/api/v1/askAsk with conversation context
Answers a natural-language question about one project's data. Requires `question` (1-8,000 chars after trim) and `projectId` (uuid); optional `conversationId` (up to 128 chars, for multi-turn) and `pageContext.pathname` (up to 512 chars, appended to the question as a surface hint). Builds workspace context from the project's last 50 eval_runs, 20 security_scans and a 200-row per-model cost rollup, resolves the project's org as the conversation namespace, then answers via the core AskEngine — a deterministic intent classifier + entity extractor over that context, with NO LLM call — returning `{ id, query (carrying the classified `intent`), answer, dataPoints, chart?, suggestedActions, confidence, latencyMs, followUps }`. Rejects after a 15 s timeout. Requires `evals:create` permission and org membership of the project; 30 req/min.
Authentication
Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.
Request body required
Example
{
"question": "string",
"projectId": "00000000-0000-0000-0000-000000000000",
"conversationId": "string",
"pageContext": {
"pathname": "string"
}
}Schema
{
"application/json": {
"schema": {
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"projectId": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"conversationId": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"pageContext": {
"type": "object",
"properties": {
"pathname": {
"type": "string",
"maxLength": 512
}
},
"additionalProperties": false
}
},
"required": [
"question",
"projectId"
],
"additionalProperties": false
}
}
}Response
200 example
{
"success": true
}All status codes
Code samples
cURL
curl -X POST \
https://evalguard.ai/api/v1/ask \
-H "Authorization: Bearer $EVALGUARD_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "question": "string", "projectId": "00000000-0000-0000-0000-000000000000", "conversationId": "string", "pageContext": { "pathname": "string" } }'TypeScript
// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:
const res = await fetch("https://evalguard.ai/api/v1/ask", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"question": "string",
"projectId": "00000000-0000-0000-0000-000000000000",
"conversationId": "string",
"pageContext": {
"pathname": "string"
}
}),
});
console.log(res.status, await res.json());Python
# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:
import os
import requests
headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"
response = requests.request(
"POST",
"https://evalguard.ai/api/v1/ask",
headers=headers,
json={
"question": "string",
"projectId": "00000000-0000-0000-0000-000000000000",
"conversationId": "string",
"pageContext": {
"pathname": "string"
}
},
)
print(response.status_code, response.json())Go
package main
import (
"context"
"fmt"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader(`{"question":"string","projectId":"00000000-0000-0000-0000-000000000000","conversationId":"string","pageContext":{"pathname":"string"}}`)
req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/ask", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil { panic(err) }
defer resp.Body.Close()
fmt.Println(resp.Status)
}