{"uid":"cap_dsFaJlJHVtn6r5tYV5lUS","slug":"clean-web-corpus-sample-47949a20","name":"Clean Web Corpus Sample","description":"Clean-markdown web corpus sample in JSONL: diverse public pages stripped to readable text with per-doc SHA-256 hashes. For RAG pipelines and agent research.","url":"https://etherealgoodsco.store/data/web-corpus","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":[],"properties":{}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","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":"$0.1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_5LZkRG5cqKhV6oAEqjq4k","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns a JSONL sample of clean, markdown-formatted web pages stripped to readable text with per-document SHA-256 hashes, intended for RAG pipelines and agent research.","exampleAgentPrompt":"Fetch me a clean markdown web corpus sample in JSONL format — I need diverse public pages stripped to readable text with SHA-256 hashes so I can test my RAG pipeline.","exampleUseCases":[{"title":"RAG pipeline bootstrapping","prompt":"I'm building a retrieval-augmented generation system and need a diverse sample of clean web text in JSONL format with SHA-256 hashes for deduplication — can you grab that corpus sample for me?"},{"title":"LLM research data collection","prompt":"I'm doing agent research and need a ready-made dataset of public web pages already cleaned to readable markdown — can you download that web corpus sample so I can start experimenting?"},{"title":"Embedding index seeding","prompt":"I need to seed a vector database with varied web content — can you pull a JSONL web corpus with per-document hashes so I can generate embeddings and load them into my index?"}],"resultDescription":"A JSONL-formatted document where each line represents a public web page cleaned to readable markdown text, accompanied by a per-document SHA-256 content hash. The corpus covers diverse public pages suitable for RAG pipelines, embedding generation, and agent research workflows.","failureModes":["HTTP 402 Payment Required if x402 payment is not provided or fails","Empty or partial JSONL if the corpus sample generation is interrupted","Stale or cached corpus if the underlying data has not been refreshed recently","Network timeout for large JSONL payloads on slow connections"],"whenToPreferThis":"Choose this endpoint when you need a ready-made, pre-cleaned sample of diverse web text in JSONL format with SHA-256 hashes — especially for bootstrapping RAG pipelines, seeding vector databases, or conducting agent research without having to scrape and clean pages yourself. Prefer this over raw scraping endpoints when reproducibility and content integrity (via hashes) matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:51:03.552Z","isFirstParty":false}