{"uid":"cap_58DOIh-Ap4PawEmupksw_","slug":"company-enrich-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-5ad06910","name":"RAG Diet — URL/HTML 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://company-enrich.agentdiet.dev/v1/rag-diet)","url":"https://company-enrich.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_n-itjpHESGggLCofo7e5l","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a webpage URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or a BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean Markdown using budget mode, focused on 'payment intents', with a max of 500 tokens — I want to see how many tokens you saved me.","exampleUseCases":[{"title":"Token-efficient RAG context preparation","prompt":"Fetch and distill https://docs.anthropic.com/claude/reference into Markdown for me — I need it compressed as much as possible to stay within my LLM context window."},{"title":"Query-focused excerpt for research grounding","prompt":"Pull the page at https://en.wikipedia.org/wiki/Retrieval-augmented_generation and give me a BM25 budget excerpt focused on 'vector databases', capped at 300 tokens — I just need the relevant bits."},{"title":"Structured data extraction from company site","prompt":"Distill https://openai.com/pricing into structured mode so I can get the pricing tables and metadata as clean JSON without all the surrounding page noise."}],"resultDescription":"Returns a status field ('ok'), a data object containing the distilled content in the chosen format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), an roi_proof object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may return minimal or empty data","Token budget (max_tokens) is set too low (below 20) — validation error returned","BM25 query is provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — 402 response requiring payment","Requested URL is behind authentication or paywalled — content cannot be fetched"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM and want to minimize token consumption and cost — especially in RAG pipelines where full HTML pages are too bloated. It is ideal when you need a specific portion of a page matching a query (BM25 budget mode), want structured extraction of tables and metadata, or need a skeleton outline of a long document. Prefer it over generic scrapers when token efficiency and LLM cost savings are primary concerns, or when you need built-in ROI proof of compression gains.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:11.525Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-rag-diet-url-html-distiller-with-bm25-5ad06910"}