{"uid":"cap_iXHKO0wAsZt1qucUGbJkJ","slug":"github-audit-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-ae2a01a7","name":"RAG Token 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://github-audit.agentdiet.dev/v1/rag-token-diet)","url":"https://github-audit.agentdiet.dev/v1/rag-token-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_RBNUWGl_I6_MJsFvHJA_v","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"github-audit.agentdiet.dev","brandSlug":"github-audit-agentdiet-dev-mpp","brandBaseUrl":"https://github-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton, or BM25-ranked excerpt within a strict token budget","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/payment-intents into clean Markdown using budget mode, focused on 'payment intent lifecycle', and keep it under 800 tokens.","exampleUseCases":[{"title":"RAG pipeline token cost reduction","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) and distill it in budget mode with the query 'attention mechanism self-attention', capping the output at 600 tokens — I want to minimize how much I send to the LLM."},{"title":"Structured data extraction from docs page","prompt":"Pull the Stripe docs page at builtin://stripe-docs and distill it into structured mode so I get tables and metadata I can parse programmatically."},{"title":"Skeleton outline of a long article","prompt":"Give me a skeleton outline of https://www.paulgraham.com/worked.html — just the high-level headings and structure, no full body text."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","HTML payload is malformed or empty — distillation returns minimal or empty data","max_tokens set below minimum of 20 — validation error","mode=budget used without a query field — BM25 ranking has no focus signal","Rate limit or payment failure via x402 — 402 response with payment required","Idempotency-Key reuse on different payloads — may return cached prior result"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget or minimize LLM API costs. It is especially valuable for RAG pipelines where raw HTML is too verbose, when you need BM25-ranked excerpts focused on a specific query, or when you want clean Markdown or structured tables from arbitrary web pages. Prefer it over generic scrapers when token efficiency and cost-savings proof (roi_proof) matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:12.852Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-ae2a01a7"}