> ## Documentation Index > Fetch the complete documentation index at: https://unstructured-53-docs-243-plugins.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Pipeline > Description ## OpenAPI ````yaml post /general/v0/general openapi: 3.1.0 info: title: Unstructured Pipeline API version: 1.0.48 servers: - url: https://api.unstructuredapp.io description: Partition Endpoint x-speakeasy-server-id: saas-api - url: https://api.unstructured.io description: Free API (Legacy) x-speakeasy-server-id: free-api - url: http://localhost:8000 description: Development server x-speakeasy-server-id: development security: - ApiKeyAuth: [] - {} tags: - name: general paths: /general/v0/general: post: tags: - general summary: Summary description: Description operationId: partition parameters: - name: unstructured-api-key in: header required: false schema: anyOf: - type: string - type: 'null' title: Unstructured-Api-Key requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/partition_parameters' responses: '200': description: Successful Response content: application/json: schema: items: $ref: '#/components/schemas/Element' description: A list of element dictionaries extracted from the file title: Elements type: array '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' 5XX: description: Server Error content: application/json: schema: $ref: '#/components/schemas/ServerError' components: schemas: partition_parameters: properties: files: type: string format: binary description: The file to extract required: 'true' examples: - summary: File to be partitioned externalValue: >- https://github.com/Unstructured-IO/unstructured/blob/98d3541909f64290b5efb65a226fc3ee8a7cc5ee/example-docs/layout-parser-paper.pdf coordinates: type: boolean title: Coordinates description: >- If `True`, return coordinates for each element extracted via OCR. Default: `False` default: false content_type: anyOf: - type: string - type: 'null' title: Content type description: >- A hint about the content type to use (such as text/markdown), when there are problems processing a specific file. This value is a MIME type in the format type/subtype. encoding: anyOf: - type: string - type: 'null' title: Encoding description: 'The encoding method used to decode the text input. Default: utf-8' extract_image_block_types: items: type: string type: array title: Image block types to extract description: >- The types of elements to extract, for use in extracting image blocks as base64 encoded data stored in metadata fields. default: [] gz_uncompressed_content_type: anyOf: - type: string - type: 'null' title: Uncompressed Content Type description: If file is gzipped, use this content type after unzipping. hi_res_model_name: anyOf: - type: string - type: 'null' title: Hi Res Model Name description: The name of the inference model used when strategy is hi_res include_page_breaks: type: boolean title: Include Page Breaks description: >- If true, the output will include page breaks if the filetype supports it. Default: false default: false languages: items: type: string type: array title: OCR Languages description: >- The languages present in the document, for use in partitioning and/or OCR. See the Tesseract documentation for a full list of languages. default: [] ocr_languages: items: type: string type: array title: OCR Languages description: >- Deprecated! The languages present in the document, for use in partitioning and/or OCR default: [] output_format: type: string enum: - application/json - text/csv title: Output Format description: >- The format of the response. Supported formats are application/json and text/csv. Default: application/json. default: application/json x-speakeasy-unknown-values: allow pdf_infer_table_structure: type: boolean title: Pdf Infer Table Structure description: >- Deprecated! Use skip_infer_table_types to opt out of table extraction for any file type. If False and strategy=hi_res, no Table Elements will be extracted from pdf files regardless of skip_infer_table_types contents. default: true skip_infer_table_types: items: type: string type: array title: Skip Infer Table Types description: >- The document types that you want to skip table extraction with. Default: [] default: [] starting_page_number: anyOf: - type: integer - type: 'null' title: PDF Starting Page Number description: >- When PDF is split into pages before sending it into the API, providing this information will allow the page number to be assigned correctly. Introduced in 1.0.27. strategy: type: string enum: - fast - hi_res - auto - ocr_only title: Strategy description: >- The strategy to use for partitioning PDF/image. Options are fast, hi_res, auto. Default: hi_res default: hi_res examples: - auto - hi_res x-speakeasy-unknown-values: allow unique_element_ids: type: boolean title: unique_element_ids description: >- When `True`, assign UUIDs to element IDs, which guarantees their uniqueness (useful when using them as primary keys in database). Otherwise a SHA-256 of element text is used. Default: `False` default: false xml_keep_tags: type: boolean title: Xml Keep Tags description: >- If `True`, will retain the XML tags in the output. Otherwise it will simply extract the text from within the tags. Only applies to XML documents. default: false chunking_strategy: anyOf: - type: string enum: - basic - by_page - by_similarity - by_title - type: 'null' title: Chunking Strategy description: >- Use one of the supported strategies to chunk the returned elements after partitioning. When 'chunking_strategy' is not specified, no chunking is performed and any other chunking parameters provided are ignored. Supported strategies: 'basic', 'by_page', 'by_similarity', or 'by_title' examples: - by_title - basic x-speakeasy-unknown-values: allow combine_under_n_chars: anyOf: - type: integer - type: 'null' title: Combine Under N Chars description: >- If chunking strategy is set, combine elements until a section reaches a length of n chars. Default: 500 include_orig_elements: anyOf: - type: boolean - type: 'null' title: Include original elements in chunks description: >- When a chunking strategy is specified, each returned chunk will include the elements consolidated to form that chunk as `.metadata.orig_elements`. Default: true. max_characters: anyOf: - type: integer - type: 'null' title: Max Characters description: >- If chunking strategy is set, cut off new sections after reaching a length of n chars (hard max). Default: 500 multipage_sections: type: boolean title: Multipage Sections description: >- If chunking strategy is set, determines if sections can span multiple sections. Default: true default: true new_after_n_chars: anyOf: - type: integer - type: 'null' title: New after n chars description: >- If chunking strategy is set, cut off new sections after reaching a length of n chars (soft max). Default: 1500 overlap: type: integer title: Overlap description: >- Specifies the length of a string ('tail') to be drawn from each chunk and prefixed to the next chunk as a context-preserving mechanism. By default, this only applies to split-chunks where an oversized element is divided into multiple chunks by text-splitting. Default: 0 default: 0 overlap_all: type: boolean title: Overlap all description: >- When `True`, apply overlap between 'normal' chunks formed from whole elements and not subject to text-splitting. Use this with caution as it entails a certain level of 'pollution' of otherwise clean semantic chunk boundaries. Default: False default: false similarity_threshold: anyOf: - type: number - type: 'null' title: similarity-threshold description: >- A value between 0.0 and 1.0 describing the minimum similarity two elements must have to be included in the same chunk. Note that similar elements may be separated to meet chunk-size criteria; this value can only guarantees that two elements with similarity below the threshold will appear in separate chunks. include_slide_notes: type: boolean title: include_slide_notes description: >- When `True`, slide notes from .ppt and .pptx files will be included in the response. Default: `True` default: true type: object required: - files title: Partition Parameters Element: title: Element type: object additionalProperties: true example: type: Title element_id: 6aa0ff22f91bbe7e26e8e25ca8052acd text: >- LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis metadata: languages: - eng page_number: 1 filename: layout-parser-paper.pdf filetype: application/pdf HTTPValidationError: type: object properties: detail: oneOf: - type: array items: $ref: '#/components/schemas/ValidationError' - type: string example: detail: - type: int_parsing loc: - body - combine_under_n_chars msg: >- Input should be a valid integer, unable to parse string as an integer input: forty ServerError: type: object properties: detail: type: string example: detail: An error occurred ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: ApiKeyAuth: type: apiKey name: unstructured-api-key in: header x-speakeasy-example: YOUR_API_KEY ````