{"uid":"cap_Cc5Np4G8Li9xektWbnYxs","slug":"machine-shop-document-preparation-chunking-3467c10f","name":"Machine Shop – Document Preparation & Chunking","description":"Turn Apify product scrape results into safe catalog updates with Catalog Update Gate. Find evidence in supplied documents, compare snapshots, extract typed JSON fields, inspect x402 quotes and assess API migrations. Preview inputs, evidence and cost for free. No live web search, scheduled monitoring or third-party purchasing.","url":"https://api.pay-forge.online/v1/prepare-document?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","title":"Text","maxLength":50000},"overlap":{"type":"integer","title":"Overlap","default":150,"maximum":9999,"minimum":0},"chunk_size":{"type":"integer","title":"Chunk Size","default":1500,"maximum":10000,"minimum":64}}},"responseSchema":{"type":"json","example":{"text":"Hello world","chunks":[{"end":11,"text":"Hello world","index":0,"start":0}],"sha256":"64ec88ca00b268e5ba1a35678a1b5316d212f4f366b2477232534a8aeca37f3c","entities":{"urls":[],"dates":[],"money":[],"emails":[],"evm_addresses":[]},"removed_duplicate_lines":0}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_J81FixoVeSILPAIZ8uahl","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Parses and chunks a text document, extracting entities (URLs, dates, money, emails, EVM addresses) and returning a content hash for downstream analysis tasks.","exampleAgentPrompt":"Can you prepare this contract text for analysis — chunk it into segments of about 1500 characters with a 150-character overlap, and pull out any dates, money amounts, email addresses, and Ethereum wallet addresses mentioned in it?","exampleUseCases":[{"title":"Extract wallet addresses from airdrop announcement","prompt":"I have this airdrop announcement text — can you chunk it and extract all EVM wallet addresses and dollar amounts mentioned in it?"},{"title":"Fingerprint a document for change detection","prompt":"Take this policy document and prepare it so I can get its SHA-256 hash and see the chunks — I want to detect if it changes later."},{"title":"Prepare contract text for evidence search","prompt":"Here's a 10,000-word legal contract — chunk it into 2000-character pieces with 200-character overlap and extract all the dates and email addresses so I can search it for evidence."}],"resultDescription":"Returns the full chunked representation of the input text (array of chunk objects with start/end indices and text), a SHA-256 hash of the content, extracted named entities (URLs, dates, money values, emails, EVM addresses), and a count of removed duplicate lines.","failureModes":["Text exceeds 50,000 character limit — request rejected","chunk_size below 64 or above 10,000 — validation error","overlap exceeds chunk_size — may produce degenerate chunks","Empty or missing text field — empty or error response","Non-UTF-8 or malformed input — parsing failure"],"whenToPreferThis":"Choose this endpoint when you need to preprocess raw text into structured, searchable chunks before feeding into an LLM context window, vector store, or evidence-comparison pipeline. It is especially useful when you also need lightweight entity extraction (emails, dates, money, EVM addresses) as a free side-effect of chunking, or when you want a stable SHA-256 fingerprint for change detection. Prefer it over general-purpose text splitters when blockchain/Web3 entity extraction (EVM addresses) is needed alongside chunking.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:44:46.030Z","isFirstParty":false,"canonicalSlug":"machine-shop-document-preparation-chunking-3467c10f"}