{"uid":"cap_NBSoatHI9tjTEKoGwWKmi","slug":"relaystation-rag-ingest-bundle-ed551217","name":"Relaystation RAG Ingest Bundle","description":"~$0.01–$0.02/run, bills the sum of steps. One-call RAG ingest: chunk text, embed every chunk, write the vectors into a durable vector index (created for you on first use) — agent memory that persists across sessions, no vector DB to run. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny","url":"https://api.relaystation.ai/v1/bundles/rag-ingest","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"properties":{}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_283R_5aUOZu5IcWfbEKAe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"One-call RAG pipeline that chunks text, embeds every chunk, and writes vectors into a durable persistent vector index — no separate vector DB required.","exampleAgentPrompt":"Ingest this product documentation text into my persistent vector index so my agent can retrieve it later: 'Our return policy allows returns within 30 days of purchase with original receipt...'","exampleUseCases":[{"title":"Knowledge base for customer support bot","prompt":"Take this FAQ document text and ingest it into my agent's vector memory so the support bot can answer questions from it later: 'Q: How do I reset my password? A: Click Forgot Password on the login page...'"},{"title":"Persistent research memory across sessions","prompt":"Store these research notes into my RAG index so I can query them in future sessions — here's the text: 'Study findings from Q3 2024: user retention improved 18% after onboarding redesign...'"},{"title":"Codebase documentation indexing","prompt":"Chunk and embed this API reference documentation and write it into my vector index: 'The /users endpoint accepts GET and POST requests. GET returns a paginated list of users...'"}],"resultDescription":"The endpoint processes the provided text by chunking it, generating embeddings for each chunk, and writing those vectors into a durable vector index associated with the caller. The index is created automatically on first use and persists across sessions, enabling future semantic retrieval. The response confirms successful ingestion and provides metadata about the indexed chunks and index state.","failureModes":["Invalid HTTP method in input body (only POST, PUT, PATCH accepted)","Invalid bodyType value outside enum (json, form-data, text)","Missing required 'input' field returns validation error","Insufficient USDC balance to cover $0.02 run cost","Empty or malformed body content causing chunking failure","x402 payment negotiation failure if wallet not configured"],"whenToPreferThis":"Choose this endpoint when you need a fully managed, one-call RAG pipeline that eliminates the need to run your own vector database. It is ideal for agents that need persistent memory across sessions without infrastructure overhead. Prefer it over raw embedding APIs when you want chunking, embedding, and indexing handled atomically in a single call at a predictable low per-run cost.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:56:49.819Z","isFirstParty":false}