{"uid":"cap_8XhaeNYXTK7S29b89wmDc","slug":"json-repair-agentdiet-dev-rag-diet-bm25-budget-controlled-web-distiller-08f21b56","name":"RAG Diet — BM25 Budget-Controlled Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://json-repair.agentdiet.dev/v1/rag-diet)","url":"https://json-repair.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_se2b1pdyPtkO02Q7ZdUBO","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML payload into compact, agent-ready tokens using BM25-ranked budget control and multiple distillation modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it using budget mode with the query 'payment intents' and a strict ceiling of 500 tokens, then show me the compressed markdown.","exampleUseCases":[{"title":"Token-budget RAG pipeline ingestion","prompt":"Grab https://openai.com/pricing and distill it in budget mode focused on the query 'embedding model cost' with a max of 300 tokens — I need to fit it inside my RAG context window without blowing my budget."},{"title":"Structured data extraction from product page","prompt":"Distill https://www.anthropic.com/product into structured mode so I get the tables and metadata as JSON — I want to compare their model specs in a structured format."},{"title":"Summarize raw HTML from a scrape","prompt":"I already scraped this HTML — can you distill it directly in markdown mode without re-fetching the URL? Here's the raw HTML: <html>...</html>"}],"resultDescription":"Returns a JSON object containing distilled content (Markdown, structured JSON, skeleton outline, or BM25-filtered excerpt depending on mode), ROI proof metrics (raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, ROI multiplier), optional cache status (HIT/MISS), and billing details including fee charged.","failureModes":["URL is unreachable or returns non-200 status — service may return an error status","HTML payload is malformed or empty — distillation may fail or return minimal content","mode=budget used without a query field — BM25 ranking has no focus term","max_tokens set below minimum of 20 — request rejected by schema validation","Payment not authorized via x402 — 402 Payment Required response blocks execution","Target URL blocks bots or requires authentication — fetched content may be incomplete"],"whenToPreferThis":"Choose this endpoint when you need to compress web pages or HTML payloads into a strict token budget before feeding them into an LLM or RAG pipeline, especially when you want BM25-ranked relevance filtering against a specific query. It is particularly valuable when LLM context costs are a concern and you need measurable ROI proof (compression ratio, tokens saved, cost saved). Prefer it over generic scrapers when you need multiple output modes (markdown, structured, skeleton, budget) and built-in token accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:23.387Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-rag-diet-bm25-budget-controlled-web-distiller-08f21b56"}