{"uid":"cap_ytDTrOEin1huxyWetT6eB","slug":"email-verify-agentdiet-dev-web-url-distillation-bm25-rag-chunker-94fa3c1d","name":"Web URL Distillation & BM25 RAG Chunker","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://email-verify.agentdiet.dev/v1/rag-chunk)","url":"https://email-verify.agentdiet.dev/v1/rag-chunk?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","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":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_gysd717AUo5xLUnkJuy_t","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"email-verify.agentdiet.dev","brandSlug":"email-verify-agentdiet-dev-mpp","brandBaseUrl":"https://email-verify.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL or raw HTML and distills it into compact, token-efficient agent-ready output using markdown, structured, skeleton, or BM25 budget modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown, keeping it under 500 tokens and focusing on 'payment intents'.","exampleUseCases":[{"title":"RAG pipeline web grounding","prompt":"Fetch and distill https://openai.com/blog/gpt-4o into clean markdown so I can feed it into my RAG pipeline without blowing my token budget."},{"title":"Focused budget excerpt for research","prompt":"Pull the page at https://arxiv.org/abs/2305.10601 and give me only the content most relevant to 'chain-of-thought prompting', capped at 300 tokens."},{"title":"Structured data extraction from docs","prompt":"Take the raw HTML from this Stripe pricing page and return it as structured JSON tables so my agent can parse the plan details without processing the full page."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an roi_proof object showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Missing required 'url' parameter returns validation error","Unreachable or blocked URLs result in fetch failure","mode=budget without a 'query' parameter may return unfiltered content","max_tokens below minimum of 20 is rejected","Invalid URL format causes parse error","Payment failure (x402) blocks execution if USDC balance insufficient"],"whenToPreferThis":"Choose this endpoint when your agent needs to consume web page content within a strict token budget, wants BM25-focused retrieval over a page before passing to an LLM, or needs to minimize LLM inference costs by compressing raw HTML/URLs into distilled markdown or structured JSON. Especially useful in RAG pipelines, agent grounding steps, or any workflow where raw web content is too token-heavy to pass directly to a model.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:17.254Z","isFirstParty":false,"canonicalSlug":"email-verify-agentdiet-dev-web-url-distillation-bm25-rag-chunker-94fa3c1d"}