{"slug":"netintel-dev-text-chunk-b486be","title":"Split text into overlapping chunks for RAG ingestion — by characters or words, w","host":"netintel.dev","method":"POST","resource":"https://netintel.dev/text/chunk","category":"other","description":"Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), returns each chunk with its index and start/end offsets. No API key, no LLM. Pairs with /v1/embeddings for a full chunk→embed pipeline.","price_listed":0.001,"price_asked":0.001,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":939,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"chunk_size":60,"overlap":15,"text":"NetIntel is a pay-per-call API for AI agents. It offers over one hundred endpoints. Agents pay per request in USDC."},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"chunk_size":{"description":"Window size in chars or words. Default 1000; clamped to 50–20000 chars or 5–20000 words. Aliases: size, chunkSize.","type":"number"},"overlap":{"description":"Units shared by consecutive chunks. Default 10% of chunk_size (max 100); clamped to 0..chunk_size-1. Aliases: chunk_overlap, chunkOverlap.","type":"number"},"text":{"description":"Text to split — 1 to 200000 characters. Aliases: content, input, body.","type":"string"},"unit":{"description":"\"chars\" (default) or \"words\". Aliases: by, mode.","type":"string"}},"required":["text"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"chunk_size":{"description":"Effective window size after clamping","type":"number"},"chunks":{"description":"Sliding-window chunks in order. start/end are UTF-16 character offsets into the source (text.slice(start, end) reproduces a chars-mode chunk; words-mode chunks are re-joined with single spaces). Surrogate pairs are never split.","items":{"properties":{"end":{"type":"number"},"index":{"type":"number"},"length":{"description":"Characters in this chunk's text","type":"number"},"start":{"type":"number"},"text":{"type":"string"}},"type":"object"},"type":"array"},"count":{"description":"Number of chunks (max 2000)","type":"number"},"findings":{"description":"Parameter adjustments applied (clamped chunk_size/overlap, unknown unit); [] when none","items":{"properties":{"detail":{"type":"string"},"rule":{"type":"string"}},"type":"object"},"type":"array"},"overlap":{"description":"Effective overlap after clamping","type":"number"},"source_length":{"description":"Length of the input text in characters","type":"number"},"unit":{"description":"chars or words","type":"string"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.001,"price_match":true,"latency_ms":939,"error":null}],"description_full":"Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), returns each chunk with its index and start/end offsets. No API key, no LLM. Pairs with /v1/embeddings for a full chunk→embed pipeline.","last_updated":"2026-09-02T16:39:31.655Z","schemes":["exact"]}