{"uid":"cap_-pRT-wsQwbfqa0QVbo4_s","slug":"hn-pulse-agentdiet-dev-web-content-distiller-with-bm25-budget-control-8f7b5d2e","name":"Web Content 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://hn-pulse.agentdiet.dev/v1/rag-diet)","url":"https://hn-pulse.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_PHO1TjW0Rs9B0LZi_5VZe","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact, agent-ready tokens using multiple modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into a BM25 budget excerpt focused on 'webhook event handling' — keep it under 500 tokens so I don't blow my context window?","exampleUseCases":[{"title":"RAG pipeline context compression","prompt":"Pull the content from https://docs.openai.com/api-reference and distill it down to a BM25 budget excerpt around 'streaming completions' — cap it at 300 tokens so it fits cleanly into my retrieval chunk."},{"title":"Structured data extraction from webpage","prompt":"Grab https://example.com/pricing and distill it into structured JSON tables — I want to see all the plan names, prices, and feature lists pulled out cleanly."},{"title":"Skeleton outline for long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline so I can quickly understand its document structure without reading the whole thing."}],"resultDescription":"Returns a distilled data object (markdown, structured JSON, skeleton, or BM25-ranked excerpt), an ROI proof object showing raw tokens, distilled tokens, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may error or return empty data","mode=budget used without a query field — BM25 ranking has no focus term","max_tokens set below minimum of 20 — request rejected","HTML payload is malformed or empty — distillation produces minimal output","Payment fails (402) — call blocked until valid x402 payment provided","Rate limiting or timeout on slow target URLs — latency spikes"],"whenToPreferThis":"Choose this endpoint when you need to compress web content before feeding it to an LLM to save tokens and cost, especially when you have a specific query focus and a hard token budget. It is particularly valuable in RAG pipelines where raw HTML would exceed context windows. Prefer it over generic scrapers when you need BM25-ranked relevance filtering, structured extraction, or markdown normalization in a single call with built-in ROI accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:51.758Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-content-distiller-with-bm25-budget-control-8f7b5d2e"}