{"uid":"cap_fL1LmBpr9wRxBWB3qEivS","slug":"github-audit-agentdiet-dev-agentdiet-article-extractor-with-bm25-e3223f54","name":"AgentDiet Article Extractor 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://github-audit.agentdiet.dev/v1/article-extractor)","url":"https://github-audit.agentdiet.dev/v1/article-extractor?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_1gYILnD9TYhSmIt__08nt","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 a URL or processes raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or BM25-ranked token-budgeted excerpts","exampleAgentPrompt":"Grab the article at https://techcrunch.com/2025/05/01/openai-funding/ and distill it into clean markdown, keeping it under 2000 tokens and focusing on funding amounts and investor names.","exampleUseCases":[{"title":"LLM context window optimization","prompt":"Fetch https://docs.stripe.com/payments/payment-intents and distill it into a BM25 budget excerpt focused on 'PaymentIntent lifecycle' — keep it under 1500 tokens so it fits in my prompt."},{"title":"News article extraction for research","prompt":"Pull the article from https://www.reuters.com/technology/ai-regulation-2025 and convert it to clean markdown so I can read it without all the ads and navigation junk."},{"title":"Structured data extraction from HTML","prompt":"I have this raw HTML from a product page — run it through the article extractor in structured mode so I get the tables and metadata as clean JSON I can process programmatically."}],"resultDescription":"Returns a JSON object containing: distilled content in the requested mode (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), ROI proof metrics 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 confirmation.","failureModes":["URL is unreachable or returns non-200 — extraction fails with error status","Raw HTML is malformed or empty — distillation returns minimal output","max_tokens set too low relative to content — may truncate critical information","BM25 query not provided when mode=budget — falls back to default behavior","Payment not included or invalid — HTTP 402 returned before processing","URL behind login/paywall — fetcher cannot access protected content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content within strict token budgets, particularly when using BM25-ranked extraction to surface the most query-relevant passages. Ideal for RAG pipelines, research agents, and LLM workflows where reducing token cost matters. Prefer over generic scrapers when you need built-in token-budget enforcement, compression ratio reporting, or multiple distillation modes (markdown, structured, skeleton, budget) from a single paid-per-call micro-API.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:57.916Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-agentdiet-article-extractor-with-bm25-e3223f54"}