Embeddings

import openai

client = openai.OpenAI(
    base_url="https://api.oxlo.ai/v1",
    api_key="<YOUR_API_KEY>"
)

response = client.embeddings.create(
    model="bge-large",
    input="Oxlo.ai is a distributed GPU network for AI inference."
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

response = client.embeddings.create(
    model="bge-large",
    input=[
        "How to deploy a machine learning model",
        "Best practices for GPU optimization",
        "Introduction to vector databases"
    ]
)

for i, item in enumerate(response.data):
    print(f"Text {i}: {len(item.embedding)} dimensions")

import numpy as np

# 1. Embed your knowledge base
docs = [
    "Oxlo.ai supports text generation, image generation, and embeddings.",
    "Free tier includes Mistral-7B, Llama-3.2-3B, and Stable Diffusion 1.5.",
    "Premium users get access to Llama-3.3-70B and DeepSeek R1 70B.",
]

doc_response = client.embeddings.create(model="bge-large", input=docs)
doc_vectors = [np.array(d.embedding) for d in doc_response.data]

# 2. Embed user's query
query = "What models are available for free?"
query_response = client.embeddings.create(model="bge-large", input=query)
query_vector = np.array(query_response.data[0].embedding)

# 3. Find most similar document (cosine similarity)
similarities = [
    np.dot(query_vector, doc_vec) / (np.linalg.norm(query_vector) * np.linalg.norm(doc_vec))
    for doc_vec in doc_vectors
]
best_match = docs[np.argmax(similarities)]
print(f"Best match: {best_match}")