Router.Embeddings
Create an Embedding
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.from orq_ai_sdk import Orq
import os
with Orq(
api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:
res = orq.router.embeddings.create(input=[
"The food was delicious",
"And the waiter was friendly",
], model="openai/text-embedding-3-small", orq={
"identity": {
"id": "contact_01ARZ3NDEKTSV4RRFFQ69G5FAV",
"display_name": "Jane Doe",
"email": "jane.doe@example.com",
"metadata": [
{
"department": "Engineering",
"role": "Senior Developer",
},
],
"logo_url": "https://example.com/avatars/jane-doe.jpg",
"tags": [
"hr",
"engineering",
],
},
})
# Handle response
print(res)
import { Orq } from "@orq-ai/node";
const orq = new Orq({
apiKey: process.env["ORQ_API_KEY"] ?? "",
});
async function run() {
const result = await orq.router.embeddings.create({
input: [
"The food was delicious",
"And the waiter was friendly",
],
model: "openai/text-embedding-3-small",
});
console.log(result);
}
run();
Show Parameters
Show Parameters
{
"input": Union[str, List[Input2]], # required
"model": str, # required
"cache": { # optional
"ttl": Optional[int],
"type": Literal["exact_match"], # required
},
"dimensions": Optional[int],
"encoding_format": Optional[Literal["float", "base64"]],
"fallbacks": { # optional
"model": str, # required
},
"load_balancer": { # optional
"models": { # required
"model": str, # required
"weight": float, # required
},
"type": Literal["weight_based"], # required
},
"name": Optional[str],
"orq": { # optional
"cache": Optional[EmbeddingCacheConfig],
"contact": { # optional
"display_name": Optional[str],
"email": Optional[str],
"id": str, # required
"metadata": List[Dict[str, Any]],
"tags": List[str],
},
"fallbacks": List[FallbackConfig],
"identity": { # optional
"id": str, # required
"display_name": Optional[str],
"email": Optional[str],
"metadata": List[Dict[str, Any]],
"logo_url": Optional[str],
"tags": List[str],
},
"load_balancer": Optional[EmbeddingLoadBalancerConfig],
"name": Optional[str],
"retry": { # optional
"count": int, # required
"on_codes": List[int], # required
},
"timeout": { # optional
"call_timeout": int, # required
},
},
"retry": { # optional
"count": int, # required
"on_codes": List[int], # required
},
"timeout": { # optional
"call_timeout": int, # required
},
"user": Optional[str],
}
{
cache?: {
ttl?: number;
type: string; // required
};
dimensions?: number;
encodingFormat?: string;
fallbacks?: {
model: string; // required
};
input: string; // required
loadBalancer?: {
models: { // required
model: string; // required
weight: number; // required
};
type: string; // required
};
model: string; // required
name?: string;
orq?: {
cache?: {
ttl?: number;
type: string; // required
};
contact?: {
displayName?: string;
email?: string;
id: string; // required
metadata?: Record<string, any>[];
tags?: string[];
};
fallbacks?: {
model: string; // required
};
identity?: {
id: string; // required
displayName?: string;
email?: string;
metadata?: Record<string, any>[];
logoUrl?: string;
tags?: string[];
};
loadBalancer?: {
models: { // required
model: string; // required
weight: number; // required
};
type: string; // required
};
name?: string;
retry?: {
count: number; // required
onCodes: number[]; // required
};
timeout?: {
callTimeout: number; // required
};
};
retry?: {
count: number; // required
onCodes: number[]; // required
};
timeout?: {
callTimeout: number; // required
};
user?: string;
}
Show Response
Show Response
{
"data": {
"embedding": Any,
"index": int,
"object": Literal["embedding"],
},
"model": str,
"object": Literal["list"],
"usage": {
"prompt_tokens": int,
"total_tokens": int,
},
}
{
data: {
embedding: any;
index: number;
object: string;
};
model: string;
object: string;
usage: {
promptTokens: number;
totalTokens: number;
};
}