{"uid":"cap_oY5Zc_7S3YGbjkF4RVXb_","slug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-ee9c578b","name":"Web Distillation 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://domain-osint.agentdiet.dev/v1/rag-diet)","url":"https://domain-osint.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_r2n5VglQn0x3nB2KQPIhF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML payload into clean Markdown, structured JSON, skeleton outline, or a token-budgeted BM25-focused excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode focused on 'payment intents', with a maximum of 500 tokens.","exampleUseCases":[{"title":"RAG pipeline page compression","prompt":"Grab the content from https://openai.com/research/gpt-4 and distill it into clean markdown so I can feed it into my RAG pipeline without blowing up my token budget."},{"title":"BM25 focused doc excerpt","prompt":"Distill https://docs.aws.amazon.com/lambda/latest/dg/welcome.html in budget mode, focused on the query 'cold start latency', and keep it under 300 tokens — I only need the relevant bits."},{"title":"Structured table extraction from HTML","prompt":"I've got this raw HTML from a pricing page — can you distill it in structured mode to pull out the pricing tables and metadata as JSON?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured tables, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may cause incomplete distillation","mode=budget without a query may return unfiltered or empty excerpts","max_tokens set too low may result in truncated or meaningless output","Private or auth-gated pages return empty content since no credentials are passed","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before feeding web content to an LLM, especially in RAG pipelines, agent memory systems, or agentic browsing workflows. It is ideal when you have a specific focus query (BM25 mode) and a strict token budget. Prefer it over raw HTTP fetching whenever compression ratio and LLM cost savings matter. Use it over general scrapers when you need clean Markdown or structured JSON tables rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:53.648Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-distillation-with-bm25-budget-control-04fd791d"}