{"uid":"cap_U4FaP9jMna5DWaOtFCWJ5","slug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-3e8ba22c","name":"Web 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://sec-intel.agentdiet.dev/v1/rag-chunk)","url":"https://sec-intel.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_9qg9JEfHtofsqRUxnAwOl","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt for RAG pipelines","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments into clean markdown using budget mode, focused on the query 'payment intents API', and keep it under 500 tokens.","exampleUseCases":[{"title":"RAG pipeline web content ingestion","prompt":"Fetch and distill https://openai.com/research/gpt-4 into structured markdown so I can embed it into my RAG knowledge base without blowing my token budget."},{"title":"BM25-focused excerpt for LLM grounding","prompt":"Pull the page at https://docs.anthropic.com/claude/reference and return only the parts most relevant to 'tool use and function calling' using budget mode with a 300 token ceiling."},{"title":"Raw HTML cleanup for agent processing","prompt":"I have raw HTML from a scraped product page — can you distill it into a clean skeleton outline so my agent can quickly understand the page structure without processing all the noise?"}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt) under 'data', an ROI proof object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache status (HIT/MISS) and billing details including fee charged.","failureModes":["Missing required 'url' field returns a validation error","Invalid or unreachable URL causes fetch failure","mode=budget without a 'query' field may return unfiltered content","max_tokens set below 20 fails schema validation","Rate limiting or payment failure via x402 blocks execution","HTML too large to process within time limits may time out"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and want to minimize token usage — especially when you have a specific query to focus on (BM25 budget mode) or need structured/skeleton output rather than raw HTML. Prefer it over generic scrapers when token cost and compression ratio matter, or when you need an ROI proof of how much context was saved. It is also ideal when you already have raw HTML and want to skip an extra fetch step.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:25.628Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-distillation-with-bm25-budget-control-bba76e87"}