This is an excellent tutorial ! Just one suggestion, can you please, the next time, use the words from the payload to create the embeddings for the vectors and then pad it as well to create vectors of n=100 dimensions and then show the same example. It will help people like me understand easy to use next steps to embed complete documents.
Love your teaching style! One question.. if I have millions of data points and I want to create and save some query results.. so that I can show my clients something while I am creating/retrieving the new data query results…how would you go about doing that ? Would you do that with Qdrant only or will you combine it with another db?
More human way of adding your vectors is like this: points = [] for i in range(len(vectors)) point = models.PointStruct( id=1, vector={ "image": [0.9, 0.1, 0.1, 0.2], "text": [0.4, 0.7, 0.1, 0.8, 0.1, 0.1, 0.9, 0.2], }, ), points.append(point) client.upsert( collection_name="{collection_name}", points=points )
The dev don't care about his own channel 😂 Those are random numbers you can't really says that livin lavida loca is trully related with that australian song. At least next time use some embedding data so that it will makes more sense 😅 Using random data for a product demo intended for production is just simply lazy.
from qdrant_client import QdrantClient from qdrant_client.http import models client.upsert( collection_name="point_example", points=models.Batch( ids=[1, 2, 3], vectors=[ [0.9, 0.1, 0.1,0.5,0.6], [0.1, 0.9, 0.1,0.2,0.4], [0.1, 0.1, 0.9,0.5,0.2], ] ), ) After run this code, collection_name = "insert_for_point_examle" vector_id = 3 # 특정 ID의 벡터 조회 client.retrieve( collection_name=collection_name, ids=[1], with_vectors = True ) i checked my data id=1, but result is [Record(id=1, payload={}, vector=[0.9878784, 0.10976427, 0.10976427])] Why not [0.9, 0.1, 0.1,0.5,0.6]..?
This is valuable knowledge, thank you for sharing. I like that Qdrant is written in Rust as well!
This is an excellent tutorial ! Just one suggestion, can you please, the next time, use the words from the payload to create the embeddings for the vectors and then pad it as well to create vectors of n=100 dimensions and then show the same example. It will help people like me understand easy to use next steps to embed complete documents.
Love your teaching style! One question.. if I have millions of data points and I want to create and save some query results.. so that I can show my clients something while I am creating/retrieving the new data query results…how would you go about doing that ? Would you do that with Qdrant only or will you combine it with another db?
More human way of adding your vectors is like this:
points = []
for i in range(len(vectors))
point = models.PointStruct(
id=1,
vector={
"image": [0.9, 0.1, 0.1, 0.2],
"text": [0.4, 0.7, 0.1, 0.8, 0.1, 0.1, 0.9, 0.2],
},
),
points.append(point)
client.upsert(
collection_name="{collection_name}",
points=points
)
could you update for method qdrant client -> method recommend -> argument: query_vector seem be changed?
Thank you very useful!
Hell yeah. Demos from the bathroom!
i was amazing with your speaking speed lol
Rudolph Extension
Delmer Meadow
Lenna Throughway
Ullrich Lane
Dash not underscore
Bode Prairie
Sally Plaza
Trever Burgs
Talon Overpass
Mariane Mountain
Christop Lake
Mateo Cliff
O'Reilly Ports
Reynolds Drive
Beahan Meadow
Kyra River
Leif Heights
Sven Cape
Helene Shoal
Beahan Mall
Bailee Ramp
Yundt Course
The dev don't care about his own channel 😂
Those are random numbers you can't really says that livin lavida loca is trully related with that australian song.
At least next time use some embedding data so that it will makes more sense 😅
Using random data for a product demo intended for production is just simply lazy.
Mohamed Plains
very compliicated tutorial ever
from 1:00 time you are writitng everything in docker
actually, the tutorial couldn't have been simpler. It was very well put together.
from qdrant_client import QdrantClient
from qdrant_client.http import models
client.upsert(
collection_name="point_example",
points=models.Batch(
ids=[1, 2, 3],
vectors=[
[0.9, 0.1, 0.1,0.5,0.6],
[0.1, 0.9, 0.1,0.2,0.4],
[0.1, 0.1, 0.9,0.5,0.2],
]
),
)
After run this code,
collection_name = "insert_for_point_examle"
vector_id = 3
# 특정 ID의 벡터 조회
client.retrieve(
collection_name=collection_name,
ids=[1],
with_vectors = True
)
i checked my data id=1, but result is [Record(id=1, payload={}, vector=[0.9878784, 0.10976427, 0.10976427])]
Why not [0.9, 0.1, 0.1,0.5,0.6]..?