{"uid":"cap_reTSf7ULWdCAo3HNWOHPX","slug":"agentrxi-url-text-chunker-with-bge-m3-embeddings-2163e158","name":"AgentRXI URL/Text Chunker with BGE-M3 Embeddings","description":"Ready-to-search chunks: turns a URL (page, PDF, Office file) or text into clean overlapping chunks with character offsets and bge-m3 embeddings (1024 dims) in one call, ready for any vector store. Up to 300 chunks. Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/chunk?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string"},"text":{"type":"string"},"embed":{"type":"boolean","description":"Include embeddings (default true)"},"overlap":{"type":"integer","description":"Default 150"},"chunk_size":{"type":"integer","description":"Characters per chunk, 200 to 4000 (default 1000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.015","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":"$0.015/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.015","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.015","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Vopr2ZxPWjf0snZI8iYax","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.015","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts a URL (webpage, PDF, Office file) or raw text into overlapping chunks with character offsets and 1024-dimensional bge-m3 embeddings, ready for vector store ingestion.","exampleAgentPrompt":"Chunk this URL https://example.com/whitepaper.pdf into 1000-character overlapping segments with 150-character overlap and include bge-m3 embeddings so I can load the results straight into my vector store.","exampleUseCases":[{"title":"RAG pipeline for a research PDF","prompt":"Take this PDF at https://arxiv.org/pdf/2401.00001 and break it into 800-character chunks with 150-character overlap, with bge-m3 embeddings included, so I can upload them to my Pinecone index."},{"title":"Indexing a knowledge-base article","prompt":"Chunk the support article at https://docs.myproduct.com/faq into overlapping 1000-character pieces and return the embeddings so my agent can do semantic search over it."},{"title":"Embedding raw pasted text","prompt":"I have this block of text I want to search over — can you split it into 500-character overlapping chunks with embeddings and give me back the character offsets for each chunk?"}],"resultDescription":"Returns up to 300 text chunks, each with its character start/end offsets within the source document and a 1024-dimensional bge-m3 embedding vector, ready for direct insertion into any vector store.","failureModes":["URL is unreachable or returns a non-200 response — chunk list will be empty or error returned","Unsupported file type at URL — parsing may fail","chunk_size outside 200–4000 range — validation error","Text or URL input missing — required field error","Document too large — may be truncated to 300 chunks maximum"],"whenToPreferThis":"Choose this endpoint when you need chunking and embedding in a single pay-per-call step without managing your own embedding infrastructure. Ideal for RAG pipelines that need bge-m3 (multilingual, 1024-dim) embeddings with overlapping chunks and character offsets, especially when the source is a URL (webpage, PDF, or Office file) rather than pre-extracted text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:19.563Z","isFirstParty":false,"canonicalSlug":"agentrxi-url-text-chunker-with-bge-m3-embeddings-2163e158"}