# Citiview Document Chunker with Embeddings

> Citiview Document Chunker with Embeddings is a paid API for AI agents from agents.citiviewgroup.com, paid per call via x402, $0.015/call, status unknown (last checked 2026-10-14).

Converts a URL (web page, PDF, Office file) or raw text into clean overlapping chunks with character offsets and bge-m3 embeddings (1024 dims), ready for vector store ingestion.

## Facts

- Endpoint: GET https://agents.citiviewgroup.com/v1/chunk?utm_source=zero.xyz
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/citiview-document-chunker-with-embeddings-e8650d15
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mrKqbMH3dbOKCFyOjwdJh

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability citiview-document-chunker-with-embeddings-e8650d15
```

Example prompt: Chunk this PDF at https://example.com/report.pdf into overlapping segments of 1000 characters each with 150-character overlap, and include bge-m3 embeddings so I can load them straight into my vector store.

## When to prefer this

Choose this endpoint when you need both chunking and embedding in a single call, specifically with bge-m3 (1024-dim) embeddings suitable for multilingual semantic search. It is ideal for RAG pipeline ingestion where you want overlapping chunks with character offsets from a URL or raw text, without managing a separate embedding model. Prefer alternatives if you need a different embedding model, more than 300 chunks, or only chunking without embeddings.

## Known failure modes

- URL is unreachable or returns a non-200 response — chunking fails with an error
- Unsupported file format at the provided URL — only web pages, PDFs, and Office files are supported
- chunk_size out of range (must be 200–4000) — request rejected with validation error
- Document exceeds the 300-chunk limit — output is capped at 300 chunks
- embed=false requested — embeddings are omitted from the response
- Oversized document may time out or be truncated before 300 chunks are produced

## How this service works

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.

## Output

Returns up to 300 text chunks, each with its text content, start and end character offsets within the original document, and a 1024-dimensional bge-m3 embedding vector. The embeddings are immediately usable with any vector store (Pinecone, Weaviate, Qdrant, etc.) for semantic similarity search.

## Request schema (JSON Schema)

```json
{
 "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"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/citiview-document-chunker-with-embeddings-e8650d15/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.citiviewgroup.com](https://www.zero.xyz/host/agents.citiviewgroup.com/llms.txt)