{"uid":"cap_Hw_G-ovYSrR5zQ8b2nqQ3","slug":"company-enrich-agentdiet-dev-web-page-html-distillation-with-bm25-c7df435e","name":"Web Page & HTML Distillation with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://company-enrich.agentdiet.dev/v1/rag-chunk)","url":"https://company-enrich.agentdiet.dev/v1/rag-chunk?utm_source=zero.xyz","method":"POST","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_cFOHNXDCiFJqzkttsbE9O","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt for RAG pipelines","exampleAgentPrompt":"Distill https://stripe.com/docs/api into clean markdown using budget mode focused on 'payment intents', and keep it under 1500 tokens so I can use it in my RAG pipeline without burning through my LLM context.","exampleUseCases":[{"title":"RAG context injection from live docs","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with a BM25 query for 'function calling', capped at 2000 tokens — I need just the relevant bits for my RAG retrieval system."},{"title":"Structured data extraction from a product page","prompt":"Take the HTML from this product listing page and distill it in structured mode so I get the tables, metadata, and pricing info as clean JSON without all the nav and footer junk."},{"title":"Skeleton outline of a long documentation site","prompt":"Distill https://docs.anthropic.com/claude/reference into skeleton mode so I can get just the heading structure and section titles — I want to understand the layout before diving deeper."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may produce minimal or empty output","Token budget (max_tokens) set too low for meaningful content — may return truncated or empty excerpt","BM25 query provided without mode=budget — query may be ignored","Missing required 'url' field — returns validation error","Payment not completed via x402 — request rejected with 402 Payment Required","Rate limiting or upstream fetch timeout — may return error status"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially for RAG pipelines where context windows are limited. It is ideal when you want BM25-ranked excerpts focused on a specific query topic, or when you need structured extraction (tables, metadata) rather than raw HTML. Prefer it over generic web scrapers when token budget control and compression ROI reporting are important to your pipeline economics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:03.268Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-page-html-distillation-with-bm25-c7df435e"}