Recrawl Document

curl --request POST \
  --url https://tavusapi.com/v2/documents/{document_id}/recrawl \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "crawl": {
    "depth": 3,
    "max_pages": 50
  }
}
'

import requests

url = "https://tavusapi.com/v2/documents/{document_id}/recrawl"

payload = { "crawl": {
        "depth": 3,
        "max_pages": 50
    } }
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({crawl: {depth: 3, max_pages: 50}})
};

fetch('https://tavusapi.com/v2/documents/{document_id}/recrawl', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://tavusapi.com/v2/documents/{document_id}/recrawl",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'crawl' => [
        'depth' => 3,
        'max_pages' => 50
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://tavusapi.com/v2/documents/{document_id}/recrawl"

	payload := strings.NewReader("{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://tavusapi.com/v2/documents/{document_id}/recrawl")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://tavusapi.com/v2/documents/{document_id}/recrawl")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}"

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

{
  "document_id": "d8-5c71baca86fc",
  "document_name": "Company Website",
  "document_url": "https://example.com/",
  "status": "recrawling",
  "progress": null,
  "error_message": "<string>",
  "created_at": "2024-01-01T12:00:00Z",
  "updated_at": "2024-01-15T10:30:00Z",
  "callback_url": "https://your-server.com/webhook",
  "tags": [
    "website",
    "company"
  ],
  "crawl_config": {
    "depth": 2,
    "max_pages": 10
  },
  "crawled_urls": [
    "https://docs.example.com/",
    "https://docs.example.com/getting-started"
  ],
  "last_crawled_at": "2024-01-01T12:05:00Z",
  "crawl_count": 1
}

{
  "error": "Document was not created with crawl configuration"
}

{
  "message": "Invalid access token"
}

{
  "message": "Document not found"
}

{
  "error": "Document must be in 'ready' or 'error' state to recrawl, current status: processing"
}

{
  "error": "Recrawl cooldown: please wait 45 minutes before recrawling this document."
}

POST

documents

{document_id}

recrawl

Recrawl Document

curl --request POST \
  --url https://tavusapi.com/v2/documents/{document_id}/recrawl \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "crawl": {
    "depth": 3,
    "max_pages": 50
  }
}
'

import requests

url = "https://tavusapi.com/v2/documents/{document_id}/recrawl"

payload = { "crawl": {
        "depth": 3,
        "max_pages": 50
    } }
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({crawl: {depth: 3, max_pages: 50}})
};

fetch('https://tavusapi.com/v2/documents/{document_id}/recrawl', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://tavusapi.com/v2/documents/{document_id}/recrawl",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'crawl' => [
        'depth' => 3,
        'max_pages' => 50
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://tavusapi.com/v2/documents/{document_id}/recrawl"

	payload := strings.NewReader("{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}")

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

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://tavusapi.com/v2/documents/{document_id}/recrawl")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://tavusapi.com/v2/documents/{document_id}/recrawl")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"crawl\": {\n    \"depth\": 3,\n    \"max_pages\": 50\n  }\n}"

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

{
  "document_id": "d8-5c71baca86fc",
  "document_name": "Company Website",
  "document_url": "https://example.com/",
  "status": "recrawling",
  "progress": null,
  "error_message": "<string>",
  "created_at": "2024-01-01T12:00:00Z",
  "updated_at": "2024-01-15T10:30:00Z",
  "callback_url": "https://your-server.com/webhook",
  "tags": [
    "website",
    "company"
  ],
  "crawl_config": {
    "depth": 2,
    "max_pages": 10
  },
  "crawled_urls": [
    "https://docs.example.com/",
    "https://docs.example.com/getting-started"
  ],
  "last_crawled_at": "2024-01-01T12:05:00Z",
  "crawl_count": 1
}

{
  "error": "Document was not created with crawl configuration"
}

{
  "message": "Invalid access token"
}

{
  "message": "Document not found"
}

{
  "error": "Document must be in 'ready' or 'error' state to recrawl, current status: processing"
}

{
  "error": "Recrawl cooldown: please wait 45 minutes before recrawling this document."
}

For AI agents, use https://docs.tavus.io/openapi.yaml for the full HTTP API contract.

Authorizations

x-api-key

string

header

required

Path Parameters

document_id

string

required

Unique id of the crawl-backed website document to refresh. Use when the source site changed, you want to refresh content on a schedule, or retry after crawl or processing errors.

The document must be in ready or error (otherwise 409). It must have been created with a crawl configuration unless you supply crawl in the request body for this call.

The same document cannot be recrawled more than once within each 1-hour cooldown (429 if invoked too soon).

Body

application/json

Optional body. Omit entirely to reuse the crawl depth / max_pages stored from document creation, or include crawl to override those values for this run only.

After 202, status is typically recrawling until processing finishes. If you set callback_url when creating the document, webhooks report progress until the document returns to ready or error.

Poll Get Document for current status, crawl_count, and last_crawled_at.

Account limits: at most 5 concurrent crawls per user and at most 100 crawl-backed documents per user.

crawl

object

Optional depth and max_pages for this recrawl only; overrides stored crawl settings from document creation when provided. If omitted, the original crawl configuration is used.

What runs: the same starting URL as the original crawl, links followed within these limits, fresh page content processed, existing vectors replaced when processing completes, and crawl_count / last_crawled_at updated (see the 202 payload and Get Document while status is recrawling).

Show child attributes

Response

Recrawl initiated successfully

document_id

string

Unique identifier for the document

Example:

"d8-5c71baca86fc"

document_name

string

Name of the document

Example:

"Company Website"

document_url

string

URL of the document

Example:

"https://example.com/"

status

enum<string>

After a successful recrawl request, typically recrawling until processing completes, then ready or error. Other values: started, processing.

Available options:

started,

processing,

ready,

error,

recrawling

Example:

"recrawling"

progress

integer | null

Processing progress as a percentage (0-100). Null when processing has not started or is complete.

Example:

null

error_message

string | null

Error code indicating why processing failed. Only present when status is error. Possible values include: file_download_failed, file_format_unsupported, file_size_too_large, file_empty, invalid_file_url, document_processing_failed, website_processing_failed, chunking_failed, embedding_failed, vector_store_failed, contact_support.

created_at

string

ISO 8601 timestamp of when the document was created

Example:

"2024-01-01T12:00:00Z"

updated_at

string

ISO 8601 timestamp of when the document was last updated

Example:

"2024-01-15T10:30:00Z"

callback_url

string

If set on Create Document, Tavus POSTs status updates here while this recrawl runs through completion.

Example:

"https://your-server.com/webhook"

Introduction

Conversation

PAL

Face

Voices

Tools

Skills

Magic Canvas

Objectives

Guardrails

Knowledge Base

Pronunciation Dictionaries

Deployments

Recrawl Document

Authorizations

Path Parameters

Body

Response