{"uid":"cap_5p0wTxUrSWV7SP_hWLcnj","slug":"private-vector-embedding-indexing-20ae73b9","name":"Private Vector Embedding & Indexing","description":"Embed and index documents into a private vector collection (768-dim, cosine). documents=[{id,text,metadata}], namespace picks the collection. Returns documents, chunks, tokens and latency.","url":"https://pearl-valium-stickers-upc.trycloudflare.com/v1/index?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"chunks":{"type":"number"},"points":{"type":"number"},"documents":{"type":"number"},"collection":{"type":"string"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","displayCostAsset":"USDC","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ZJNE51NkoGb7JTVpOuAOL","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Embeds and indexes documents into a private 768-dimensional cosine vector collection, returning chunk, token, and latency stats.","exampleAgentPrompt":"Index these three product documentation pages into my 'product-docs' collection — each has an id, the full text, and some metadata tags — and tell me how many chunks and tokens were created.","exampleUseCases":[{"title":"Private RAG knowledge base ingestion","prompt":"Take these 50 internal policy documents — each with an id, full text, and department metadata — and index them into the 'company-policies' collection so I can run private semantic search over them later."},{"title":"Customer support FAQ vectorization","prompt":"I have 200 FAQ entries with ids, question-and-answer text, and category metadata. Index them all into the 'support-faq' collection and tell me the total chunks and tokens produced."},{"title":"Research paper corpus indexing","prompt":"Embed and index these 10 research paper abstracts into the 'ml-papers' namespace — each has a paper id, abstract text, and author metadata — I want to do semantic similarity search over them afterward."}],"resultDescription":"Returns a summary including the list of indexed documents, number of chunks created, total tokens processed, and indexing latency in milliseconds for the operation against the specified collection.","failureModes":["Invalid or missing documents array returns 400 error","Collection name conflict or namespace collision may overwrite or reject documents","Overly large documents or too many chunks may exceed memory limits of the local GPU host","Cloudflare tunnel downtime causes connection failures or timeouts","Malformed document objects (missing id or text) cause indexing to fail partially or entirely"],"whenToPreferThis":"Choose this endpoint when you need to embed and persist documents into a private, local 768-dimensional cosine vector index without sending data to a third-party cloud embedding service. Ideal for privacy-sensitive workloads, RAG pipeline ingestion, or when you need full control over the vector collection namespace and metadata. Prefer over cloud-hosted vector DBs when data residency or uncensored model embedding matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:39:57.135Z","isFirstParty":false,"canonicalSlug":"private-vector-embedding-indexing-20ae73b9"}