
- Version (`version`, text, required): Choose a supported version for the selected tier, or Latest to use its current version.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.
- Agentic options (`agentic_options`, object): Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus). These options customize how the AI processes and interprets document content. Only applicable when using non-fast tiers.
- Client name (`client_name`, text): Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2'
- Configuration (`configuration_id`, text): ID of a saved parse configuration. When set, `tier` and `version` default to the saved configuration's values , omit them or pass `'configured'`.
- Crop box (`crop_box`, object): Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges
- Disable cache (`disable_cache`, true/false): Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results
- Fast options (`fast_options`, object): Options for fast tier parsing (rule-based, no AI). Fast tier uses deterministic algorithms for text extraction without AI enhancement. It's the fastest and most cost-effective option, best suited for simple documents with standard layouts. Currently has no configurable options but reserved for future expansion.
- File (`file_id`, text): ID of an existing file in the project to parse. Mutually exclusive with source_url
- Http proxy (`http_proxy`, text): HTTP/HTTPS proxy for fetching source_url. Ignored if using file_id
- Input options (`input_options`, object): Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type
- Output options (`output_options`, object): Output formatting options for markdown, text, and extracted images
- Page ranges (`page_ranges`, object): Page selection: limit total pages or specify exact pages to process
- Processing control (`processing_control`, object): Job execution controls including timeouts and failure thresholds
- Processing options (`processing_options`, object): Document processing options including OCR, table extraction, and chart parsing
- Source url (`source_url`, text): Public URL of the document to parse. Mutually exclusive with file_id
- User metadata (`user_metadata`, object): Arbitrary key/value tags to attach to this job. Returned when retrieving the job. Not searchable. Limits apply to the number of entries and the length of keys and values; oversized metadata is rejected.
- Webhook configuration ids (`webhook_configuration_ids`, list): IDs of saved webhook configurations to notify for this job.
- Webhook configurations (`webhook_configurations`, list): Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "error_message": "example",
    "id": "example",
    "name": "example",
    "project_id": "example",
    "status": "CANCELLED",
    "tier": "example",
    "updated_at": "example",
    "usage": {
      "credits": 1.0,
      "parse_credits": 1.0
    },
    "user_metadata": {}
  }
}
```

### Create webhook

Create webhook.

**Inputs**

- Webhook url (`webhook_url`, text, required): URL to receive webhook POST notifications.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.
- Webhook events (`webhook_events`, list): Events to subscribe to. If null, all events are delivered. An empty list subscribes to nothing and is rejected. One or more of: `batch.cancelled`, `batch.error`, `batch.pending`, `batch.running`, `batch.success`, `classify.cancelled`, `classify.error`, `classify.partial_success` (Classify.partial success), `classify.pending`, `classify.running`, and 28 more.
- Webhook headers (`webhook_headers`, object): Custom HTTP headers sent with each webhook request.
- Webhook output format (`webhook_output_format`, text): Response format sent to the webhook: 'string' (default) or 'json'. One of: `json`, `string`.
- Webhook signing secret (`webhook_signing_secret`, text): Shared secret used to sign deliveries to this endpoint. Write-only: it is never returned in responses.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "updated_at": "example",
    "webhook_events": [],
    "webhook_headers": {},
    "webhook_output_format": "example",
    "webhook_url": "example"
  }
}
```

### Delete configuration

Delete configuration.

**Inputs**

- Config id (`config_id`, text, required): Config id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "name": "example",
    "parameters": {},
    "product_type": "classify_v2",
    "updated_at": "example",
    "version": "example"
  }
}
```

### Delete file

Delete file.

**Inputs**

- File (`file_id`, text, required): File id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {}
}
```

### Delete parse job

Delete parse job.

**Inputs**

- Job id (`job_id`, text, required): Job id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "id": "example",
    "project_id": "example"
  }
}
```

### Delete webhook

Delete webhook.

**Inputs**

- Webhook id (`config_id`, text, required): Webhook id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {}
}
```

### Get configuration

Get configuration.

**Inputs**

- Config id (`config_id`, text, required): Config id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "name": "example",
    "parameters": {},
    "product_type": "classify_v2",
    "updated_at": "example",
    "version": "example"
  }
}
```

### Get file

Get file.

**Inputs**

- File (`file_id`, text, required): File id.
- Expand (`expand`, list): Fields to expand.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "download_url": {
      "expires_at": "example",
      "form_fields": {},
      "url": "example"
    },
    "expires_at": "example",
    "external_file_id": "example",
    "file_type": "example",
    "id": "example",
    "last_modified_at": "example",
    "name": "example",
    "project_id": "example",
    "purpose": "example"
  }
}
```

### Get parse job

Get parse job.

**Inputs**

- Job id (`job_id`, text, required): Job id.
- Expand (`expand`, list): Fields to include: text, markdown, items, metadata, forms, job_metadata, usage, text_content_metadata, markdown_content_metadata, items_content_metadata, metadata_content_metadata, forms_content_metadata, raw_words_content_metadata, xlsx_content_metadata, output_pdf_content_metadata, images_content_metadata. Metadata fields include presigned URLs.
- Image filenames (`image_filenames`, text): Filter to specific image filenames (optional). Example: image_0.png,image_1.jpg
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "forms": {
      "pages": []
    },
    "images_content_metadata": {
      "images": [],
      "total_count": 1
    },
    "items": {
      "pages": []
    },
    "job": {
      "created_at": "example",
      "error_message": "example",
      "id": "example",
      "name": "example",
      "project_id": "example",
      "status": "CANCELLED",
      "tier": "example",
      "updated_at": "example",
      "usage": {
        "credits": 1.0
      },
      "user_metadata": {}
    },
    "job_metadata": {},
    "markdown": {
      "pages": []
    },
    "markdown_full": "example",
    "metadata": {
      "usage": {
        "num_pages_billed": 1,
        "num_pages_extracted": 1
      }
    },
    "raw_parameters": {},
    "result_content_metadata": {},
    "text": {
      "pages": []
    },
    "text_full": "example"
  }
}
```

### Get webhook

Get webhook.

**Inputs**

- Webhook id (`config_id`, text, required): Webhook id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "updated_at": "example",
    "webhook_events": [],
    "webhook_headers": {},
    "webhook_output_format": "example",
    "webhook_url": "example"
  }
}
```

### List configurations

List configurations.

**Inputs**

- Latest only (`latest_only`, true/false): Return only the latest version per configuration name.
- Name (`name`, text): Filter by configuration name.
- Organization id (`organization_id`, text): Organization id.
- Page size (`page_size`, number): Number of items per page.
- Page token (`page_token`, text): Pagination token.
- Product type (`product_type`, list): Filter by one or more product types. Repeat the parameter for multiple values. One or more of: `classify_v2` (Classify v2), `extract_v2` (Extract v2), `parse_v2` (Parse v2), `split_v1` (Split v1), `spreadsheet_v1` (Spreadsheet v1), `unknown`.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "items": [],
    "next_page_token": "example"
  }
}
```

### List files

List files.

**Inputs**

- Expand (`expand`, list): Fields to expand on each file.
- External file id (`external_file_id`, text): Filter by external file ID.
- File ids (`file_ids`, list): Filter by specific file IDs.
- File name (`file_name`, text): Filter by file name (exact match).
- Order by (`order_by`, text): Order the results. One of 'name' (ascending), 'id' (ascending) or 'created_at' (descending). An explicit asc/desc modifier and multi-field ordering are not supported; anything else is rejected.
- Organization id (`organization_id`, text): Organization id.
- Page size (`page_size`, number): The maximum number of items to return. Defaults to 50, maximum is 1000.
- Page token (`page_token`, text): A page token received from a previous list call. Provide this to retrieve the subsequent page.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "items": [],
    "next_page_token": "example"
  }
}
```

### List parse jobs

List parse jobs.

**Inputs**

- Created at on or after (`created_at_on_or_after`, text): Include items created at or after this timestamp (inclusive)
- Created at on or before (`created_at_on_or_before`, text): Include items created at or before this timestamp (inclusive)
- Job ids (`job_ids`, list): Filter by specific job IDs
- Organization id (`organization_id`, text): Organization id.
- Page size (`page_size`, number): Number of items per page
- Page token (`page_token`, text): Token for pagination
- Project id (`project_id`, text): Project id.
- Status (`status`, text): Filter by job status (PENDING, RUNNING, COMPLETED, FAILED, CANCELLED). One of: `CANCELLED`, `COMPLETED`, `FAILED`, `PENDING`, `RUNNING`.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "items": [],
    "next_page_token": "example"
  }
}
```

### List parse versions

List parse versions.

**Inputs**: None.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "agentic": [],
    "agentic_plus": [],
    "cost_effective": [],
    "fast": [],
    "latest": {
      "agentic": "example",
      "agentic_plus": "example",
      "cost_effective": "example",
      "fast": "example"
    }
  }
}
```

### List webhooks

List webhooks.

**Inputs**

- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.

**Outputs**

- `data` (list): Api result.

**Example output**

```json
{
  "data": []
}
```

### Query files

Query files.

**Inputs**

- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.
- Filter (`filter`, object): Filter parameters for file queries.
- Order by (`order_by`, text): A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order.
- Page size (`page_size`, number): The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum.
- Page token (`page_token`, text): A page token, received from a previous list call. Provide this to retrieve the subsequent page.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "items": [],
    "next_page_token": "example"
  }
}
```

### Update configuration

Update configuration.

**Inputs**

- Config id (`config_id`, text, required): Config id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.
- Name (`name`, text): Updated name (omit to leave unchanged).
- Parameters (`parameters`, object): Updated parameters (omit to leave unchanged).

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "name": "example",
    "parameters": {},
    "product_type": "classify_v2",
    "updated_at": "example",
    "version": "example"
  }
}
```

### Update webhook

Update webhook.

**Inputs**

- Webhook id (`config_id`, text, required): Webhook id.
- Organization id (`organization_id`, text): Organization id.
- Project id (`project_id`, text): Project id.
- Webhook events (`webhook_events`, list): Updated event subscriptions. Omit to leave unchanged; [] is rejected. One or more of: `batch.cancelled`, `batch.error`, `batch.pending`, `batch.running`, `batch.success`, `classify.cancelled`, `classify.error`, `classify.partial_success` (Classify.partial success), `classify.pending`, `classify.running`, and 28 more.
- Webhook headers (`webhook_headers`, object): Updated headers.
- Webhook output format (`webhook_output_format`, text): Updated output format. One of: `json`, `string`.
- Webhook signing secret (`webhook_signing_secret`, text): Updated signing secret (write-only). Send to rotate the secret.
- Webhook url (`webhook_url`, text): Updated webhook URL.

**Outputs**

- `data` (object): Api result.

**Example output**

```json
{
  "data": {
    "created_at": "example",
    "id": "example",
    "updated_at": "example",
    "webhook_events": [],
    "webhook_headers": {},
    "webhook_output_format": "example",
    "webhook_url": "example"
  }
}
```
