{"uid":"cap_IMsNM8x06v9U_mtcISTZr","slug":"alpha-stream-agentdiet-dev-agentdiet-rag-diet-bm25-budget-web-3016432a","name":"AgentDiet RAG-Diet: BM25-Budget Web Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://alpha-stream.agentdiet.dev/v1/rag-diet)","url":"https://alpha-stream.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_qTmZ2JXEU__l6CwLkA4Br","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt — returning compression ROI proof with each call","exampleAgentPrompt":"Distill the page at https://docs.stripe.com/payments/payment-intents into clean markdown using budget mode, focused on 'payment intent lifecycle', and keep it under 800 tokens.","exampleUseCases":[{"title":"RAG pipeline context compression","prompt":"Fetch and distill https://openai.com/research/gpt-4 into clean markdown so I can inject it into my RAG pipeline without blowing my context window."},{"title":"BM25 focused topic excerpt","prompt":"Pull the page at https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and extract only the parts relevant to 'attention mechanism' in budget mode, with a max of 500 tokens."},{"title":"Structured table extraction from HTML","prompt":"I have a raw HTML string of a financial comparison table — distill it into structured JSON mode so I can pull out the data rows cleanly."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus 'roi_proof' metrics showing raw_tokens, distilled_tokens, compression_ratio_pct, tokens_saved, roi_multiplier, and llm_cost_saved_usd. Also includes billing details and optional cache hit/miss status with latency.","failureModes":["URL unreachable or returns non-200 — distillation cannot proceed, error status returned","Invalid or empty HTML string when using html param — parsing fails","max_tokens set below minimum of 20 — validation error","query param missing when mode=budget — BM25 ranking has nothing to rank against","Payment/402 failure if x402 credentials are invalid or insufficient balance","Rate limiting or timeout when fetching large or slow-loading URLs"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing web content to an LLM — especially when operating with strict context budgets or building RAG pipelines. The BM25 budget mode is uniquely useful when you have a specific query and need only the most relevant excerpt from a page within a token ceiling, which generic scrapers don't provide. Prefer it over raw fetch+truncate approaches when compression ROI metrics matter to your pipeline observability.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:19.104Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-rag-diet-bm25-budget-web-3016432a"}