{"uid":"cap_PnKs3Cpke2_OYRWwfqykC","slug":"alpha-stream-agentdiet-dev-web-distillation-with-bm25-budget-control-c5e6da85","name":"Web Distillation with BM25 Budget Control (RAG Chunk)","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-chunk)","url":"https://alpha-stream.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_K6aLuQ5U5_yny5PIWVKwa","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 compact, agent-ready tokens with BM25-ranked budget control for precise context-window management","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments/payment-intents into compact markdown using budget mode, focused on the query 'how to create a payment intent', and keep it under 500 tokens.","exampleUseCases":[{"title":"RAG pipeline context injection","prompt":"Fetch and distill https://openai.com/research/gpt-4 into markdown so I can inject it into my RAG pipeline — keep it under 800 tokens and focus on the query 'GPT-4 capabilities and benchmarks'."},{"title":"Cost-saving LLM web research","prompt":"I need to read this long news article at https://techcrunch.com/2024/01/15/ai-regulation-update without blowing my token budget — distill it into budget mode with a 300-token ceiling, focused on 'AI regulation policy changes'."},{"title":"Structured data extraction from HTML","prompt":"Here's the raw HTML from a product pricing page — distill it in structured mode so I get the tables and metadata as clean JSON instead of the full HTML mess."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content in the requested format (markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, 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 status — endpoint may return an error status","HTML payload is malformed or empty — distillation may fail or return minimal output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided but mode is not 'budget' — query may be ignored","Rate limiting or payment failure via x402 — request blocked without valid payment","Target site blocks scraping (e.g. Cloudflare) — fetch may fail or return partial content"],"whenToPreferThis":"Choose this endpoint when you need to fit web content into a strict LLM context window and want precise token-budget control with BM25 relevance ranking. It is especially valuable for RAG pipelines where you need the most query-relevant content from a long page, not just a naive truncation. Prefer it over generic scraping tools when you need quantified compression metrics (tokens saved, cost saved) to track efficiency. Use the 'budget' mode with a query and max_tokens when context is scarce; use 'markdown' or 'structured' modes when you want clean reformatting without a hard token cap.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:41.347Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-web-distillation-with-bm25-budget-control-c5e6da85"}