jina-clip-v2

pip install pinecone requests

from pinecone import Pinecone, ServerlessSpec

pc = Pinecone(api_key="API_KEY")

JINA_API_KEY = ""  # Replace with your Jina API key
dimension = 1024  # Specify the desired embedding dimension

index_name = "jina-clip-v2"

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=dimension,
        metric="cosine",
        spec=ServerlessSpec(
            cloud='aws',
            region='us-east-1'  # Replace with your preferred region
        )
    )

index = pc.Index(index_name)

from typing import List
import requests

def get_embeddings(
    inputs: List[dict],  # Each item is {"text": ...} or {"image": <image URL>}
    dimensions: int = 1024,
    task: str = None  # Set to 'retrieval.query' for text retrieval
):
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {JINA_API_KEY}'
    }
    data = {
        'input': inputs,
        'model': 'jina-clip-v2',
        'dimensions': dimensions,
    }
    if task:
        data['task'] = task

    response = requests.post('https://api.jina.ai/v1/embeddings', headers=headers, json=data)
    return response.json()

# Example data with image and text
data = [
    {"id": "img1", "modality": "image", "content": "https://example.com/image1.jpg"},
    {"id": "txt1", "modality": "text", "content": "A red apple on a table."},
    {"id": "img2", "modality": "image", "content": "https://example.com/image2.png"},
    {"id": "txt2", "modality": "text", "content": "A basket of green apples."},
]

vectors = []
for item in data:
    embeddings = get_embeddings([{item["modality"]: item["content"]}], dimensions=dimension)
    embedding = embeddings["data"][0]["embedding"]
    vectors.append({
        "id": item['id'],
        "values": embedding,
        "metadata": {'content': item['content'], 'modality': item['modality']}
    })

index.upsert(
    vectors=vectors,
    namespace="ns1"  # optionally specify a namespace
)

query = "Santa With Glasses"  # Text query

embeddings = get_embeddings([{"text": query}], dimensions=dimension, task='retrieval.query')
query_embedding = embeddings["data"][0]["embedding"]

results = index.query(
    namespace="ns1",
    vector=query_embedding,
    top_k=3,
    include_values=False,
    include_metadata=True
)

print(results)