Ask Memory
curl --request POST \
--url https://api.velt.dev/v2/memory/ask \
--header 'Content-Type: application/json' \
--header 'x-velt-api-key: <x-velt-api-key>' \
--header 'x-velt-auth-token: <x-velt-auth-token>' \
--data '
{
"data": {
"question": "<string>",
"organizationId": "<string>",
"documentId": "<string>",
"filters": {},
"recencyDays": 123
}
}
'import requests
url = "https://api.velt.dev/v2/memory/ask"
payload = { "data": {
"question": "<string>",
"organizationId": "<string>",
"documentId": "<string>",
"filters": {},
"recencyDays": 123
} }
headers = {
"x-velt-api-key": "<x-velt-api-key>",
"x-velt-auth-token": "<x-velt-auth-token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'x-velt-api-key': '<x-velt-api-key>',
'x-velt-auth-token': '<x-velt-auth-token>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
data: {
question: '<string>',
organizationId: '<string>',
documentId: '<string>',
filters: {},
recencyDays: 123
}
})
};
fetch('https://api.velt.dev/v2/memory/ask', 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.velt.dev/v2/memory/ask",
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([
'data' => [
'question' => '<string>',
'organizationId' => '<string>',
'documentId' => '<string>',
'filters' => [
],
'recencyDays' => 123
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-velt-api-key: <x-velt-api-key>",
"x-velt-auth-token: <x-velt-auth-token>"
],
]);
$response = curl_exec($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.velt.dev/v2/memory/ask"
payload := strings.NewReader("{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-velt-api-key", "<x-velt-api-key>")
req.Header.Add("x-velt-auth-token", "<x-velt-auth-token>")
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.velt.dev/v2/memory/ask")
.header("x-velt-api-key", "<x-velt-api-key>")
.header("x-velt-auth-token", "<x-velt-auth-token>")
.header("Content-Type", "application/json")
.body("{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.velt.dev/v2/memory/ask")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-velt-api-key"] = '<x-velt-api-key>'
request["x-velt-auth-token"] = '<x-velt-auth-token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}"
response = http.request(request)
puts response.read_body{
"result": {
"answer": "Reviewers consistently reject copy that makes medical claims without a citation...",
"citations": [
{ "recordId": "act_8f3...", "snippet": "Claim 'clinically proven' lacks a citation." }
],
"confidence": 0.74,
"recordsSearched": 18
}
}
Ask Memory
POST
/
v2
/
memory
/
ask
Ask Memory
curl --request POST \
--url https://api.velt.dev/v2/memory/ask \
--header 'Content-Type: application/json' \
--header 'x-velt-api-key: <x-velt-api-key>' \
--header 'x-velt-auth-token: <x-velt-auth-token>' \
--data '
{
"data": {
"question": "<string>",
"organizationId": "<string>",
"documentId": "<string>",
"filters": {},
"recencyDays": 123
}
}
'import requests
url = "https://api.velt.dev/v2/memory/ask"
payload = { "data": {
"question": "<string>",
"organizationId": "<string>",
"documentId": "<string>",
"filters": {},
"recencyDays": 123
} }
headers = {
"x-velt-api-key": "<x-velt-api-key>",
"x-velt-auth-token": "<x-velt-auth-token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'x-velt-api-key': '<x-velt-api-key>',
'x-velt-auth-token': '<x-velt-auth-token>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
data: {
question: '<string>',
organizationId: '<string>',
documentId: '<string>',
filters: {},
recencyDays: 123
}
})
};
fetch('https://api.velt.dev/v2/memory/ask', 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.velt.dev/v2/memory/ask",
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([
'data' => [
'question' => '<string>',
'organizationId' => '<string>',
'documentId' => '<string>',
'filters' => [
],
'recencyDays' => 123
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-velt-api-key: <x-velt-api-key>",
"x-velt-auth-token: <x-velt-auth-token>"
],
]);
$response = curl_exec($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.velt.dev/v2/memory/ask"
payload := strings.NewReader("{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-velt-api-key", "<x-velt-api-key>")
req.Header.Add("x-velt-auth-token", "<x-velt-auth-token>")
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.velt.dev/v2/memory/ask")
.header("x-velt-api-key", "<x-velt-api-key>")
.header("x-velt-auth-token", "<x-velt-auth-token>")
.header("Content-Type", "application/json")
.body("{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.velt.dev/v2/memory/ask")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-velt-api-key"] = '<x-velt-api-key>'
request["x-velt-auth-token"] = '<x-velt-auth-token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"data\": {\n \"question\": \"<string>\",\n \"organizationId\": \"<string>\",\n \"documentId\": \"<string>\",\n \"filters\": {},\n \"recencyDays\": 123\n }\n}"
response = http.request(request)
puts response.read_body{
"result": {
"answer": "Reviewers consistently reject copy that makes medical claims without a citation...",
"citations": [
{ "recordId": "act_8f3...", "snippet": "Claim 'clinically proven' lacks a citation." }
],
"confidence": 0.74,
"recordsSearched": 18
}
}
Use this API to ask a natural-language question over your Memory. The answer is grounded in your judgments and ingested knowledge, and comes with citations and a confidence score. When retrieval finds no relevant context,
answer is an empty string with confidence: 0 rather than an invented answer; treat that as “Memory has nothing to say about this yet.”
Endpoint
POST https://api.velt.dev/v2/memory/ask
Headers
Your API key.
Your Auth Token.
Body
Params
Show properties
Show properties
Non-empty natural-language question.
Narrow to one organization.
Narrow to one document. Requires
organizationId.Same shape as the Search Judgments filters.
annotationId requires organizationId.1 to 365. Recency-true retrieval instead of vector search.
Example Requests
Ask a policy question
{
"data": {
"question": "How do we handle marketing copy that makes medical claims?"
}
}
Response
answer is the grounded answer (an empty string when there is no grounding context). citations point at the judgment records the answer drew on. confidence is 0 when the answer is empty.
Success Response
{
"result": {
"answer": "Reviewers consistently reject copy that makes medical claims without a citation...",
"citations": [
{ "recordId": "act_8f3...", "snippet": "Claim 'clinically proven' lacks a citation." }
],
"confidence": 0.74,
"recordsSearched": 18
}
}
Failure Response
{
"error": {
"message": "ERROR_MESSAGE",
"status": "INVALID_ARGUMENT"
}
}
{
"result": {
"answer": "Reviewers consistently reject copy that makes medical claims without a citation...",
"citations": [
{ "recordId": "act_8f3...", "snippet": "Claim 'clinically proven' lacks a citation." }
],
"confidence": 0.74,
"recordsSearched": 18
}
}
Was this page helpful?
⌘I

