Standard Embeddings

from perplexity import Perplexity

client = Perplexity()

response = client.embeddings.create(
    input=[
        "Scientists explore the universe driven by curiosity.",
        "Curiosity compels us to seek explanations, not just observations.",
        "Historical discoveries began with curious questions.",
        "The pursuit of knowledge distinguishes human curiosity from mere stimulus response.",
        "Philosophy examines the nature of curiosity."
    ],
    model="pplx-embed-v1-4b"
)

for emb in response.data:
    print(f"Index {emb.index}: {emb.embedding}")

import base64
import numpy as np
from perplexity import Perplexity

client = Perplexity()

def decode_embedding(b64_string):
    """Decode a base64-encoded int8 embedding."""
    return np.frombuffer(base64.b64decode(b64_string), dtype=np.int8).astype(np.float32)

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 1. Embed your documents
documents = [
    "Python is a versatile programming language",
    "Machine learning automates analytical model building",
    "The Eiffel Tower is located in Paris, France"
]

doc_response = client.embeddings.create(input=documents, model="pplx-embed-v1-4b")
doc_embeddings = [decode_embedding(emb.embedding) for emb in doc_response.data]

# 2. Embed a search query
query = "What programming languages are good for data science?"
query_response = client.embeddings.create(input=[query], model="pplx-embed-v1-4b")
query_embedding = decode_embedding(query_response.data[0].embedding)

# 3. Find most similar documents
scores = [
    (i, cosine_similarity(query_embedding, doc_emb))
    for i, doc_emb in enumerate(doc_embeddings)
]
ranked = sorted(scores, key=lambda x: x[1], reverse=True)

print("Search results:")
for idx, score in ranked:
    print(f"  {score:.4f}: {documents[idx]}")