For an end-to-end guide follow this link: https://qdrant.tech/documentation/embeddings/mixpeek/

​
Video

We’ll be using vuse-generic-v1 to build a collection of 1 second interval video chunks into a 768 dimension embedding collection.

You’ll need to create a Qdrant collection called video_chunks with 768 dimensions for vuse-generic-v1 model embeddings.

​
Ingest

from mixpeek import Mixpeek
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance

# Initialize the Mixpeek client with your API key
mixpeek = Mixpeek("YOUR_API_KEY")

# Initialize Qdrant client
client = QdrantClient("localhost", port=6333)

# Create collection
client.recreate_collection(
    collection_name="video_chunks",
    vectors_config=VectorParams(size=768, distance=Distance.COSINE),
)

# Process video chunks
processed_chunks = mixpeek.tools.video.process(
    video_source="https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/Jurassic+Park+(2).mp4",
    chunk_interval=1, # 1 second intervals
    resolution=[720, 1280]
)

for i, chunk in enumerate(processed_chunks):
    print(f"Processing video chunk: {i}")

    # embed each chunk
    embed_response = mixpeek.embed.video(
        model_id="vuse-generic-v1",
        input=chunk['base64_chunk'],
        input_type="base64"
    )

    # Add to Qdrant
    client.upsert(
        collection_name="video_chunks",
        points=[
            {
                "id": i,
                "vector": embed_response['embedding'],
                "payload": {
                    "start_time": chunk["start_time"],
                    "end_time": chunk["end_time"]
                }
            }
        ]
    )

​
Text Query

query = "two boys inside a car"

embed_response = mixpeek.embed.video(
    model_id="vuse-generic-v1",
    input=query,
    input_type="text"
)

results = client.search(
    collection_name="video_chunks",
    query_vector=embed_response['embedding'],
    limit=10
)

for result in results:
    print(result)

​
Video Query

# we'll use a cartoon version of jurassic park
file_url = "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/rabbit-jurassic.mp4"

embed_response = mixpeek.embed.video(
    model_id="vuse-generic-v1",
    input=file_url,
    input_type="url"
)

results = client.search(
    collection_name="video_chunks",
    query_vector=embed_response['embedding'],
    limit=10
)

for result in results:
    print(result)

​
Image

We’ll be using openai-clip-vit-base-patch32 to build a collection of image embeddings with 512 dimensions.

You’ll need to create a Qdrant collection called images with 512 dimensions for openai-clip-vit-base-patch32 model embeddings.

​
Ingest

from mixpeek import Mixpeek
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance

# Initialize the Mixpeek client with your API key
mixpeek = Mixpeek("YOUR_API_KEY")

# Initialize Qdrant client
client = QdrantClient("localhost", port=6333)

# Create collection
client.recreate_collection(
    collection_name="images",
    vectors_config=VectorParams(size=512, distance=Distance.COSINE),
)

# List of image URLs to process
image_urls = [
    "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/image1.jpg",
    "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/image2.jpg",
    "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/image3.jpg",
    "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/image4.jpg"
]

for i, url in enumerate(image_urls):
    print(f"Processing image: {url}")

    # Embed each image
    embed_response = mixpeek.embed.image(
        model_id="openai-clip-vit-base-patch32",
        input=url,
        input_type="url"
    )

    # Add to Qdrant
    client.upsert(
        collection_name="images",
        points=[
            {
                "id": i,
                "vector": embed_response['embedding'],
                "payload": {"image_url": url}
            }
        ]
    )

​
Text Query

query = "a cat sitting on a windowsill"

embed_response = mixpeek.embed.image(
    model_id="openai-clip-vit-base-patch32",
    input=query,
    input_type="text"
)

results = client.search(
    collection_name="images",
    query_vector=embed_response['embedding'],
    limit=5
)

for result in results:
    print(result)

​
Image Query

# Use an image from the same bucket as a query
query_image = "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/qdrant/query_image.jpg"

embed_response = mixpeek.embed.image(
    model_id="openai-clip-vit-base-patch32",
    input=query_image,
    input_type="url"
)

results = client.search(
    collection_name="images",
    query_vector=embed_response['embedding'],
    limit=5
)

for result in results:
    print(result)

Was this page helpful?

Suggest editsRaise issue
WeaviateRedis