# Import the Pinecone library
from pinecone.grpc import PineconeGRPC as Pinecone
from pinecone import ServerlessSpec
import time

# Initialize a Pinecone client with your API key
pc = Pinecone(api_key="YOUR_API_KEY")

# Define a sample dataset where each item has a unique ID and piece of text
data = [
    {"id": "vec1", "text": "Apple is a popular fruit known for its sweetness and crisp texture."},
    {"id": "vec2", "text": "The tech company Apple is known for its innovative products like the iPhone."},
    {"id": "vec3", "text": "Many people enjoy eating apples as a healthy snack."},
    {"id": "vec4", "text": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces."},
    {"id": "vec5", "text": "An apple a day keeps the doctor away, as the saying goes."},
    {"id": "vec6", "text": "Apple Computer Company was founded on April 1, 1976, by Steve Jobs, Steve Wozniak, and Ronald Wayne as a partnership."}
]

# Convert the text into numerical vectors that Pinecone can index
embeddings = pc.inference.embed(
    model="llama-text-embed-v2",
    inputs=[d['text'] for d in data],
    parameters={"input_type": "passage", "truncate": "END"}
)

print(embeddings)

EmbeddingsList(
    model='llama-text-embed-v2',
    data=[
        {'values': [0.04925537109375, -0.01313018798828125, -0.0112762451171875, ...]},
        ...
    ],
    usage={'total_tokens': 130}
)