multilingual-e5-large

pip install --upgrade pinecone

from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

# Create an index for dense vectors with integrated inference
index_name = "multilingual-e5-large"
pc.create_index_for_model(
    name=index_name,
    cloud="aws",
    region="us-east-1",
    embed={
        "model": "multilingual-e5-large",
        "field_map": {
            "text": "text"  # Map the record field to be embedded
        }
    }
)

index = pc.Index(index_name)

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."}
]

index.upsert_records(
    namespace="example-namespace",
    records=data
)

query_payload = {
    "inputs": {
        "text": "Tell me about the tech company known as Apple."
    },
    "top_k": 3
}

results = index.search(
    namespace="example-namespace",
    query=query_payload
)

print(results)