Skip to content
POST/api/v1/embeddings

Compute embeddings

Two actions, selected by the required `action` discriminator. `action:"store"` persists a caller-supplied embedding: `{projectId, id, vector (1..16000 floats), label?, metadata?}` → 201 with the stored row. `action:"similar"` runs a top-K similarity search within the project: `{projectId, queryVector? | queryId?, topK? (1..1000, default 10)}` → `[{id, label, score}]`, served by the pgvector `stored_embeddings_ann_search` cosine-ANN RPC and falling back to an in-memory JS cosine over at most 1000 rows only when pgvector/the RPC is absent (a permission or tenancy error surfaces as 403/500 instead). This endpoint does NOT compute embeddings and calls no embedding provider — supply the vector yourself.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Schema
{
  "application/json": {
    "schema": {
      "oneOf": [
        {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "store"
              ]
            },
            "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)$"
            },
            "id": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            },
            "vector": {
              "minItems": 1,
              "maxItems": 16000,
              "type": "array",
              "items": {
                "type": "number"
              }
            },
            "label": {
              "type": "string",
              "maxLength": 20000
            },
            "metadata": {
              "type": "object",
              "additionalProperties": {}
            }
          },
          "required": [
            "action",
            "projectId",
            "id",
            "vector"
          ],
          "additionalProperties": false
        },
        {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "similar"
              ]
            },
            "projectId": {
              "type": "string",
              "format": "uuid",
              "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
            },
            "queryVector": {
              "minItems": 1,
              "maxItems": 16000,
              "type": "array",
              "items": {
                "type": "number"
              }
            },
            "queryId": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            },
            "topK": {
              "type": "integer",
              "minimum": 1,
              "maximum": 1000
            }
          },
          "required": [
            "action",
            "projectId"
          ],
          "additionalProperties": false
        }
      ]
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Embeddings.
201Created.
400(no description)
401(no description)
403Forbidden — NOT_ORG_MEMBER.
404Not Found — NOT_FOUND.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/embeddings \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

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/embeddings", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
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']}"}

response = requests.request("POST", "https://evalguard.ai/api/v1/embeddings", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/embeddings", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404409429500

Other Evals endpoints