{"templateId":"markdown","sharedDataIds":{"sidebar":"sidebar-index.sidebars.yaml"},"props":{"metadata":{"markdoc":{"tagList":[]},"type":"markdown"},"seo":{"title":"Parsing","llmstxt":{"hide":false,"sections":[{"title":"Table of contents","includeFiles":["**/*"],"excludeFiles":[]}],"excludeFiles":[]}},"dynamicMarkdocComponents":[],"compilationErrors":[],"ast":{"$$mdtype":"Tag","name":"article","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"span","attributes":{"style":{"color":"#cdcefb","fontSize":"14px","fontWeight":"700","textTransform":"uppercase","letterSpacing":"0.05em","display":"block","marginBottom":"-30px"}},"children":["Get Started"]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":1,"id":"parsing","__idx":0},"children":["Parsing"]},{"$$mdtype":"Tag","name":"blockquote","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Convert documents into OCR, markdown, and page-level parsing data."]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Parsing is the Anesya endpoint for turning a document into machine-usable content before structured extraction."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["It can:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["run OCR on the document"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["generate ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["markdown_content"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["return page-level parsing data in ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ocr_content"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["describe images when picture descriptions are enabled"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["report processing status and partial page failures"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Use parsing when you need visibility into the document content itself, not only the final structured JSON."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If you only need the final structured result from a schema, see ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/extract"},"children":["Extract"]},"."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"what-parsing-is-for","__idx":1},"children":["What parsing is for"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Parsing is the right entry point when you want to:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["inspect OCR output before extraction"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["get readable markdown for LLM workflows"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["process one document or fan out over a list of public URLs"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["detect partial page failures"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["reuse a parsing in later downstream steps"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The typical flow is:"]},{"$$mdtype":"Tag","name":"Diagram","attributes":{"data-language":"mermaid","diagramType":"mermaid","diagramSource":"flowchart LR\n A[Document ID, URL, file, or URL list] --> B[Create parsing]\n B --> C[Poll parsing]\n C --> D[Use markdown or OCR]\n C --> E[Create extract]\n","diagramHtml":"

Document ID, URL, file, or URL list

Create parsing

Poll parsing

Use markdown or OCR

Create extract

","diagramHtmlDark":"

Document ID, URL, file, or URL list

Create parsing

Poll parsing

Use markdown or OCR

Create extract

"},"children":["flowchart LR\n A[Document ID, URL, file, or URL list] --> B[Create parsing]\n B --> C[Poll parsing]\n C --> D[Use markdown or OCR]\n C --> E[Create extract]\n"]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"quick-start","__idx":2},"children":["Quick start"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The safest parsing workflow has three steps:"]},{"$$mdtype":"Tag","name":"ol","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["prepare one input document"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["create the parsing"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["poll it until the status is final"]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"option-a-start-from-a-stored-document","__idx":3},"children":["Option A: Start from a stored document"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Upload the file first if you want a reusable document ID."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"curl -X POST \"https://api.anesya.app/v0/documents\" \\\n -H \"X-API-Key: $ANESYA_API_KEY\" \\\n -F \"file=@invoice.pdf;type=application/pdf\" \\\n -F \"filename=invoice.pdf\"\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Then create the parsing:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"curl -X POST \"https://api.anesya.app/v0/parsing\" \\\n -H \"X-API-Key: $ANESYA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"document\": \"YOUR_DOCUMENT_ID\",\n \"model\": \"PIGALLE\",\n \"picture_description_enabled\": false,\n \"table_verification_enabled\": false\n }'\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"option-b-start-directly-from-a-public-url","__idx":4},"children":["Option B: Start directly from a public URL"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"curl -X POST \"https://api.anesya.app/v0/parsing\" \\\n -H \"X-API-Key: $ANESYA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"document\": \"https://example.com/invoice.pdf\",\n \"model\": \"PIGALLE\"\n }'\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"option-c-start-directly-from-a-local-file","__idx":5},"children":["Option C: Start directly from a local file"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"curl -X POST \"https://api.anesya.app/v0/parsing\" \\\n -H \"X-API-Key: $ANESYA_API_KEY\" \\\n -F \"document=@invoice.pdf;type=application/pdf\" \\\n -F \"model=PIGALLE\" \\\n -F \"picture_description_enabled=false\" \\\n -F \"table_verification_enabled=false\"\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"poll-the-parsing","__idx":6},"children":["Poll the parsing"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"curl -X GET \"https://api.anesya.app/v0/parsing/YOUR_PARSING_ID\" \\\n -H \"X-API-Key: $ANESYA_API_KEY\"\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Stop polling when ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["status"]}," is one of:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FINISHED"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PARTIAL_FINISHED"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ERROR"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["For a complete polling strategy, see ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/quickstart"},"children":["API quickstart"]},"."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"what-you-get-back","__idx":7},"children":["What you get back"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The parsing retrieve endpoint returns a resource shaped like this:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"id\": \"d1b96998-f20e-4b6f-8fa5-78a70b1db9b2\",\n \"document\": {\n \"id\": \"300f339f-da71-4f9f-80f6-c25a63baae75\",\n \"filename\": \"invoice.pdf\"\n },\n \"picture_description_enabled\": false,\n \"table_verification_enabled\": false,\n \"model\": \"PIGALLE\",\n \"pictures\": [],\n \"ocr_content\": {\n \"pages\": []\n },\n \"markdown_content\": \"# Invoice\\n\\nInvoice number: INV-2025-0042\\n\\nTotal: 1280.50 EUR\",\n \"pages_total\": 3,\n \"pages_success\": 3,\n \"pages_failed\": 0,\n \"status\": \"FINISHED\",\n \"metadata\": {\n \"source\": \"api\"\n },\n \"error\": null,\n \"created_at\": \"2025-06-12T14:57:00.000000Z\",\n \"updated_at\": \"2025-06-12T14:58:12.000000Z\"\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"key-fields","__idx":8},"children":["Key fields"]},{"$$mdtype":"Tag","name":"div","attributes":{"className":"md-table-wrapper"},"children":[{"$$mdtype":"Tag","name":"table","attributes":{"className":"md"},"children":[{"$$mdtype":"Tag","name":"thead","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"Field"},"children":["Field"]},{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"What it contains"},"children":["What it contains"]}]}]},{"$$mdtype":"Tag","name":"tbody","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["document"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["The source document metadata"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["markdown_content"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Readable markdown version of the parsed document"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ocr_content"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Structured OCR payload"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pictures"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Parsed image entries with optional descriptions"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_total"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Total page count"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_success"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Number of pages successfully processed"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_failed"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Number of failed pages"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["status"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Current parsing state"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Error message when parsing fails"]}]}]}]}]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"input-options","__idx":9},"children":["Input options"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["document"]}," field in ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["POST /v0/parsing"]}," accepts four shapes."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"1-existing-document-id","__idx":10},"children":["1. Existing document ID"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Best when the file is already stored in Anesya and may be reused later."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"document\": \"300f339f-da71-4f9f-80f6-c25a63baae75\"\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"2-public-or-pre-signed-url","__idx":11},"children":["2. Public or pre-signed URL"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Best when the file is already hosted elsewhere."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"document\": \"https://example.com/invoice.pdf\"\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"3-multipart-uploaded-file","__idx":12},"children":["3. Multipart uploaded file"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Best when your app already has the local file content and does not need a separate document-upload step."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"text","header":{"controls":{"copy":{}}},"source":"multipart/form-data\ndocument=@invoice.pdf\n","lang":"text"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"4-list-of-public-or-pre-signed-urls","__idx":13},"children":["4. List of public or pre-signed URLs"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Best when you want to fan out over several remote documents at once."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"document\": [\n \"https://example.com/doc-1.pdf\",\n \"https://example.com/doc-2.pdf\"\n ]\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Important behavior:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["this URL-list shape is supported on parsing"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["it returns an ",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["array of parsing objects"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the extract endpoint does not document the same URL-list support"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If you need one extract per URL, create the parsings first, then iterate over the returned parsing IDs."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"response-format-details","__idx":14},"children":["Response format details"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Parsing has two main response shapes depending on the endpoint you call."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"post-v0parsing","__idx":15},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["POST /v0/parsing"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Create parsing returns:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["one parsing object for one document ID, one URL, or one uploaded file"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["an array of parsing objects for a list of URLs"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Example single-object response:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"id\": \"PARSING_ID\",\n \"status\": \"IN_QUEUE\"\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Example array response:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"[\n {\n \"id\": \"PARSING_ID_1\",\n \"status\": \"IN_QUEUE\"\n },\n {\n \"id\": \"PARSING_ID_2\",\n \"status\": \"IN_QUEUE\"\n }\n]\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"get-v0parsing","__idx":16},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["GET /v0/parsing"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["List parsing returns a paginated resource:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"count\": 2,\n \"next\": null,\n \"previous\": null,\n \"results\": [\n {\n \"id\": \"PARSING_ID\",\n \"status\": \"FINISHED\"\n }\n ]\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"get-v0parsingid","__idx":17},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["GET /v0/parsing/{id}"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Retrieve parsing returns the full parsing resource, including:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["markdown_content"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ocr_content"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pictures"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["page counters"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["status"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["errors"]}]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"parsing-statuses","__idx":18},"children":["Parsing statuses"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["These are the possible parsing states:"]},{"$$mdtype":"Tag","name":"div","attributes":{"className":"md-table-wrapper"},"children":[{"$$mdtype":"Tag","name":"table","attributes":{"className":"md"},"children":[{"$$mdtype":"Tag","name":"thead","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"Status"},"children":["Status"]},{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"Meaning"},"children":["Meaning"]},{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"What to do"},"children":["What to do"]}]}]},{"$$mdtype":"Tag","name":"tbody","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["IN_QUEUE"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Accepted and waiting to start"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["keep polling"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["IN_PROGRESS"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Processing is running"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["keep polling"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FINISHED"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Completed successfully"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["use the parsing output"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PARTIAL_FINISHED"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Completed with one or more failed pages"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["use it if partial content is acceptable"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ERROR"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Processing failed"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["inspect ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}]}]}]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PARTIAL_FINISHED"]}," is an important state."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["It is not a full success, but it is often still usable, especially if:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["most pages succeeded"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the failed pages are not critical"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["your next step is tolerant to partial source coverage"]}]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"configuration-options","__idx":19},"children":["Configuration options"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The parsing endpoint exposes a deliberately small set of knobs."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"model","__idx":20},"children":["Model"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"model\": \"PIGALLE\"\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Supported values:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PIGALLE"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PIGALLE_LITE"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Use ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PIGALLE"]}," by default unless you already know ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PIGALLE_LITE"]}," is sufficient for your workload."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"picture-descriptions","__idx":21},"children":["Picture descriptions"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"picture_description_enabled\": true\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Enable this when image descriptions are useful for your workflow."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"table-verification","__idx":22},"children":["Table verification"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"table_verification_enabled\": true\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Enable this when table accuracy matters more than raw speed."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"metadata","__idx":23},"children":["Metadata"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"json","header":{"controls":{"copy":{}}},"source":"{\n \"metadata\": {\n \"source\": \"n8n\",\n \"customer_id\": \"cust_123\"\n }\n}\n","lang":"json"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Use metadata to keep track of source systems, customer context, or workflow identifiers."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"best-practices","__idx":24},"children":["Best practices"]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"1-prefer-a-stored-document-when-reuse-matters","__idx":25},"children":["1. Prefer a stored document when reuse matters"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If the same file may be parsed again, extracted later, or audited, upload it first with ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["/v0/documents"]},"."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["This gives you a reusable document ID and a cleaner workflow than repeatedly uploading the same file."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"2-use-parsing-before-extract-when-visibility-matters","__idx":26},"children":["2. Use parsing before extract when visibility matters"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If you need OCR, markdown, pictures, or page-level status, do not jump directly to extract."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Create a parsing first, inspect it, then create the extract from the parsing ID."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"3-use-url-list-fan-out-only-on-parsing","__idx":27},"children":["3. Use URL-list fan-out only on parsing"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If your source input is a list of URLs:"]},{"$$mdtype":"Tag","name":"ol","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["send the list to ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["/v0/parsing"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["receive an array of parsing IDs"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["iterate over those IDs to create extracts if needed"]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"4-treat-partial_finished-as-a-distinct-state","__idx":28},"children":["4. Treat ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PARTIAL_FINISHED"]}," as a distinct state"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Do not collapse it into generic failure logic."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Instead, inspect:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_success"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_failed"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Then decide whether the workflow can continue."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"5-enable-picture-and-table-options-only-when-they-help","__idx":29},"children":["5. Enable picture and table options only when they help"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Both ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["picture_description_enabled"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["table_verification_enabled"]}," should be chosen intentionally."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If your use case does not depend on those features, keep them disabled for simpler requests."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"6-trim-pdfs-early-when-only-a-subset-matters","__idx":30},"children":["6. Trim PDFs early when only a subset matters"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If you only need part of a PDF, trim it during document upload with the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pdf_page_start"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pdf_page_end"]}," query parameters on ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/api/schema/documents/document_create"},"children":["Create document"]},"."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["That reduces unnecessary downstream processing."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"common-pitfalls","__idx":31},"children":["Common pitfalls"]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"assuming-parsing-is-synchronous","__idx":32},"children":["Assuming parsing is synchronous"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["POST /v0/parsing"]}," creates a resource and starts processing. It does not mean the final content is ready immediately."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Always poll the parsing resource until the status is final."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"assuming-post-v0parsing-always-returns-one-object","__idx":33},"children":["Assuming ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["POST /v0/parsing"]}," always returns one object"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["document"]}," is a list of URLs, the response is an array."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["This is one of the most common integration mistakes in no-code tools and coding agents."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"passing-a-url-list-to-extract","__idx":34},"children":["Passing a URL list to extract"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["That list behavior is documented on parsing, not on extract."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If you need multiple downstream extracts, create multiple parsings first."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"ignoring-error","__idx":35},"children":["Ignoring ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["When a parsing fails, do not branch only on ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["status"]},"."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Always inspect the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}," field for debugging and retry decisions."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"troubleshooting","__idx":36},"children":["Troubleshooting"]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"401-unauthorized","__idx":37},"children":["401 Unauthorized"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Your API key is missing or invalid. Check the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["X-API-Key"]}," header."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"parsing-remains-in-in_queue-or-in_progress","__idx":38},"children":["Parsing remains in ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["IN_QUEUE"]}," or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["IN_PROGRESS"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Keep polling. Parsing is asynchronous by design."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"parsing-finishes-with-partial_finished","__idx":39},"children":["Parsing finishes with ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["PARTIAL_FINISHED"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Review ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["pages_failed"]}," and decide whether partial output is acceptable for the workflow."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"parsing-fails-with-error","__idx":40},"children":["Parsing fails with ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["ERROR"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Inspect the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["error"]}," field, then verify:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the document input is valid"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the public URL is accessible"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the pre-signed URL is still valid"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["the uploaded file is readable"]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"public-url-parsing-fails-unexpectedly","__idx":41},"children":["Public URL parsing fails unexpectedly"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["If the input uses a short-lived pre-signed URL, it may expire before or during processing."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Use a longer validity window or upload the file first."]},{"$$mdtype":"Tag","name":"hr","attributes":{},"children":[]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"related-guides","__idx":42},"children":["Related guides"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/quickstart"},"children":["API quickstart"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/parsing"},"children":["Parsing guide"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/extract"},"children":["Extract guide"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/quickstart"},"children":["Quickstart polling flow"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/n8n/n8n-parsing"},"children":["n8n parsing workflow"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/tutorials/agent-guide"},"children":["Anesya API Reference for Coding Agents"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/api/schema/parsings/parsing_create"},"children":["API reference"]}]}]}]},"headings":[{"value":"Parsing","id":"parsing","depth":1},{"value":"What parsing is for","id":"what-parsing-is-for","depth":2},{"value":"Quick start","id":"quick-start","depth":2},{"value":"Option A: Start from a stored document","id":"option-a-start-from-a-stored-document","depth":3},{"value":"Option B: Start directly from a public URL","id":"option-b-start-directly-from-a-public-url","depth":3},{"value":"Option C: Start directly from a local file","id":"option-c-start-directly-from-a-local-file","depth":3},{"value":"Poll the parsing","id":"poll-the-parsing","depth":3},{"value":"What you get back","id":"what-you-get-back","depth":2},{"value":"Key fields","id":"key-fields","depth":3},{"value":"Input options","id":"input-options","depth":2},{"value":"1. Existing document ID","id":"1-existing-document-id","depth":3},{"value":"2. Public or pre-signed URL","id":"2-public-or-pre-signed-url","depth":3},{"value":"3. Multipart uploaded file","id":"3-multipart-uploaded-file","depth":3},{"value":"4. List of public or pre-signed URLs","id":"4-list-of-public-or-pre-signed-urls","depth":3},{"value":"Response format details","id":"response-format-details","depth":2},{"value":"POST /v0/parsing","id":"post-v0parsing","depth":3},{"value":"GET /v0/parsing","id":"get-v0parsing","depth":3},{"value":"GET /v0/parsing/{id}","id":"get-v0parsingid","depth":3},{"value":"Parsing statuses","id":"parsing-statuses","depth":2},{"value":"Configuration options","id":"configuration-options","depth":2},{"value":"Model","id":"model","depth":3},{"value":"Picture descriptions","id":"picture-descriptions","depth":3},{"value":"Table verification","id":"table-verification","depth":3},{"value":"Metadata","id":"metadata","depth":3},{"value":"Best practices","id":"best-practices","depth":2},{"value":"1. Prefer a stored document when reuse matters","id":"1-prefer-a-stored-document-when-reuse-matters","depth":3},{"value":"2. Use parsing before extract when visibility matters","id":"2-use-parsing-before-extract-when-visibility-matters","depth":3},{"value":"3. Use URL-list fan-out only on parsing","id":"3-use-url-list-fan-out-only-on-parsing","depth":3},{"value":"4. Treat PARTIAL_FINISHED as a distinct state","id":"4-treat-partial_finished-as-a-distinct-state","depth":3},{"value":"5. Enable picture and table options only when they help","id":"5-enable-picture-and-table-options-only-when-they-help","depth":3},{"value":"6. Trim PDFs early when only a subset matters","id":"6-trim-pdfs-early-when-only-a-subset-matters","depth":3},{"value":"Common pitfalls","id":"common-pitfalls","depth":2},{"value":"Assuming parsing is synchronous","id":"assuming-parsing-is-synchronous","depth":3},{"value":"Assuming POST /v0/parsing always returns one object","id":"assuming-post-v0parsing-always-returns-one-object","depth":3},{"value":"Passing a URL list to extract","id":"passing-a-url-list-to-extract","depth":3},{"value":"Ignoring error","id":"ignoring-error","depth":3},{"value":"Troubleshooting","id":"troubleshooting","depth":2},{"value":"401 Unauthorized","id":"401-unauthorized","depth":3},{"value":"Parsing remains in IN_QUEUE or IN_PROGRESS","id":"parsing-remains-in-in_queue-or-in_progress","depth":3},{"value":"Parsing finishes with PARTIAL_FINISHED","id":"parsing-finishes-with-partial_finished","depth":3},{"value":"Parsing fails with ERROR","id":"parsing-fails-with-error","depth":3},{"value":"Public URL parsing fails unexpectedly","id":"public-url-parsing-fails-unexpectedly","depth":3},{"value":"Related guides","id":"related-guides","depth":2}],"frontmatter":{"seo":{"title":"Parsing"}},"lastModified":"2026-04-22T15:07:29.000Z","pagePropGetterError":{"message":"","name":""}},"slug":"/tutorials/parsing","userData":{"isAuthenticated":false,"teams":["anonymous"]},"isPublic":true}