{"uid":"cap_0HxobDMdwaEOZt6yIOMtT","slug":"serp-extract-agentdiet-dev-rag-diet-bm25-budget-controlled-web-bff38d08","name":"RAG Diet – BM25 Budget-Controlled Web Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/rag-diet)","url":"https://serp-extract.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_woFbtnwteEVnqCue0EeOv","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, token-budgeted agent-ready content using BM25 ranking with multiple output modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it using budget mode with the query 'payment intents API' and a max of 500 tokens, so I only get the most relevant content without blowing my context window?","exampleUseCases":[{"title":"RAG pipeline webpage compression","prompt":"Grab the content at https://openai.com/research/gpt-4 and distill it into markdown under 800 tokens, focusing the BM25 query on 'multimodal capabilities' — I need it compact enough to feed into my retrieval pipeline."},{"title":"Competitor pricing page extraction","prompt":"Fetch https://www.anthropic.com/pricing and extract a structured summary — tables, metadata, the works — so I can compare their pricing tiers without wading through the full page."},{"title":"Raw HTML distillation from scraped content","prompt":"I already have the raw HTML from a product page — can you distill it directly in skeleton mode so I just get the outline of headings and key sections without all the noise?"}],"resultDescription":"Returns a JSON object containing the distilled content (markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), an ROI proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — fetch fails with error status","HTML payload is empty or malformed — distillation returns minimal/empty data","max_tokens set too low (below 20) — rejected by schema validation","BM25 query not provided when mode=budget — may return unfiltered or empty results","Payment not included or insufficient — HTTP 402 response blocking execution","Rate limiting or timeout on slow target URLs"],"whenToPreferThis":"Choose this endpoint when you need to pass web content to an LLM but want to minimize token usage and cost — especially when a specific query focus is known (use budget+BM25 mode) or when you need structured extraction rather than raw HTML. It is superior to generic scrapers when token budgeting, compression ratio reporting, and LLM cost savings matter, and uniquely supports raw HTML input without re-fetching.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:46.162Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-rag-diet-bm25-budget-controlled-web-bff38d08"}