Skip to main content

Embeddings API Reference

Complete reference for the BrilliantAI Embeddings API.

Create Embeddings​

Endpoint​

POST https://api.brilliantai.co/embeddings

Request Parameters​

ParameterTypeRequiredDescription
modelstringYesID of the embedding model
inputstring or arrayYesText to embed
encoding_formatstringNoOutput format (float or base64)

Example Request​

from openai import OpenAI

client = OpenAI(
    base_url="https://api.brilliantai.co",
    api_key="your-api-key"
)

response = client.embeddings.create(
    model="text-embedding-3-large",
    input="Your text string goes here"
)

vector = response.data[0].embedding

Response Format​

{
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "embedding": [0.0023064255, ...],
            "index": 0
        }
    ],
    "model": "text-embedding-3-large",
    "usage": {
        "prompt_tokens": 8,
        "total_tokens": 8
    }
}

Batch Processing​

Example​

# Batch text inputs
texts = [
    "First document",
    "Second document",
    "Third document"
]

response = client.embeddings.create(
    model="text-embedding-3-large",
    input=texts
)

# Get embeddings for each input
embeddings = [data.embedding for data in response.data]

Error Handling​

try:
    response = client.embeddings.create(...)
except openai.APIError as e:
    print(f"API Error: {e}")
except openai.RateLimitError as e:
    print(f"Rate Limit Error: {e}")
except openai.APIConnectionError as e:
    print(f"Connection Error: {e}")

Vector Database Integration​

Pinecone Example​

import pinecone

# Initialize Pinecone
pinecone.init(api_key="your-pinecone-key")
index = pinecone.Index("your-index")

# Get embedding
response = client.embeddings.create(
    model="text-embedding-3-large",
    input="Document text"
)
vector = response.data[0].embedding

# Store in Pinecone
index.upsert([
    ("doc1", vector, {"metadata": "value"})
])

Weaviate Example​

import weaviate

# Initialize Weaviate client
client = weaviate.Client("http://localhost:8080")

# Get embedding
response = openai_client.embeddings.create(
    model="text-embedding-3-large",
    input="Document text"
)
vector = response.data[0].embedding

# Store in Weaviate
client.data_object.create(
    class_name="Document",
    data_object={"content": "Document text"},
    vector=vector
)

Best Practices​

  1. Performance Optimization

    • Batch similar length texts
    • Use appropriate chunk sizes
    • Cache common embeddings

  2. Cost Management

    • Monitor token usage
    • Optimize input text length
    • Implement caching

  3. Vector Storage

    • Choose appropriate vector DB
    • Index properly
    • Regular maintenance

Next Steps​