> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://documents.pyramid-ai.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://documents.pyramid-ai.com/_mcp/server.

# Single-shot Q&A over project, org, or Open Library knowledge

POST https://api.pyramid-ai.com/api/v2/agent/query
Content-Type: application/json

Stateless query endpoint — does not persist a chat history. Use this for
one-off questions. For multi-turn conversation, use POST /chat instead.

`search_scope` picks the corpus: `project` (default, `project_id`
required), `org` (the org's own documents), or `open_library` (the
shared Open Library corpus of Hong Kong government engineering
documents — requires the `api.open_library` feature).


Reference: https://documents.pyramid-ai.com/api-reference/api-explorer/agent/query-agent

## Authentication

- `Authorization` header (bearer token, required) — Pyramid API key (prefix with "Bearer ")

## Servers

- `https://api.pyramid-ai.com` (Production, default)
- `https://api-staging.pyramid-ai.com` (Staging (sandbox) — use pai_test_* keys)

## Request

### Body (application/json)

This endpoint expects an object.

- `query` (string, required)
- `project_id` (string, optional) — Required when search_scope is "project" (the default); must be omitted for "org" and "open_library".
- `max_sources` (integer, optional, default: 5)
- `response_format` (enum, optional, default: text)
  - Allowed values: `text`, `json`
- `response_schema` (ApiV2AgentQueryPostRequestBodyContentApplicationJsonSchemaResponseSchema, optional) — JSON schema for structured output (required when response_format=json)
- `search_scope` (enum, optional) — Which corpus the query searches. Exclusive — one request searches one corpus. - `project` — the given project's document chunks (`project_id` required). - `org` — the organization's own org-level documents (`project_id` must be omitted). - `open_library` — the shared Open Library corpus of Hong Kong government engineering documents (`project_id` must be omitted). Requires the `api.open_library` feature to be enabled for your organization. When omitted, the scope is derived for backward compatibility: `project` when `project_id` is present, `org` otherwise.
  - Allowed values: `project`, `org`, `open_library`

## Response

### 200

Query result

- `request_id` (string, required) — Server-generated per-request UUID. Also sent as `X-Request-Id` response header. Include in support tickets.
- `success` (any, required)
- `data` (ApiV2AgentQueryPostResponsesContentApplicationJsonSchemaData, optional)
- `pagination` (Pagination, optional) — Present only on list endpoints. Top-level (not nested inside `data`).

## Errors

### 400 Bad Request Error

Validation error

- `success` (any, required)
- `error` (ApiErrorError, required)
- `request_id` (string, required)

### 401 Unauthorized Error

Unauthorized

- `success` (any, required)
- `error` (ApiErrorError, required)
- `request_id` (string, required)

## Types

### ApiV2AgentQueryPostRequestBodyContentApplicationJsonSchemaResponseSchema

JSON schema for structured output (required when response_format=json)

### ApiV2AgentQueryPostResponsesContentApplicationJsonSchemaData

- `answer` (string, required)
- `sources` (list of Source, required)
- `model` (string, required)
- `usage` (ApiV2AgentQueryPostResponsesContentApplicationJsonSchemaDataUsage, required)

### Pagination

Offset-based pagination for list endpoints. Clients compute `has_more` from `offset + data.length < total`. Cursor pagination may be added per-endpoint later if deep-pagination performance becomes a concern.

- `total` (integer, required) — Total item count matching the filters (ignoring limit/offset).
- `offset` (integer, required)
- `limit` (integer, required, default: 50)

### ApiErrorError

- `code` (enum, required)
  - Allowed values: `VALIDATION_ERROR`, `UNAUTHORIZED`, `FORBIDDEN`, `FEATURE_NOT_ENABLED`, `AGENT_NOT_ENABLED`, `QUOTA_EXCEEDED`, `NOT_FOUND`, `CONFLICT`, `IDEMPOTENCY_KEY_REUSED`, `IDEMPOTENCY_IN_PROGRESS`, `UPLOAD_NOT_FOUND`, `UPLOAD_SIZE_MISMATCH`, `RATE_LIMITED`, `INTERNAL_ERROR`
- `message` (string, required) — Human-readable description. May be shown to end users; keep stable across minor changes.
- `docs_url` (string, optional) — Link to the error's documentation section.
- `field` (string, optional) — Only for `VALIDATION_ERROR`. JSONPath-ish reference to the offending field (e.g. `body.project_id`).
- `feature` (string, optional) — Only for `FEATURE_NOT_ENABLED`. The feature key the request required.

### Source

Citation pointing to a chunk in a project document or the Open Library. Used by agent query, chat, and check verify responses.

- `chunk_id` (string, required) — Chunk identifier. A UUID for project documents; an opaque string for Open Library chunks.
- `file_name` (string, required)
- `relevance` (double, required)
- `page` (integer, optional, nullable) — Page number within the source document. Always null for Open Library sources.
- `quote` (string, optional, nullable) — Verbatim excerpt that supports the answer.
- `source_type` (enum, optional) — Which corpus the source came from. Absent on legacy responses; treat absence as `document`.
  - Allowed values: `document`, `open_library`
- `url` (string, optional, nullable) — Public URL of the source document. Only present on Open Library sources.

### ApiV2AgentQueryPostResponsesContentApplicationJsonSchemaDataUsage

## Examples

**Request**

```json
{
  "query": "What are the main compliance requirements?"
}
```

**Response**

```json
{
  "request_id": "string",
  "success": null,
  "data": {
    "answer": "string",
    "sources": [
      {
        "chunk_id": "string",
        "file_name": "tree_survey_q1.pdf",
        "relevance": 0.95,
        "page": 1,
        "quote": "string",
        "source_type": "document",
        "url": "string"
      }
    ],
    "model": "string",
    "usage": {}
  },
  "pagination": {
    "total": 127,
    "offset": 0,
    "limit": 50
  }
}
```

**SDK Code**

```python
import requests

url = "https://api.pyramid-ai.com/api/v2/agent/query"

payload = { "query": "What are the main compliance requirements?" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.pyramid-ai.com/api/v2/agent/query';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"query":"What are the main compliance requirements?"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.pyramid-ai.com/api/v2/agent/query"

	payload := strings.NewReader("{\n  \"query\": \"What are the main compliance requirements?\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.pyramid-ai.com/api/v2/agent/query")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"What are the main compliance requirements?\"\n}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.pyramid-ai.com/api/v2/agent/query")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"What are the main compliance requirements?\"\n}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.pyramid-ai.com/api/v2/agent/query', [
  'body' => '{
  "query": "What are the main compliance requirements?"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.pyramid-ai.com/api/v2/agent/query");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"query\": \"What are the main compliance requirements?\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = ["query": "What are the main compliance requirements?"] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.pyramid-ai.com/api/v2/agent/query")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```