> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# DocuPipe

> DocuPipe provides document parsing, structured data extraction, classification, analysis, review, workflow, and export APIs.

![DocuPipe logo](https://mintcdn.com/composio-preview/VNLruGH5mLZqXdPH/images/toolkits/docupipe.svg?fit=max\&auto=format\&n=VNLruGH5mLZqXdPH\&q=85\&s=a069799984610cb75c44ffe6c9e99496)

* **Category:** ai document extraction
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 13
* **Triggers:** 0
* **Slug:** `DOCUPIPE`
* **Version:** 20261101\_00

## Tools

> [accordion] Create Schema
>
> **Slug:** `DOCUPIPE_CREATE_SCHEMA`
>
> Create a reusable extraction schema from a valid JSON Schema and optional extraction guidelines.
>
> #### Input Parameters
>
> **guidelines** `string`
>
> Optional instructions applied when documents are standardized with this schema.
>
> **json\_schema** `object` *required*
>
> Valid JSON Schema describing the structured data to extract. Arbitrary nested JSON Schema keywords and values are preserved.
>
> **schema\_name** `string` *required*
>
> Name for the extraction schema.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Document
>
> **Slug:** `DOCUPIPE_DELETE_DOCUMENT`
>
> Permanently delete one previously submitted DocuPipe document by ID. This destructive operation cannot be undone.
>
> #### Input Parameters
>
> **document\_id** `string` *required*
>
> Document ID to permanently delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Documents
>
> **Slug:** `DOCUPIPE_DELETE_DOCUMENTS`
>
> Permanently delete multiple previously submitted DocuPipe documents by ID in one batch. This destructive operation cannot be undone.
>
> #### Input Parameters
>
> **document\_ids** `array` *required*
>
> Document IDs to permanently delete in one batch. Provide at least one ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Find Documents
>
> **Slug:** `DOCUPIPE_FIND_DOCUMENTS`
>
> Browse documents by dataset and creation time, or search filenames and document IDs when query is provided. Returns one page and a continuation cursor.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Documents per page. Browse mode supports 1-20,000; search mode supports 1-500.
>
> **query** `string`
>
> Case-insensitive partial filename or document-ID match (1-50 characters). Omit to browse documents.
>
> **dataset** `string`
>
> Only return documents in this dataset.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by a previous call. Reuse it unchanged instead of constructing an offset.
>
> **to\_timestamp** `string`
>
> Inclusive creation-time upper bound in ISO 8601 format. Available only when query is omitted.
>
> **from\_timestamp** `string`
>
> Inclusive creation-time lower bound in ISO 8601 format. Available only when query is omitted.
>
> **exclude\_payload** `boolean`
>
> Exclude parsed result payloads from browse responses. Set false only when browse results must include content; unavailable with query.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Find Jobs
>
> **Slug:** `DOCUPIPE_FIND_JOBS`
>
> Retrieve one asynchronous job by ID, or list and filter jobs when job\_id is omitted. Job details expose status, progress, errors, outputs, and credit use.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Jobs to return on this list page. DocuPipe documents no maximum.
>
> **job\_id** `string`
>
> Exact job ID to retrieve. Omit to list jobs using the filters below.
>
> **status** `string`
>
> Filter listed jobs by processing status.
>
> **end\_date** `string`
>
> List jobs on or before this date in yyyy-mm-dd format.
>
> **job\_type** `string`
>
> Filter listed jobs by DocuPipe job type.
>
> **schema\_id** `string`
>
> Filter listed jobs by schema ID.
>
> **start\_date** `string`
>
> List jobs on or after this date in yyyy-mm-dd format.
>
> **document\_id** `string`
>
> Filter listed jobs by source document ID.
>
> **next\_cursor** `string`
>
> Continuation cursor from a previous list call. Unavailable when job\_id is provided.
>
> **new\_document\_id** `string`
>
> Filter listed jobs by a newly created document ID, such as split or merge output.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Account Usage
>
> **Slug:** `DOCUPIPE_GET_ACCOUNT_USAGE`
>
> Return current plan and credit state together with job counts and credits consumed by job type, optionally including daily usage.
>
> #### Input Parameters
>
> **include\_daily\_usage** `boolean`
>
> Include the daily credit-usage breakdown in addition to aggregate job-type totals.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Document
>
> **Slug:** `DOCUPIPE_GET_DOCUMENT`
>
> Retrieve a processed document, including processing state, parsed content, page count, metadata, and file details.
>
> #### Input Parameters
>
> **document\_id** `string` *required*
>
> Document ID returned by Upload Document or Find Documents.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Schema
>
> **Slug:** `DOCUPIPE_GET_SCHEMA`
>
> Retrieve one extraction schema and its full JSON Schema definition by ID.
>
> #### Input Parameters
>
> **schema\_id** `string` *required*
>
> Schema ID returned by List Schemas, Create Schema, or Standardize Document.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Standardization
>
> **Slug:** `DOCUPIPE_GET_STANDARDIZATION`
>
> Retrieve one completed standardization as structured JSON, including extraction data and field metadata.
>
> #### Input Parameters
>
> **standardization\_id** `string` *required*
>
> Standardization ID returned by Standardize Document or List Standardizations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Schemas
>
> **Slug:** `DOCUPIPE_LIST_SCHEMAS`
>
> List extraction schemas available to the connected workspace, optionally including each full JSON Schema payload. Returns one page and an opaque continuation cursor.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Schemas to return on this page (1-1000).
>
> **next\_cursor** `string`
>
> Continuation cursor returned by a previous call.
>
> **exclude\_payload** `boolean`
>
> Exclude full jsonSchema payloads for compact discovery; set false when schema definitions are needed.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Standardizations
>
> **Slug:** `DOCUPIPE_LIST_STANDARDIZATIONS`
>
> List standardizations, optionally filtered by schema, document, or up to 1000 standardization IDs, returning one page and a continuation cursor when more may be available. Structured extraction payloads are excluded by default and can be included.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Results to return on this page (1-1000).
>
> **schema\_id** `string`
>
> Only return results created with this schema.
>
> **document\_id** `string`
>
> Only return results for this document.
>
> **next\_cursor** `string`
>
> Continuation cursor returned by a previous call. Reuse it unchanged.
>
> **exclude\_payload** `boolean`
>
> Exclude structured data payloads for compact discovery; set false when extraction data is needed.
>
> **standardization\_ids** `array`
>
> Specific standardization IDs to retrieve (maximum 1000). They are sent to DocuPipe as one comma-separated query value.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Standardize Document
>
> **Slug:** `DOCUPIPE_STANDARDIZE_DOCUMENT`
>
> Start V3 agentic structured extraction for one processed document and return the job and standardization IDs. Standard effort costs 2 credits per page; high effort costs 4 credits per page. Omitting schema\_id also consumes schema-generation credits.
>
> #### Input Parameters
>
> **pages** `array`
>
> Zero-indexed pages to standardize; omit for the entire document.
>
> **timeout** `integer`
>
> Job timeout in seconds for webhook error reporting; not the HTTP timeout.
>
> **schema\_id** `string`
>
> Existing schema to use. If omitted, DocuPipe auto-generates and saves a draft schema, consuming schema-generation credits too.
>
> **guidelines** `string`
>
> Extraction instructions overriding schema guidelines (maximum 50,000 characters).
>
> **document\_id** `string` *required*
>
> Processed document to standardize.
>
> **effort\_level** `string ("standard" | "high")`
>
> Extraction effort: standard costs 2 credits per page; high uses the best models and costs 4 credits per page.
>
> **use\_metadata** `boolean`
>
> Include document metadata as extraction context.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Document
>
> **Slug:** `DOCUPIPE_UPLOAD_DOCUMENT`
>
> Submit one local file or remote file URL for asynchronous parsing. Returns the document and job IDs used to track processing. When workflow\_id is provided, also run that existing workflow after parsing and return its result IDs. Processing consumes credits based on page count and workflow steps.
>
> #### Input Parameters
>
> **url** `string`
>
> Remote document URL. Use this when no local file is supplied; file and url cannot be combined.
>
> **file** `object`
>
> Local document file to upload. Use this when no remote URL is supplied.
>
> **pages** `array`
>
> Zero-indexed pages to parse. Omit or pass an empty list to parse all pages.
>
> **dataset** `string`
>
> Dataset name used to group the document.
>
> **timeout** `integer`
>
> Job timeout in seconds used for webhook error reporting. This is not the HTTP request timeout.
>
> **filename** `string`
>
> Filename without its extension; forwarded as document.filename.
>
> **metadata** `object`
>
> User metadata to attach. Its JSON-serialized size must not exceed 10 KB.
>
> **file\_type** `string ("pdf" | "image" | "text" | "json" | "html" | "word" | "table")`
>
> DocuPipe file type. Omit to let DocuPipe infer it from the content.
>
> **workflow\_id** `string`
>
> Existing workflow to run after parsing.
>
> **parse\_version** `integer ("1" | "2" | "3")`
>
> Parsing version. DocuPipe supports versions 1, 2, and 3.
>
> **file\_extension** `string ("pdf" | "png" | "jpeg" | "webp" | "tiff" | "txt" | "json" | "xml" | "html" | "doc" | "docx" | "csv" | "xlsx" | "xls" | "eml")`
>
> File extension expected by DocuPipe. For a local file, the tool infers a supported extension from its name when possible.
>
> **processing\_method** `string ("asImage" | "removeWatermark")`
>
> Optional processing method. asImage treats native PDFs as images; removeWatermark is experimental.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
