{"uid":"cap_Y2HhjROoLvTBSrxN3PDqE","slug":"defi-yield-agentdiet-dev-web-content-distillation-with-bm25-budget-f1495f94","name":"Web Content 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://defi-yield.agentdiet.dev/v1/rag-chunk)","url":"https://defi-yield.agentdiet.dev/v1/rag-chunk?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_OIMpeyldlmitk44lMBRat","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt with token savings reporting","exampleAgentPrompt":"Fetch the Stripe docs page at https://stripe.com/docs/api and distill it in budget mode focused on 'payment intents' with a 500 token ceiling, so I can pass only the relevant chunk to my LLM.","exampleUseCases":[{"title":"RAG pipeline content ingestion","prompt":"Grab the content at https://docs.openai.com/api-reference and convert it to clean markdown so I can index it in my RAG pipeline."},{"title":"Token-budget excerpt for LLM context","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) in budget mode with the query 'attention mechanism' and keep it under 300 tokens — I need to fit this into a tight LLM prompt."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it into structured JSON tables so I can compare their pricing tiers against ours."}],"resultDescription":"Returns a distilled representation of the webpage or HTML in the requested mode (Markdown, structured JSON, skeleton, or BM25 budget excerpt), along with ROI proof metrics showing raw vs. distilled token counts, compression ratio, tokens saved, estimated LLM cost saved in USD, and cache hit/miss status with latency.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is empty or malformed — distillation may return minimal output","mode=budget without a query parameter — BM25 ranking cannot proceed without a focus query","max_tokens set below 20 — rejected by schema validation","Payment not included or insufficient — x402 payment required error","Target site blocks scraping — content may be incomplete or empty"],"whenToPreferThis":"Choose this endpoint when you need to compress web content before feeding it to an LLM, especially when working with token budgets or RAG pipelines. The BM25 budget mode is uniquely suited for extracting only the most query-relevant passages from a page within a strict token ceiling. Prefer this over generic scrapers when you need ROI proof of token savings and cost reduction, or when you need multiple distillation modes (markdown, structured, skeleton, budget) from a single endpoint. Best for agent workflows where minimizing LLM context cost is a priority.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:10.618Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-content-distillation-with-bm25-budget-f1495f94"}