{"uid":"cap_nooN9JFkFGaLj_RP1A6Ra","slug":"defi-yield-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-budget-1ab5aec7","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://defi-yield.agentdiet.dev/v1/rag-diet)","url":"https://defi-yield.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_TfUCwaAymrPG-BQ9s6e0r","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compressed Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt for LLM consumption.","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/payment-intents into compressed Markdown using budget mode with a focus query of 'payment intent lifecycle' and a max token budget of 500 tokens.","exampleUseCases":[{"title":"RAG pipeline web page compression","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into clean Markdown so I can drop it into my RAG pipeline without blowing my token budget."},{"title":"Query-focused excerpt for research","prompt":"Pull the page at https://arxiv.org/abs/2305.10601 and give me only the sections most relevant to 'chain-of-thought prompting' — keep it under 300 tokens using budget mode."},{"title":"Structured data extraction from docs","prompt":"Grab the Stripe pricing page at https://stripe.com/pricing and distill it into structured JSON tables showing all the fee tiers and product names."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked excerpt depending on mode), plus an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, and an optional 'cache' block indicating HIT/MISS status and latency.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error status","HTML content is empty or unparseable — distilled output may be minimal or empty","BM25 query not provided when mode=budget — may fall back to unfiltered truncation","max_tokens set below minimum of 20 — request rejected with validation error","Target page is behind authentication/paywall — only publicly accessible content is distilled","Rate limits or payment failure on the x402 layer — request blocked before processing"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM and want to minimize token usage and cost. It is particularly valuable in RAG pipelines where you need to compress long pages to fit context windows, when you want BM25-ranked excerpts focused on a specific query, or when you need structured JSON extraction from messy HTML. Prefer it over raw fetch-and-parse approaches when token budget control and compression ROI reporting matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:56.305Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-budget-1ab5aec7"}