{"uid":"cap_adTdFXNMlsd2xCo-FbDp1","slug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-51064c28","name":"Web URL 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://shopify-intel.agentdiet.dev/v1/rag-chunk)","url":"https://shopify-intel.agentdiet.dev/v1/rag-chunk?utm_source=zero.xyz","method":"GET","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_FxLXV5iFBoWPmlsLsDbnk","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"shopify-intel.agentdiet.dev","brandSlug":"shopify-intel-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and BM25-ranked token budgeting","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, capping it at 2000 tokens and focusing the BM25 budget on 'payment intents'.","exampleUseCases":[{"title":"RAG pipeline webpage compression","prompt":"Fetch https://docs.shopify.com/api/admin-rest and distill it into structured JSON tables so I can load it into my RAG pipeline without blowing my token budget."},{"title":"Budget-capped competitor research","prompt":"Pull the content from https://www.competitor.com/pricing and give me a BM25-focused excerpt about 'enterprise plans', keeping it under 500 tokens."},{"title":"Documentation skeleton for agent memory","prompt":"Get the skeleton outline of https://platform.openai.com/docs/guides/function-calling so my agent can navigate its structure without reading the whole page."}],"resultDescription":"Returns a distilled version of the target page in the requested format (markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), along with ROI proof metrics showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (below 20) causes a validation error","BM25 query provided without mode=budget may be ignored","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-rendered pages may return incomplete content","Missing required 'url' parameter returns a 400-level error","x402 payment failure prevents endpoint access"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and want to minimize token consumption. It is particularly valuable when working with large documentation pages, when you have a strict token budget, or when you need BM25-ranked relevance filtering to extract only the portions of a page relevant to a specific query. Prefer this over raw web scrapers when token efficiency and structured output format matter, or when you want built-in ROI metrics showing how much context and cost you saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T07:49:47.699Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-3ffa961f"}