Embeddings

import os
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key=os.environ["ZURELAY_API_KEY"],
)
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The food was delicious and the waiter was friendly.",
)
vector = response.data[0].embedding  # a list of 1,536 floats
print(len(vector), response.usage.prompt_tokens)  # 1536 10

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [-0.0022748, -0.0093183, 0.0158532, ..., -0.0028842]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": { "prompt_tokens": 10, "total_tokens": 10 }
}

# pip install tiktoken
import tiktoken
# The tokenizer text-embedding-3 counts with, to keep each request under the limits
enc = tiktoken.get_encoding("cl100k_base")
def batches(texts, max_inputs=2048, max_tokens=300_000):
    batch, tokens = [], 0
    for text in texts:
        count = len(enc.encode(text))
        if batch and (len(batch) == max_inputs or tokens + count > max_tokens):
            yield batch
            batch, tokens = [], 0
        batch.append(text)
        tokens += count
    if batch:
        yield batch
vectors = []
for batch in batches(texts):
    response = client.embeddings.create(model="text-embedding-3-small", input=batch)
    vectors += [item.embedding for item in response.data]  # in the order sent

response = client.embeddings.create(
    model="text-embedding-3-large",
    input="The food was delicious and the waiter was friendly.",
    dimensions=1024,
)
print(len(response.data[0].embedding))  # 1024

import base64
import numpy as np
response = client.embeddings.create(
    model="text-embedding-3-small",
    input=["First text", "Second text"],
    encoding_format="base64",
)
# Each embedding is a base64 string of little-endian float32 numbers
vectors = [np.frombuffer(base64.b64decode(item.embedding), dtype="<f4") for item in response.data]

# pip install openai numpy
import os
import numpy as np
from openai import OpenAI
client = OpenAI(base_url="https://api.zurelay.com/v1", api_key=os.environ["ZURELAY_API_KEY"])
MODEL = "text-embedding-3-small"
docs = [
    "To change your password, open Settings, choose Security and click Change password.",
    "Invoices are emailed on the first day of each month and can be downloaded under Billing.",
    "Invite teammates from the Team page; each person signs in with their own email.",
    "API keys can be limited to a monthly budget, a rate limit and a list of models.",
]
def embed(texts):
    response = client.embeddings.create(model=MODEL, input=texts)
    return np.array([item.embedding for item in response.data])
doc_vectors = embed(docs)  # embed once, and store the vectors beside the text
def search(query, k=2):
    query_vector = embed([query])[0]
    # The vectors have length 1, so the dot product is the cosine similarity
    scores = doc_vectors @ query_vector
    best = np.argsort(-scores)[:k]
    return [(docs[i], float(scores[i])) for i in best]
for text, score in search("How can I change my password?"):
    print(f"{score:.3f}  {text}")  # the password article comes first

# After the search example above: retrieve, then answer from what was found
question = "How do I stop a key from spending too much?"
notes = "\n".join(text for text, _ in search(question))
answer = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[
        {
            "role": "system",
            "content": "Answer from these notes only. If they don't say, say so.\n\n" + notes,
        },
        {"role": "user", "content": question},
    ],
)
print(answer.choices[0].message.content)

# pip install langchain-openai
import os
from langchain_openai import OpenAIEmbeddings
embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",
    base_url="https://api.zurelay.com/v1",
    api_key=os.environ["ZURELAY_API_KEY"],
)
query_vector = embeddings.embed_query("How can I change my password?")
doc_vectors = embeddings.embed_documents(["First document", "Second document"])

# pip install llama-index-embeddings-openai
import os
from llama_index.core import Settings
from llama_index.embeddings.openai import OpenAIEmbedding
Settings.embed_model = OpenAIEmbedding(
    model="text-embedding-3-small",
    api_base="https://api.zurelay.com/v1",
    api_key=os.environ["ZURELAY_API_KEY"],
)
vector = Settings.embed_model.get_text_embedding("How can I change my password?")

// npm install ai @ai-sdk/openai
import { createOpenAI } from "@ai-sdk/openai";
import { cosineSimilarity, embed, embedMany } from "ai";
const zurelay = createOpenAI({
  baseURL: "https://api.zurelay.com/v1",
  apiKey: process.env.ZURELAY_API_KEY,
});
const model = zurelay.embedding("text-embedding-3-small");
const { embeddings } = await embedMany({ model, values: ["First document", "Second document"] });
const { embedding } = await embed({ model, value: "How can I change my password?" });
console.log(cosineSimilarity(embedding, embeddings[0]));