Databases
MongoDB
For an end-to-end guide follow this link: https://cloud.mongodb.com/ecosystem/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 an Atlas vector search index of 768 dimensions for
vuse-generic-v1 model embeddings. We’re calling it video_index.
Ingest
from mixpeek import Mixpeek
from pymongo import MongoClient
# Initialize the Mixpeek client with your API key
mixpeek = Mixpeek("YOUR_API_KEY")
client = MongoClient("YOUR_MONGODB_URI")
# Process video chunks
processed_chunks = mixpeek.tools.video.process(
video_source="https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/Jurassic+Park+(2).mp4",
chunk_interval=1, # 1 second intervals
resolution=[720, 1280]
)
for index, chunk in enumerate(processed_chunks):
print(f"Processing video chunk: {index}")
# embed each chunk
embed_response = mixpeek.embed.video(
model_id="vuse-generic-v1",
input=chunk['base64_chunk'],
input_type="base64"
)
result = {
"start_time": chunk["start_time"],
"end_time": chunk["end_time"],
"embedding": embed_response['embedding']
}
client.db.collection.insert_one(result)
Text Query
query = "two boys inside a car"
embed_response = mixpeek.embed.video(
model_id="vuse-generic-v1",
input=query,
input_type="text"
)
aggregation = [{
"$vectorSearch": {
"index": "default",
"path": "embedding",
"queryVector": embed_response['embedding'],
"numCandidates": 100
"limit": 10
}
}]
results = client.db.collection.aggregate(aggregation)
for result in results:
print(result)
Video Query
# we'll use a cartoon version of jurassic park
file_url = "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/rabbit-jurassic.mp4"
embed_response = mixpeek.embed.video(
model_id="vuse-generic-v1",
input=file_url,
input_type="url"
)
aggregation = [{
"$vectorSearch": {
"index": "default",
"path": "embedding",
"queryVector": embed_response['embedding'],
"numCandidates": 100
"limit": 10
}
}]
results = client.db.collection.aggregate(aggregation)
for result in results:
print(result)
Image
We’ll be using clip-v1 to build a collection of image embeddings with 512 dimensions.
You’ll need to create an Atlas vector search index of 512 dimensions for
clip-v1 model embeddings. We’re calling it image_index.
Ingest
from mixpeek import Mixpeek
from pymongo import MongoClient
# Initialize the Mixpeek client with your API key
mixpeek = Mixpeek("YOUR_API_KEY")
client = MongoClient("YOUR_MONGODB_URI")
# List of image URLs to process
image_urls = [
"https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/image1.jpg",
"https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/image2.jpg",
"https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/image3.jpg",
"https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/image4.jpg"
]
for url in 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"
)
result = {
"image_url": url,
"embedding": embed_response['embedding']
}
client.db.image_collection.insert_one(result)
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"
)
aggregation = [{
"$vectorSearch": {
"index": "image_index",
"path": "embedding",
"queryVector": embed_response['embedding'],
"numCandidates": 100,
"limit": 5
}
}]
results = client.db.image_collection.aggregate(aggregation)
for result in results:
print(result)
Image Query
# Use an image from the same bucket as a query
query_image = "https://mixpeek-public-demo.s3.us-east-2.amazonaws.com/mongodb/query_image.jpg"
embed_response = mixpeek.embed.image(
model_id="clip-v1",
input=query_image,
input_type="url"
)
aggregation = [{
"$vectorSearch": {
"index": "image_index",
"path": "embedding",
"queryVector": embed_response['embedding'],
"numCandidates": 100,
"limit": 5
}
}]
results = client.db.image_collection.aggregate(aggregation)
for result in results:
print(result)