{"uid":"cap_1qQRJByNu2sMzNAzAR1Mp","slug":"workflows-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-budget-4ba20f15","name":"RAG Diet — URL/HTML Distiller 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://workflows.agentdiet.dev/v1/rag-diet)","url":"https://workflows.agentdiet.dev/v1/rag-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_qAlw7k7Lc6VVh0jXuMDPP","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready tokens using one of four modes (markdown, structured, skeleton, or BM25 budget-capped excerpt).","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"RAG pipeline token cost reduction","prompt":"Fetch https://openai.com/pricing and distill it into structured tables so I can plug it into my RAG pipeline without blowing my token budget."},{"title":"Topic-focused excerpt for research","prompt":"I need a BM25 budget excerpt from https://en.wikipedia.org/wiki/Large_language_model focused on 'context window scaling' — cap it at 300 tokens."},{"title":"Raw HTML cleanup for agent ingestion","prompt":"I have raw HTML from a product page — can you distill it into skeleton mode so my agent just sees the headings and key structure without all the noise?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio %, ROI multiplier, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch error returned","HTML payload is empty or malformed — distillation may return minimal output","mode=budget used without a 'query' field — BM25 scoring has no focus signal","max_tokens set below 20 — validation error","Invalid or expired x402 payment — 402 Payment Required response","URL is behind authentication or a bot wall — content may be inaccessible"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of a webpage or raw HTML before feeding it to an LLM, especially when you want BM25-guided relevance filtering with a hard token budget ceiling. It is better than generic scrapers when LLM cost optimization and compression ratio measurement matter, or when you need structured output modes (markdown, tables, skeleton) rather than raw HTML text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:53.725Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-budget-4ba20f15"}