!pip install -qU voyageai pinecone

EMBEDDING_DIMENSION = 1024  # can choose between 1024 (default), 256, 512, and 2048
EMBEDDING_DTYPE = "float"   # can choose between "float" (default), "int8", "uint8", "binary", "ubinary"

from pinecone import Pinecone, ServerlessSpec

pc = Pinecone(api_key="API_KEY")

# Create Index
index_name = "voyage-3-large"

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=EMBEDDING_DIMENSION,
        metric="cosine",
        spec=ServerlessSpec(
            cloud="aws",
            region="us-east-1"
        )
    )

index = pc.Index(index_name)

# Embed data
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."},
]

import voyageai

vo = voyageai.Client(api_key=VOYAGE_API_KEY)

model_id = "voyage-3-large"

def embed(docs: list[str], input_type: str) -> list[list[float]]:
    embeddings = vo.embed(
		    docs,
		    model=model_id,
		    input_type=input_type,
		    output_dimension=EMBEDDING_DIMENSION,
		    output_dtype=EMBEDDING_DTYPE
		).embeddings
    return embeddings

# Use "document" input type for documents
embeddings = embed([d["text"] for d in data], input_type="document")

vectors = []
for d, e in zip(data, embeddings):
    vectors.append({
        "id": d['id'],
        "values": e,
        "metadata": {'text': d['text']}
    })

index.upsert(
    vectors=vectors,
    namespace="ns1"
)

query = "Tell me about the tech company known as Apple"

# Use "query" input type for queries
x = embed([query], input_type="query")

results = index.query(
    namespace="ns1",
    vector=x[0],
    top_k=3,
    include_values=False,
    include_metadata=True
)

print(results)