{"uid":"cap_34BGCGyEJrOBYqCyvPm9T","slug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-687b8b15","name":"Web Content 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://arxiv-digest.agentdiet.dev/v1/rag-chunk)","url":"https://arxiv-digest.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_zPB8amKrPIon4c0LsxMKP","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or BM25-ranked token-budgeted excerpts for LLM consumption","exampleAgentPrompt":"Distill https://arxiv.org/abs/2401.00123 into clean markdown using budget mode focused on 'attention mechanisms' and cap it at 500 tokens.","exampleUseCases":[{"title":"RAG pipeline webpage preprocessing","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured JSON tables so I can feed it into my RAG pipeline without blowing my token budget."},{"title":"Focused excerpt for research query","prompt":"Grab https://arxiv.org/abs/2310.06825 and give me only the sections relevant to 'reinforcement learning from human feedback' in budget mode, keeping it under 800 tokens."},{"title":"Clean markdown for LLM context","prompt":"Take this raw HTML I have and convert it to clean markdown — I want to paste it into my prompt without all the nav bars and script tags eating up my context window."}],"resultDescription":"Returns a JSON object with: distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode); ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD; cache status (HIT/MISS) and latency; and billing details. The data field contains the actual distilled output ready for LLM consumption.","failureModes":["URL unreachable or returns non-200 status — fetch failure error","HTML payload missing when url not provided — validation error","max_tokens below minimum of 20 — schema validation rejection","BM25 query missing when mode=budget — may return unfiltered content","Payment not included or invalid — HTTP 402 payment required","Oversized HTML payload — may timeout or be truncated","Rate limiting or upstream block on target URL"],"whenToPreferThis":"Choose this endpoint when you need to preprocess web content for LLM consumption with strict token control, especially when context window costs matter. It is particularly valuable for RAG pipelines needing BM25-ranked excerpts relevant to a specific query, or when you want structured JSON/skeleton output rather than raw HTML. Prefer it over generic scrapers when you need built-in compression metrics, token-budget enforcement, and multiple distillation modes (markdown, structured, skeleton, budget) in a single paid-per-call API.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:26.177Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-687b8b15"}