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

# Get knowledge sources

GET https://example.ada.support/api/v2/knowledge/sources/

Get knowledge sources

Reference: https://docs.ada.cx/reference/knowledge/sources/list

## Authentication

- `Authorization` header (bearer token, required) — Bearer authentication of the form `Bearer <token>`, where token is your auth token.

## Response

### 200

Knowledge sources

- `data` (list of KnowledgeSourceResponse, optional)

## Errors

### 400 Bad Request Error

Bad Request

- `errors` (list of ErrorsErrorsItems, required) — A list of errors

### 401 Unauthorized Error

Unauthorized

- `errors` (list of ErrorsErrorsItems, required) — A list of errors

### 429 Too Many Requests Error

Too Many Requests

- `errors` (list of ErrorsErrorsItems, required) — A list of errors

### 500 Internal Server Error

Internal Server Error

- `errors` (list of ErrorsErrorsItems, required) — A list of errors

## Types

### KnowledgeSourceResponse

- `id` (string, required) — A unique identifier for the knowledge source
- `name` (string, required) — The name of the knowledge source
- `availability_rules` (AvailabilityRule, required, nullable) — The source's availability-rule template. Each new article created under the source whose request omits `availability_rules` gets it. `null` when the source has none.
- `external_id` (string, optional, nullable) — An external identifier for the knowledge source
- `metadata` (KnowledgeSourceResponseMetadata, optional, nullable) — A dictionary of arbitrary key,value pairs. This data is not used by Ada, but can be used by the client to store additional information about the knowledge source.
- `created` (string, optional) — The date the knowledge source was created
- `updated` (string, optional) — The date the knowledge source was last updated
- `last_sync` (string, optional) — The date the knowledge source was last synchronized
- `status` (enum, optional) — Deletion lifecycle status of the knowledge source: `deleting` while an asynchronous deletion is in progress, `delete_failed` if the deletion failed. `null` when no deletion is in progress.
  - Allowed values: `deleting`, `delete_failed`

### ErrorsErrorsItems

- `type` (string, required) — The error type
- `message` (string, required) — The error message
- `details` (string, optional, nullable) — Extra information about the error

### AvailabilityRule

A two-level tree of conditions that determines availability based on variable values during a conversation. The root group has a `match` combinator and a list of conditions or condition groups. A rule may contain at most 1000 conditions in total, counting every condition across the root and all nested condition groups.

- `match` (enum, required) — Whether all conditions must pass (`all`) or any one condition must pass (`any`).
  - Allowed values: `all`, `any`
- `conditions` (list of AvailabilityRuleConditionsItems, required) — List of conditions or condition groups. Must contain at least one entry. Each entry is either a `Condition` object (with `variable`, `operator`, and optional `value`) or a `ConditionGroup` object (with its own `match` and nested `conditions` list).

### KnowledgeSourceResponseMetadata

A dictionary of arbitrary key,value pairs. This data is not used by Ada, but can be used by the client to store additional information about the knowledge source.

### AvailabilityRuleConditionsItems

### AvailabilityRuleCondition

A single condition comparing a variable to a value.

- `variable` (AvailabilityRuleConditionVariable, required) — The variable to test, referenced by `id`. Look up the ids for your Agent through the variables endpoint. Not every variable can be used in a rule; referencing one that can't returns a `400`.
- `operator` (enum, required) — The comparison operator. Unary operators (`is_set`, `is_not_set`) must not include a `value` field.
  - Allowed values: `equals`, `does_not_equal`, `greater_than`, `less_than`, `starts_with`, `ends_with`, `contains`, `does_not_contain`, `is_set`, `is_not_set`
- `value` (AvailabilityRuleConditionValue, optional) — The value to compare against. Omit for unary operators (`is_set`, `is_not_set`).
- `case_sensitive` (boolean, optional) — Whether the comparison is case-sensitive. Defaults to `false`. Only meaningful for the equality (`equals`, `does_not_equal`) and string (`starts_with`, `ends_with`, `contains`, `does_not_contain`) operators. Omitted from responses when `false`.

### AvailabilityRuleConditionGroup

A nested group of conditions inside a rule's top-level `conditions` list. Condition groups may contain only `Condition` objects — further nesting is not supported.

- `match` (enum, required) — Whether all conditions must pass (`all`) or any one condition must pass (`any`).
  - Allowed values: `all`, `any`
- `conditions` (list of AvailabilityRuleCondition, required) — List of conditions inside this condition group. Must contain at least one entry.

### AvailabilityRuleConditionVariable

The variable to test, referenced by `id`. Look up the ids for your Agent through the variables endpoint. Not every variable can be used in a rule; referencing one that can't returns a `400`.

- `id` (string, required) — The id of the variable.

### AvailabilityRuleConditionValue

The value to compare against. Omit for unary operators (`is_set`, `is_not_set`).

## Examples

**Response**

```json
{
  "data": [
    {
      "id": "107a82",
      "name": "My Name",
      "external_id": "21k-dmwdnio292nj3kbf80s",
      "created": "2021-01-01T00:00:00Z",
      "updated": "2021-01-01T00:00:00Z"
    }
  ]
}
```

**SDK Code**

```python
import requests

url = "https://example.ada.support/api/v2/knowledge/sources/"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.json())
```

```javascript
const url = 'https://example.ada.support/api/v2/knowledge/sources/';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

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"
	"net/http"
	"io"
)

func main() {

	url := "https://example.ada.support/api/v2/knowledge/sources/"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	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://example.ada.support/api/v2/knowledge/sources/")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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.get("https://example.ada.support/api/v2/knowledge/sources/")
  .header("Authorization", "Bearer <token>")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://example.ada.support/api/v2/knowledge/sources/', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

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

```csharp
using RestSharp;

var client = new RestClient("https://example.ada.support/api/v2/knowledge/sources/");
var request = new RestRequest(Method.GET);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Authorization": "Bearer <token>"]

let request = NSMutableURLRequest(url: NSURL(string: "https://example.ada.support/api/v2/knowledge/sources/")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"
request.allHTTPHeaderFields = headers

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()
```