{"uid":"cap_MIhEUm-SGRCVy1UqhScNF","slug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-59618671","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/context-diet)","url":"https://arxiv-digest.agentdiet.dev/v1/context-diet?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_iukczojlMGn9lqRz7qY1T","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 compresses a URL or raw HTML into token-efficient Markdown, structured JSON, skeleton outlines, or BM25-ranked budget excerpts with ROI proof.","exampleAgentPrompt":"Fetch the page at https://arxiv.org/abs/2401.12345 and distill it into clean markdown, keeping it under 500 tokens using budget mode focused on the query 'transformer attention mechanisms'.","exampleUseCases":[{"title":"Token-efficient research paper ingestion","prompt":"Pull the content from https://arxiv.org/abs/2312.00752 and compress it into a budget excerpt of no more than 300 tokens, focusing on the query 'diffusion model training loss' so I can feed it to my LLM without blowing my context window."},{"title":"Structured data extraction from a docs page","prompt":"Take this URL https://stripe.com/docs/payments/payment-intents and distill it into structured JSON tables and metadata — I want the key parameters and response fields organized, not raw HTML."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline mode so I get just the section headers and key structure — nothing more, I just need the shape of the document."}],"resultDescription":"Returns a status field, distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss metadata and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is malformed or empty — distillation may yield minimal output","mode=budget used without a query parameter — BM25 ranking has no focus term","max_tokens set below meaningful content threshold (minimum 20) — very sparse output","Payment not included or invalid — HTTP 402 returned before processing","Rate limiting or upstream fetch timeout for slow target URLs"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before passing web content to an LLM, especially when working with long pages, documentation sites, or research papers. The BM25 budget mode is uniquely suited for query-focused extraction with a hard token ceiling, making it ideal for RAG pipelines and cost-sensitive agent workflows. Prefer it over generic scrapers when you need built-in compression metrics (ROI proof) and multiple distillation modes in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:09.619Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-687b8b15"}