# Citiview Document Q&A (Ask a Document)

> Citiview Document Q&A (Ask a Document) is a paid API for AI agents from agents.citiviewgroup.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-14).

Accepts a document URL or raw text plus a question, and returns a direct answer backed by exact quotes from the document, using embeddings for long-document search.

## Facts

- Endpoint: GET https://agents.citiviewgroup.com/v1/ask?utm_source=zero.xyz
- Price: $0.02/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-q-a-ask-a-document-adf26b2e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UoiWO8e2PL_W5XYA6s8Xf

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-q-a-ask-a-document-adf26b2e
```

Example prompt: Look at this PDF — https://example.com/annual-report-2024.pdf — and tell me: what was the company's total revenue in 2024? I need the exact quote from the document.

## When to prefer this

Prefer this endpoint when you need a grounded, quote-backed answer from a specific document (PDF, Word, Excel, CSV, or web page) rather than a general web search or open-ended generation. Especially useful when accuracy and traceability to source text matter, such as legal review, financial document analysis, or research extraction. Choose this over generic chat completions when you need the answer to be anchored to a particular document's content.

## Known failure modes

- Document URL is inaccessible or returns a non-200 status — no content to parse
- Unsupported file format beyond PDF, Word, Excel, CSV, or web page
- Question field is missing — required parameter not provided
- Document is too large or encoding is unreadable — parsing fails
- Answer not found in document — model may indicate no relevant content
- Rate limiting or payment failure at $0.02 USDC per call

## How this service works

Ask a document: give a web page, PDF, Word, Excel or CSV URL (or raw text) and a question; get an answer backed by exact quotes from the document. Long documents are searched with embeddings first. Also callable as GET with the same fields as query parameters.

## Output

A natural language answer to the posed question, supported by exact verbatim quotes from the source document. For long documents, relevant sections are first retrieved via embeddings before generating the answer.

## 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",
     "required": [
      "question"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Document or page URL"
      },
      "text": {
       "type": "string",
       "description": "Raw text instead of url"
      },
      "question": {
       "type": "string"
      }
     }
    }
   },
   "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-q-a-ask-a-document-adf26b2e/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)