Trigger topic extraction for the sources in scope
curl --request POST \
--url https://api.mentionlab.io/api/v1/source-topics/extract \
--header 'Content-Type: application/json' \
--header 'x-project-id: <x-project-id>' \
--data '
{
"startDate": "2025-01-01",
"endDate": "2025-01-31",
"countries": [
"BE",
"FR"
],
"languages": [
"en",
"fr"
],
"models": [
"gpt-4o",
"claude-3-5-sonnet"
],
"queryIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTagIds": [
"42"
],
"execTagIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTagGroupIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"execTagGroupIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTypes": [],
"timezone": "UTC",
"groupByEntityGroup": false,
"showAllEntities": false
}
'import requests
url = "https://api.mentionlab.io/api/v1/source-topics/extract"
payload = {
"startDate": "2025-01-01",
"endDate": "2025-01-31",
"countries": ["BE", "FR"],
"languages": ["en", "fr"],
"models": ["gpt-4o", "claude-3-5-sonnet"],
"queryIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTagIds": ["42"],
"execTagIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTagGroupIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"execTagGroupIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTypes": [],
"timezone": "UTC",
"groupByEntityGroup": False,
"showAllEntities": False
}
headers = {
"x-project-id": "<x-project-id>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-project-id': '<x-project-id>', 'Content-Type': 'application/json'},
body: JSON.stringify({
startDate: '2025-01-01',
endDate: '2025-01-31',
countries: ['BE', 'FR'],
languages: ['en', 'fr'],
models: ['gpt-4o', 'claude-3-5-sonnet'],
queryIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTagIds: ['42'],
execTagIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTagGroupIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
execTagGroupIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTypes: [],
timezone: 'UTC',
groupByEntityGroup: false,
showAllEntities: false
})
};
fetch('https://api.mentionlab.io/api/v1/source-topics/extract', 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://api.mentionlab.io/api/v1/source-topics/extract",
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([
'startDate' => '2025-01-01',
'endDate' => '2025-01-31',
'countries' => [
'BE',
'FR'
],
'languages' => [
'en',
'fr'
],
'models' => [
'gpt-4o',
'claude-3-5-sonnet'
],
'queryIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTagIds' => [
'42'
],
'execTagIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTagGroupIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'execTagGroupIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTypes' => [
],
'timezone' => 'UTC',
'groupByEntityGroup' => false,
'showAllEntities' => false
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-project-id: <x-project-id>"
],
]);
$response = curl_exec($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://api.mentionlab.io/api/v1/source-topics/extract"
payload := strings.NewReader("{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-project-id", "<x-project-id>")
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://api.mentionlab.io/api/v1/source-topics/extract")
.header("x-project-id", "<x-project-id>")
.header("Content-Type", "application/json")
.body("{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mentionlab.io/api/v1/source-topics/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-project-id"] = '<x-project-id>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}"
response = http.request(request)
puts response.read_body{
"runId": "019dd32e-b19e-7956-88f6-4b9a877f3697",
"enqueued": 248
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}Source Topics
Trigger topic extraction for the sources in scope
Selects the top 1000 source pages (deduped per url + month, ranked by citation count) matching the standard analytics filters (date range, countries, languages, models, queries, tags) and enqueues their cached page metadata (title + description) for vectorization into the source-topics vector store. Use /source-topics/preview to inspect the selected set first. Returns the id of the created run and the number of enqueued jobs. Every trigger creates a NEW run; extracts are serialized per project — a 409 is returned while another extraction run is in flight. Sources whose metadata was not cached at scrape time are skipped by the worker.
POST
/
api
/
v1
/
source-topics
/
extract
Trigger topic extraction for the sources in scope
curl --request POST \
--url https://api.mentionlab.io/api/v1/source-topics/extract \
--header 'Content-Type: application/json' \
--header 'x-project-id: <x-project-id>' \
--data '
{
"startDate": "2025-01-01",
"endDate": "2025-01-31",
"countries": [
"BE",
"FR"
],
"languages": [
"en",
"fr"
],
"models": [
"gpt-4o",
"claude-3-5-sonnet"
],
"queryIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTagIds": [
"42"
],
"execTagIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTagGroupIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"execTagGroupIds": [
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
],
"queryTypes": [],
"timezone": "UTC",
"groupByEntityGroup": false,
"showAllEntities": false
}
'import requests
url = "https://api.mentionlab.io/api/v1/source-topics/extract"
payload = {
"startDate": "2025-01-01",
"endDate": "2025-01-31",
"countries": ["BE", "FR"],
"languages": ["en", "fr"],
"models": ["gpt-4o", "claude-3-5-sonnet"],
"queryIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTagIds": ["42"],
"execTagIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTagGroupIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"execTagGroupIds": ["3fa85f64-5717-4562-b3fc-2c963f66afa6"],
"queryTypes": [],
"timezone": "UTC",
"groupByEntityGroup": False,
"showAllEntities": False
}
headers = {
"x-project-id": "<x-project-id>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-project-id': '<x-project-id>', 'Content-Type': 'application/json'},
body: JSON.stringify({
startDate: '2025-01-01',
endDate: '2025-01-31',
countries: ['BE', 'FR'],
languages: ['en', 'fr'],
models: ['gpt-4o', 'claude-3-5-sonnet'],
queryIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTagIds: ['42'],
execTagIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTagGroupIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
execTagGroupIds: ['3fa85f64-5717-4562-b3fc-2c963f66afa6'],
queryTypes: [],
timezone: 'UTC',
groupByEntityGroup: false,
showAllEntities: false
})
};
fetch('https://api.mentionlab.io/api/v1/source-topics/extract', 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://api.mentionlab.io/api/v1/source-topics/extract",
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([
'startDate' => '2025-01-01',
'endDate' => '2025-01-31',
'countries' => [
'BE',
'FR'
],
'languages' => [
'en',
'fr'
],
'models' => [
'gpt-4o',
'claude-3-5-sonnet'
],
'queryIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTagIds' => [
'42'
],
'execTagIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTagGroupIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'execTagGroupIds' => [
'3fa85f64-5717-4562-b3fc-2c963f66afa6'
],
'queryTypes' => [
],
'timezone' => 'UTC',
'groupByEntityGroup' => false,
'showAllEntities' => false
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-project-id: <x-project-id>"
],
]);
$response = curl_exec($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://api.mentionlab.io/api/v1/source-topics/extract"
payload := strings.NewReader("{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-project-id", "<x-project-id>")
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://api.mentionlab.io/api/v1/source-topics/extract")
.header("x-project-id", "<x-project-id>")
.header("Content-Type", "application/json")
.body("{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.mentionlab.io/api/v1/source-topics/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-project-id"] = '<x-project-id>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"startDate\": \"2025-01-01\",\n \"endDate\": \"2025-01-31\",\n \"countries\": [\n \"BE\",\n \"FR\"\n ],\n \"languages\": [\n \"en\",\n \"fr\"\n ],\n \"models\": [\n \"gpt-4o\",\n \"claude-3-5-sonnet\"\n ],\n \"queryIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagIds\": [\n \"42\"\n ],\n \"execTagIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"execTagGroupIds\": [\n \"3fa85f64-5717-4562-b3fc-2c963f66afa6\"\n ],\n \"queryTypes\": [],\n \"timezone\": \"UTC\",\n \"groupByEntityGroup\": false,\n \"showAllEntities\": false\n}"
response = http.request(request)
puts response.read_body{
"runId": "019dd32e-b19e-7956-88f6-4b9a877f3697",
"enqueued": 248
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}{
"statusCode": 400,
"message": "Validation failed",
"error": "Bad Request"
}Headers
Project ID to specify the project context
Body
application/json
Start date (inclusive)
Example:
"2025-01-01"
End date (inclusive)
Example:
"2025-01-31"
Filter by country codes
Example:
["BE", "FR"]
Filter by language codes
Example:
["en", "fr"]
Filter by AI models
Example:
["gpt-4o", "claude-3-5-sonnet"]
Filter by query IDs
Example:
["3fa85f64-5717-4562-b3fc-2c963f66afa6"]
Filter by source presence: "sources" (only with sources), "no_sources" (only without), "all" (no filter). Legacy true/false values are still accepted.
Available options:
all, sources, no_sources Filter by shopping presence: "shopping" (only with shopping), "no_shopping" (only without), "all" (no filter). Legacy true/false values are still accepted.
Available options:
all, shopping, no_shopping Filter by sponsored-ad presence: "ads" (only with ads), "no_ads" (only without), "all" (no filter). Legacy true/false values are still accepted.
Available options:
all, ads, no_ads Filter by query tag IDs (numeric — bigint column)
Example:
["42"]
Filter by execution tag IDs
Example:
["3fa85f64-5717-4562-b3fc-2c963f66afa6"]
Filter by query tag group IDs — matches rows carrying any tag filed under a selected group. Combines with queryTagIds per queryTagMode.
Example:
["3fa85f64-5717-4562-b3fc-2c963f66afa6"]
Filter by execution tag group IDs — matches rows carrying any tag filed under a selected group. Combines with execTagIds per execTagMode.
Example:
["3fa85f64-5717-4562-b3fc-2c963f66afa6"]
Filter by query type. Include "untyped" to also match queries without a type. Results from since-deleted queries are excluded when this filter is set.
Available options:
comparative, informative, perception, untyped Query tag matching mode: "or" matches ANY tag (default), "and" matches ALL tags.
Available options:
and, or Execution tag matching mode: "or" matches ANY tag (default), "and" matches ALL tags.
Available options:
and, or Deprecated and ignored. Date bounds and buckets are always UTC. Accepted for backward compatibility only.
Example:
"UTC"
Row grouping level for entity results. "none" = one row per entity, "division" = one row per division (entities not in a division get their own row), "group" = one row per top-level group (divisions roll up into their group). Defaults to "none".
Available options:
none, division, group Deprecated — use groupBy instead. true is equivalent to groupBy="group".
Example:
false
Include entities that have only ever been seen in a single AI response. These are mostly one-off extraction noise and are hidden by default.
Example:
false
Response
Run UUID. Poll its status via GET /api/v1/source-topics/runs/{runId} (or the list endpoint) to track progress.
Example:
"019dd32e-b19e-7956-88f6-4b9a877f3697"
Number of source topic-extraction jobs enqueued (one per distinct (url, month) matching the filters). Jobs are deduped at the queue level, so re-triggering with the same scope is idempotent. Sources whose page metadata was not cached are skipped by the worker and are not represented in this count beyond their enqueue.
Example:
248