{"uid":"cap_qnM682wN9dfX42rjTyCq2","slug":"web-dossier-extraction-rag-ingestion-5a5076f9","name":"Web Dossier Extraction & RAG Ingestion","description":"Machine-payable x402 utilities for hashing, Base64, UUID generation, unit and timezone conversion, realtime crypto market data, webpage/document extraction, URL-to-Markdown, metadata, RAG ingestion and deterministic website change detection.","url":"https://x402-gateway-production-1f21.up.railway.app/web/dossier?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri"},"chunk_size":{"type":"integer","maximum":10000,"minimum":100},"user_agent":{"type":"string","maxLength":200},"chunk_overlap":{"type":"integer","maximum":5000,"minimum":0},"max_text_chars":{"type":"integer","maximum":150000,"minimum":1000}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"status":"ready"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.008","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.008/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.008","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.008","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Bc9b-RLeoRd50Wyr6KRlr","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.008","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL and returns a structured dossier of its content including full text, metadata, and RAG-ready chunked segments for downstream ingestion","exampleAgentPrompt":"Fetch the page at https://example.com/blog/ai-trends and extract all its text as a dossier with chunks of 500 characters and an overlap of 50 — I want it ready for RAG ingestion.","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"Pull the content from https://docs.acmecorp.com/api-reference and chunk it into 800-character segments with 100 characters of overlap so I can load it into my vector database."},{"title":"Competitive research dossier","prompt":"Extract the full text and metadata from https://competitor.io/about and give me a structured dossier — I need everything up to 50,000 characters for analysis."},{"title":"Blog post content extraction","prompt":"Grab the webpage at https://techblog.example.com/post/123 and extract the article text with a chunk size of 1000 and chunk overlap of 200 so I can summarize and embed it."}],"resultDescription":"Returns a JSON object with status 'ready' plus extracted page text, document metadata (title, description, URL), and chunked text segments sized and overlapped according to input parameters, suitable for direct ingestion into a vector store or RAG pipeline.","failureModes":["URL is unreachable or returns non-200 status — extraction fails with error","Page is JavaScript-rendered and content is not accessible via static fetch","max_text_chars exceeded or content is too large — truncation or rejection","Invalid URL format — schema validation error","Rate limiting or blocking by target website — empty or partial content returned","Payment not received via x402 — 402 response before processing begins"],"whenToPreferThis":"Choose this endpoint when you need to ingest a single webpage or document URL into a RAG pipeline with configurable chunking, or when you need structured text plus metadata from a web page in one call. Prefer it over generic scrapers when chunk_size and chunk_overlap control matter for downstream embedding workflows. Best for agentic pipelines that need machine-payable, per-call web extraction without maintaining infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:47:20.489Z","isFirstParty":false,"canonicalSlug":"web-dossier-extraction-rag-ingestion-5a5076f9"}