> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pinkfish.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# reducto
> Document Intelligence API
**Server path:** `/reducto` | **Type:** Application | **PCID required:** Yes
## Tools
| Tool | Description |
| --------------------------------------------------- | -------------- |
| [`reducto_cancel_job`](#reducto_cancel_job) | Cancel Job |
| [`reducto_classify`](#reducto_classify) | Classify |
| [`reducto_edit`](#reducto_edit) | Edit |
| [`reducto_edit_async`](#reducto_edit_async) | Edit Async |
| [`reducto_extract`](#reducto_extract) | Extract |
| [`reducto_extract_async`](#reducto_extract_async) | Extract Async |
| [`reducto_get_job`](#reducto_get_job) | Retrieve Parse |
| [`reducto_list_jobs`](#reducto_list_jobs) | Get Jobs |
| [`reducto_parse`](#reducto_parse) | Parse |
| [`reducto_parse_async`](#reducto_parse_async) | Async Parse |
| [`reducto_pipeline`](#reducto_pipeline) | Pipeline |
| [`reducto_pipeline_async`](#reducto_pipeline_async) | Pipeline Async |
| [`reducto_split`](#reducto_split) | Split |
| [`reducto_split_async`](#reducto_split_async) | Split Async |
| [`reducto_upload`](#reducto_upload) | Upload |
***
## reducto\_cancel\_job
Cancel Job
**Parameters:**
| Parameter | Type | Required | Default | Description |
| --------- | ------ | -------- | ------- | ----------- |
| `job_id` | string | Yes | — | Job Id |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"job_id": {
"type": "string",
"description": "Job Id"
}
},
"required": [
"PCID",
"job_id"
]
}
```
***
## reducto\_classify
Classify
**Parameters:**
| Parameter | Type | Required | Default | Description | |
| ----------------------- | --------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
| `classification_schema` | object\[] | No | — | A list of classification categories and their matching criteria. | |
| `document_metadata` | string | null | No | — | Optional document-level metadata to include in classification prompts. |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions | |
| `page_range` | object | No | — | The page range to process (1-indexed). By default, the first 5 pages are used. If more than 25 pages are selected, only the first 25 (after sorting) are used. Only applies to PDFs; ignored for other document types. | |
| `persist_results` | boolean | No | — | If True, persist the results indefinitely. Defaults to False. | |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"classification_schema": {
"type": "array",
"items": {
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "The category name/label that documents will be classified into (e.g., 'invoice', 'contract', 'receipt')."
},
"criteria": {
"type": "array",
"items": {
"type": "string"
},
"description": "A list of criteria, keywords, or descriptions that define what characteristics a document must have to be classified into this category (e.g., ['contains billing information', 'has itemized charges'])."
}
},
"required": [
"category",
"criteria"
]
},
"description": "A list of classification categories and their matching criteria."
},
"document_metadata": {
"type": [
"string",
"null"
],
"description": "Optional document-level metadata to include in classification prompts."
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"page_range": {
"description": "The page range to process (1-indexed). By default, the first 5 pages are used. If more than 25 pages are selected, only the first 25 (after sorting) are used. Only applies to PDFs; ignored for other document types."
},
"persist_results": {
"type": "boolean",
"description": "If True, persist the results indefinitely. Defaults to False."
}
},
"required": [
"PCID",
"input"
]
}
```
***
## reducto\_edit
Edit
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------------- | --------- | -------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `document_url` | object | Yes | — | The URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document |
| `edit_instructions` | string | Yes | — | The instructions for the edit. |
| `edit_options` | object | No | — | Edit Options |
| `form_schema` | object\[] | No | — | Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes. Only works for PDFs. |
| `priority` | boolean | No | — | If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"document_url": {
"description": "The URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document"
},
"edit_instructions": {
"type": "string",
"description": "The instructions for the edit."
},
"edit_options": {
"type": "object",
"description": "Edit Options",
"properties": {
"color": {
"type": "string",
"description": "The color to use for edits, in hex format."
},
"font_size": {
"type": "number",
"description": "The font size (in points) to use for filled text fields. If not specified, font size is automatically calculated based on field dimensions."
},
"llm_provider_preference": {
"type": "string",
"description": "The LLM provider to use for edit processing. If not specified, defaults to 'google'",
"enum": [
"openai",
"anthropic",
"google"
]
},
"enable_overflow_pages": {
"type": "boolean",
"description": "If True, creates overflow pages for text that doesn't fit in form fields. Defaults to False."
},
"flatten": {
"type": "boolean",
"description": "If True, flattens form fields after filling, converting them to static content. Defaults to False."
}
}
},
"form_schema": {
"type": "array",
"items": {
"type": "object",
"properties": {
"bbox": {
"type": "object",
"description": "The bbox value"
},
"description": {
"type": "string",
"description": "Description of the widget extracted from the document"
},
"type": {
"type": "string",
"enum": [
"text",
"checkbox",
"radio",
"dropdown",
"barcode"
],
"description": "Type of the form widget"
},
"fill": {
"type": "boolean",
"description": "If True (default), the system will attempt to fill this widget. If False, the widget will be created but intentionally left unfilled."
},
"value": {
"type": "string",
"description": "If provided, this value will be used directly instead of attempting to intelligently determine the field value."
},
"font_size": {
"type": "number",
"description": "Font size in points for this specific field. Takes priority over the global font_size in EditOptions. If not set, falls back to the global font_size, then to auto-calculated sizing."
}
},
"required": [
"bbox",
"description",
"type"
]
},
"description": "Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes. Only works for PDFs."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
}
},
"required": [
"PCID",
"document_url",
"edit_instructions"
]
}
```
***
## reducto\_edit\_async
Edit Async
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------------- | --------- | -------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `document_url` | object | Yes | — | The URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document |
| `edit_instructions` | string | Yes | — | The instructions for the edit. |
| `edit_options` | object | No | — | Edit Options |
| `form_schema` | object\[] | No | — | Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes. Only works for PDFs. |
| `priority` | boolean | No | — | If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs. |
| `webhook` | object | No | — | The webhook value |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"document_url": {
"description": "The URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document"
},
"edit_instructions": {
"type": "string",
"description": "The instructions for the edit."
},
"edit_options": {
"type": "object",
"description": "Edit Options",
"properties": {
"color": {
"type": "string",
"description": "The color to use for edits, in hex format."
},
"font_size": {
"type": "number",
"description": "The font size (in points) to use for filled text fields. If not specified, font size is automatically calculated based on field dimensions."
},
"llm_provider_preference": {
"type": "string",
"description": "The LLM provider to use for edit processing. If not specified, defaults to 'google'",
"enum": [
"openai",
"anthropic",
"google"
]
},
"enable_overflow_pages": {
"type": "boolean",
"description": "If True, creates overflow pages for text that doesn't fit in form fields. Defaults to False."
},
"flatten": {
"type": "boolean",
"description": "If True, flattens form fields after filling, converting them to static content. Defaults to False."
}
}
},
"form_schema": {
"type": "array",
"items": {
"type": "object",
"properties": {
"bbox": {
"type": "object",
"description": "The bbox value"
},
"description": {
"type": "string",
"description": "Description of the widget extracted from the document"
},
"type": {
"type": "string",
"enum": [
"text",
"checkbox",
"radio",
"dropdown",
"barcode"
],
"description": "Type of the form widget"
},
"fill": {
"type": "boolean",
"description": "If True (default), the system will attempt to fill this widget. If False, the widget will be created but intentionally left unfilled."
},
"value": {
"type": "string",
"description": "If provided, this value will be used directly instead of attempting to intelligently determine the field value."
},
"font_size": {
"type": "number",
"description": "Font size in points for this specific field. Takes priority over the global font_size in EditOptions. If not set, falls back to the global font_size, then to auto-calculated sizing."
}
},
"required": [
"bbox",
"description",
"type"
]
},
"description": "Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes. Only works for PDFs."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"type": "object",
"description": "The webhook value",
"properties": {
"mode": {
"type": "string",
"description": "The mode to use for webhook delivery. Defaults to 'disabled'. We recommend using 'svix' for production environments.",
"enum": [
"disabled",
"svix",
"direct"
]
},
"url": {
"type": "string",
"description": "The URL to send the webhook to (if using direct webhoook)."
},
"metadata": {
"description": "JSON metadata included in webhook request body"
},
"channels": {
"type": "array",
"items": {
"type": "string"
},
"description": "A list of Svix channels the message will be delivered down, omit to send to all channels."
}
}
}
},
"required": [
"PCID",
"document_url",
"edit_instructions"
]
}
```
***
## reducto\_extract
Extract
**Parameters:**
| Parameter | Type | Required | Default | Description |
| --------- | ------ | -------- | ------- | ------------ |
| `body` | object | Yes | — | Request body |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"body": {
"description": "Request body"
}
},
"required": [
"PCID",
"body"
]
}
```
***
## reducto\_extract\_async
Extract Async
**Parameters:**
| Parameter | Type | Required | Default | Description |
| -------------- | ------ | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `async` | object | No | — | The async value |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `instructions` | object | No | — | The instructions value |
| `parsing` | object | No | — | The parsing value |
| `settings` | object | No | — | The settings value |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"async": {
"type": "object",
"description": "The async value",
"properties": {
"metadata": {
"description": "JSON metadata included in webhook request body. Defaults to None."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"description": "The webhook configuration for the asynchronous processing."
}
}
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"instructions": {
"type": "object",
"description": "The instructions value",
"properties": {
"schema": {
"description": "The JSON schema to use for the extraction."
},
"system_prompt": {
"type": "string",
"description": "The system prompt to use for the extraction."
}
}
},
"parsing": {
"type": "object",
"description": "The parsing value",
"properties": {
"enhance": {
"type": "object",
"description": "The enhance value"
},
"retrieval": {
"type": "object",
"description": "The retrieval value"
},
"formatting": {
"type": "object",
"description": "The formatting value"
},
"spreadsheet": {
"type": "object",
"description": "The spreadsheet value"
},
"settings": {
"type": "object",
"description": "The settings value"
}
}
},
"settings": {
"type": "object",
"description": "The settings value",
"properties": {
"include_images": {
"type": "boolean",
"description": "If True, include images in the extraction."
},
"optimize_for_latency": {
"type": "boolean",
"description": "If True, jobs will be processed with a higher throughput and priority at a higher cost. Defaults to False."
},
"array_extract": {
"type": "boolean",
"description": "If True, use array extraction."
},
"deep_extract": {
"type": "boolean",
"description": "If True, use Deep Extract, an agentic extraction mode that iteratively refines its output to achieve near-perfect accuracy. Best for complex documents where accuracy is critical."
},
"citations": {
"type": "object",
"description": "The citations value"
}
}
}
},
"required": [
"PCID",
"input"
]
}
```
***
## reducto\_get\_job
Retrieve Parse
**Parameters:**
| Parameter | Type | Required | Default | Description |
| --------- | ------ | -------- | ------- | ----------- |
| `job_id` | string | Yes | — | Job Id |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"job_id": {
"type": "string",
"description": "Job Id"
}
},
"required": [
"PCID",
"job_id"
]
}
```
***
## reducto\_list\_jobs
Get Jobs
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ----------------- | ------- | -------- | ------- | ---------------------------------------------------------------------------------------------- |
| `exclude_configs` | boolean | No | — | Exclude raw\_config from response to reduce size |
| `cursor` | string | No | — | Cursor for pagination. Use the next\_cursor from the previous response to fetch the next page. |
| `limit` | integer | No | — | Maximum number of jobs to return per page. Defaults to 100, max 500. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"exclude_configs": {
"type": "boolean",
"description": "Exclude raw_config from response to reduce size"
},
"cursor": {
"type": "string",
"description": "Cursor for pagination. Use the next_cursor from the previous response to fetch the next page."
},
"limit": {
"type": "integer",
"description": "Maximum number of jobs to return per page. Defaults to 100, max 500."
}
},
"required": [
"PCID"
]
}
```
***
## reducto\_parse
Parse
**Parameters:**
| Parameter | Type | Required | Default | Description |
| --------- | ------ | -------- | ------- | ------------ |
| `body` | object | Yes | — | Request body |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"body": {
"description": "Request body"
}
},
"required": [
"PCID",
"body"
]
}
```
***
## reducto\_parse\_async
Async Parse
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ---------------- | ------ | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `async` | object | No | — | The async value |
| `enhance` | object | No | — | The enhance value |
| `formatting` | object | No | — | The formatting value |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `queue_priority` | string | No | — | Customer-facing queue priority for parse jobs. |
| `retrieval` | object | No | — | The retrieval value |
| `settings` | object | No | — | The settings value |
| `spreadsheet` | object | No | — | The spreadsheet value |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"async": {
"type": "object",
"description": "The async value",
"properties": {
"metadata": {
"description": "JSON metadata included in webhook request body. Defaults to None."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"description": "The webhook configuration for the asynchronous processing."
}
}
},
"enhance": {
"type": "object",
"description": "The enhance value",
"properties": {
"agentic": {
"type": "array",
"description": "Agentic uses vision language models to enhance the accuracy of the output of different types of extraction. This will incur a cost and latency increase."
},
"summarize_figures": {
"type": "boolean",
"description": "If True, summarize figures using a small vision language model. Defaults to True."
},
"intelligent_ordering": {
"type": "boolean",
"description": "If True, use an advanced vision language model to improve reading order accuracy, with a small increase in latency. Defaults to False."
}
}
},
"formatting": {
"type": "object",
"description": "The formatting value",
"properties": {
"add_page_markers": {
"type": "boolean",
"description": "If True, add page markers to the output. Defaults to False. Useful for extracting data with page specific information."
},
"table_output_format": {
"type": "string",
"description": "The mode to use for table output. Defaults to dynamic, which returns md for simpler tables and html for more complex tables.",
"enum": [
"html",
"json",
"md",
"jsonbbox",
"dynamic",
"csv"
]
},
"merge_tables": {
"type": "boolean",
"description": "A flag to indicate if consecutive tables with the same number of columns should be merged. Defaults to False."
},
"include": {
"type": "array",
"items": {
"type": "string",
"enum": [
"change_tracking",
"highlight",
"comments",
"hyperlinks",
"signatures",
"ignore_watermarks"
]
},
"description": "A list of formatting to include in the output."
}
}
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"queue_priority": {
"type": "string",
"description": "Customer-facing queue priority for parse jobs.",
"enum": [
"auto",
"batch"
]
},
"retrieval": {
"type": "object",
"description": "The retrieval value",
"properties": {
"chunking": {
"type": "object",
"description": "The chunking value"
},
"filter_blocks": {
"type": "array",
"items": {
"type": "string",
"enum": [
"Header",
"Footer",
"Title",
"Section Header",
"Page Number",
"List Item",
"Figure",
"Table",
"Key Value",
"Text",
"Comment",
"Signature"
]
},
"description": "A list of block types to filter out from 'content' and 'embed' fields. By default, no blocks are filtered."
},
"embedding_optimized": {
"type": "boolean",
"description": "If True, use embedding optimized mode. Defaults to False."
}
}
},
"settings": {
"type": "object",
"description": "The settings value",
"properties": {
"ocr_system": {
"type": "string",
"description": "Standard is our best multilingual OCR system. Legacy only supports germanic languages and is available for backwards compatibility.",
"enum": [
"standard",
"legacy"
]
},
"extraction_mode": {
"type": "string",
"description": "The mode to use for text extraction from PDFs. OCR mode uses optical character recognition only. Hybrid mode combines OCR with embedded PDF text for best accuracy (default).",
"enum": [
"ocr",
"hybrid"
]
},
"force_url_result": {
"type": "boolean",
"description": "Force the result to be returned in URL form."
},
"force_file_extension": {
"type": "string",
"description": "Force the URL to be downloaded as a specific file extension (e.g. `.png`)."
},
"return_ocr_data": {
"type": "boolean",
"description": "If True, return OCR data in the result. Defaults to False."
},
"return_images": {
"type": "array",
"items": {
"type": "string",
"enum": [
"figure",
"table",
"page"
]
},
"description": "Whether to return images for the specified block types. 'page' returns full page images. By default, no images are returned."
},
"embed_pdf_metadata": {
"type": "boolean",
"description": "If True, embed OCR metadata into the returned PDF. Defaults to False."
},
"persist_results": {
"type": "boolean",
"description": "If True, persist the results indefinitely. Defaults to False."
},
"timeout": {
"type": "number",
"description": "The timeout for the job in seconds."
},
"page_range": {
"description": "The page range to process (1-indexed). By default, the entire document is processed. For spreadsheets, you can also provide a list of sheet names."
},
"document_password": {
"type": "string",
"description": "Password to decrypt password-protected documents."
}
}
},
"spreadsheet": {
"type": "object",
"description": "The spreadsheet value",
"properties": {
"split_large_tables": {
"type": "object",
"description": "Split Large Tables"
},
"include": {
"type": "array",
"items": {
"type": "string",
"enum": [
"cell_colors",
"formula",
"dropdowns"
]
},
"description": "Whether to include cell color, formula, and dropdown information in the output."
},
"clustering": {
"type": "string",
"description": "In a spreadsheet with different tables inside, we enable splitting up the tables by default. Accurate mode applies more powerful models for superior accuracy, at 5× the default per-cell rate. Disabling will register as one large table.",
"enum": [
"accurate",
"fast",
"disabled"
]
},
"exclude": {
"type": "array",
"items": {
"type": "string",
"enum": [
"hidden_sheets",
"hidden_rows",
"hidden_cols",
"styling",
"spreadsheet_images"
]
},
"description": "Whether to exclude hidden sheets, rows, or columns in the output."
}
}
}
},
"required": [
"PCID",
"input"
]
}
```
***
## reducto\_pipeline
Pipeline
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------- | ------ | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `pipeline_id` | string | Yes | — | The ID of the pipeline to use for the document. |
| `settings` | object | No | — | Settings for pipeline execution that override pipeline defaults. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"pipeline_id": {
"type": "string",
"description": "The ID of the pipeline to use for the document."
},
"settings": {
"type": "object",
"description": "Settings for pipeline execution that override pipeline defaults.",
"properties": {
"document_password": {
"type": "string",
"description": "Password to decrypt password-protected documents."
}
}
}
},
"required": [
"PCID",
"input",
"pipeline_id"
]
}
```
***
## reducto\_pipeline\_async
Pipeline Async
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------- | ------ | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `async` | object | No | — | The async value |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `pipeline_id` | string | Yes | — | The ID of the pipeline to use for the document. |
| `settings` | object | No | — | Settings for pipeline execution that override pipeline defaults. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"async": {
"type": "object",
"description": "The async value",
"properties": {
"metadata": {
"description": "JSON metadata included in webhook request body. Defaults to None."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"description": "The webhook configuration for the asynchronous processing."
}
}
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"pipeline_id": {
"type": "string",
"description": "The ID of the pipeline to use for the document."
},
"settings": {
"type": "object",
"description": "Settings for pipeline execution that override pipeline defaults.",
"properties": {
"document_password": {
"type": "string",
"description": "Password to decrypt password-protected documents."
}
}
}
},
"required": [
"PCID",
"input",
"pipeline_id"
]
}
```
***
## reducto\_split
Split
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------------- | --------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `parsing` | object | No | — | The parsing value |
| `settings` | object | No | — | The settings value |
| `split_description` | object\[] | Yes | — | The configuration options for processing the document. |
| `split_rules` | string | No | — | The prompt that describes rules for splitting the document. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"parsing": {
"type": "object",
"description": "The parsing value",
"properties": {
"enhance": {
"type": "object",
"description": "The enhance value"
},
"retrieval": {
"type": "object",
"description": "The retrieval value"
},
"formatting": {
"type": "object",
"description": "The formatting value"
},
"spreadsheet": {
"type": "object",
"description": "The spreadsheet value"
},
"settings": {
"type": "object",
"description": "The settings value"
}
}
},
"settings": {
"type": "object",
"description": "The settings value",
"properties": {
"table_cutoff": {
"type": "string",
"description": "If tables should be truncated to the first few rows or if all content should be preserved. truncate improves latency, preserve is recommended for cases where partition_key is being used and the partition_key may be included within the table. Defaults to truncate",
"enum": [
"truncate",
"preserve"
]
},
"allow_page_overlap": {
"type": "boolean",
"description": "If True, a page can belong to multiple categories/partitions. If False, each page must belong to exactly one category. Defaults to True."
}
}
},
"split_description": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The name value"
},
"description": {
"type": "string",
"description": "The description value"
},
"partition_key": {
"type": "string",
"description": "Partition Key"
}
},
"required": [
"name",
"description"
]
},
"description": "The configuration options for processing the document."
},
"split_rules": {
"type": "string",
"description": "The prompt that describes rules for splitting the document."
}
},
"required": [
"PCID",
"input",
"split_description"
]
}
```
***
## reducto\_split\_async
Split Async
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ------------------- | --------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `async` | object | No | — | The async value |
| `input` | object | Yes | — | For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions |
| `parsing` | object | No | — | The parsing value |
| `settings` | object | No | — | The settings value |
| `split_description` | object\[] | Yes | — | The configuration options for processing the document. |
| `split_rules` | string | No | — | The prompt that describes rules for splitting the document. |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"async": {
"type": "object",
"description": "The async value",
"properties": {
"metadata": {
"description": "JSON metadata included in webhook request body. Defaults to None."
},
"priority": {
"type": "boolean",
"description": "If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs."
},
"webhook": {
"description": "The webhook configuration for the asynchronous processing."
}
}
},
"input": {
"description": "For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only) For edit pipelines, this should be a string containing the edit instructions"
},
"parsing": {
"type": "object",
"description": "The parsing value",
"properties": {
"enhance": {
"type": "object",
"description": "The enhance value"
},
"retrieval": {
"type": "object",
"description": "The retrieval value"
},
"formatting": {
"type": "object",
"description": "The formatting value"
},
"spreadsheet": {
"type": "object",
"description": "The spreadsheet value"
},
"settings": {
"type": "object",
"description": "The settings value"
}
}
},
"settings": {
"type": "object",
"description": "The settings value",
"properties": {
"table_cutoff": {
"type": "string",
"description": "If tables should be truncated to the first few rows or if all content should be preserved. truncate improves latency, preserve is recommended for cases where partition_key is being used and the partition_key may be included within the table. Defaults to truncate",
"enum": [
"truncate",
"preserve"
]
},
"allow_page_overlap": {
"type": "boolean",
"description": "If True, a page can belong to multiple categories/partitions. If False, each page must belong to exactly one category. Defaults to True."
}
}
},
"split_description": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The name value"
},
"description": {
"type": "string",
"description": "The description value"
},
"partition_key": {
"type": "string",
"description": "Partition Key"
}
},
"required": [
"name",
"description"
]
},
"description": "The configuration options for processing the document."
},
"split_rules": {
"type": "string",
"description": "The prompt that describes rules for splitting the document."
}
},
"required": [
"PCID",
"input",
"split_description"
]
}
```
***
## reducto\_upload
Upload
**Parameters:**
| Parameter | Type | Required | Default | Description |
| ----------- | ------ | -------- | ------- | ------------------- |
| `extension` | string | No | — | The extension value |
| `file` | object | No | — | The file value |
```json theme={null}
{
"type": "object",
"properties": {
"PCID": {
"type": "string",
"description": "Pink Connect ID for the authenticated connection"
},
"extension": {
"type": "string",
"description": "The extension value"
},
"file": {
"description": "The file value"
}
},
"required": [
"PCID"
]
}
```