Вложения Jina#

import requests

import qdrant_client
from qdrant_client.models import Distance, VectorParams, Batch

# Provide Jina API key and choose one of the available models.
JINA_API_KEY = "jina_xxxxxxxxxxx"
MODEL = "jina-embeddings-v3"
DIMENSIONS = 1024 # Or choose your desired output vector dimensionality.
TASK = 'retrieval.passage' # For indexing, or set to retrieval.query for querying

# Get embeddings from the API
url = "https://api.jina.ai/v1/embeddings"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {JINA_API_KEY}",
}

data = {
    "input": ["Your text string goes here", "You can send multiple texts"],
    "model": MODEL,
    "dimensions": DIMENSIONS,
    "task": TASK,
    "late_chunking": True,
}

response = requests.post(url, headers=headers, json=data)
embeddings = [d["embedding"] for d in response.json()["data"]]


# Index the embeddings into {{prod_name}}
client = qdrant_client.QdrantClient(":memory:")
client.create_collection(
    collection_name="MyCollection",
    vectors_config=VectorParams(size= DIMENSIONS, distance=Distance.DOT),
)


qdrant_client.upsert(
    collection_name="MyCollection",
    points=Batch(
        ids=list(range(len(embeddings))),
        vectors=embeddings,
    ),
)

import requests
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct

# Provide your Jina API key and choose the model.
JINA_API_KEY = "jina_xxxxxxxxxxx"
MODEL = "jina-clip-v2"
DIMENSIONS = 1024  # Set the desired output vector dimensionality.

# Define the inputs
text_input = "A blue cat"
image_url = "https://i.pinimg.com/600x315/21/48/7e/21487e8e0970dd366dafaed6ab25d8d8.jpg"

# Get embeddings from the Jina API
url = "https://api.jina.ai/v1/embeddings"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {JINA_API_KEY}",
}
data = {
    "input": [
        {"text": text_input},
        {"image": image_url},
    ],
    "model": MODEL,
    "dimensions": DIMENSIONS,
}

response = requests.post(url, headers=headers, json=data)
response_data = response.json()["data"]

# The model doesn't differentiate between images and text, so we extract output based on the input order.
text_embedding = response_data[0]["embedding"]
image_embedding = response_data[1]["embedding"]

# Initialize Qdrant client
client = QdrantClient(url="http://localhost:6333/")

# Create a collection with named vectors
collection_name = "MyCollection"
client.recreate_collection(
    collection_name=collection_name,
    vectors_config={
        "text_vector": VectorParams(size=DIMENSIONS, distance=Distance.DOT),
        "image_vector": VectorParams(size=DIMENSIONS, distance=Distance.DOT),
    },
)

client.upsert(
    collection_name=collection_name,
    points=[
        PointStruct(
            id=0,
            vector={
                "text_vector": text_embedding,
                "image_vector": image_embedding,
            }
        )
    ],
)

# Now let's query the collection
search_query = "A purple cat"

# Get the embedding for the search query from the Jina API
url = "https://api.jina.ai/v1/embeddings"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {JINA_API_KEY}",
}
data = {
    "input": [{"text": search_query}],
    "model": MODEL,
    "dimensions": DIMENSIONS,
    # "task": "retrieval.query" # Uncomment this line for text-to-text retrieval tasks
}

response = requests.post(url, headers=headers, json=data)
query_embedding = response.json()["data"][0]["embedding"]

search_results = client.query_points(
    collection_name=collection_name,
    query=query_embedding,
    using="image_vector",
    limit=5
).points

for result in search_results:
    print(f"ID: {result.id}, Score: {result.score}")