-
Hi!
I noticed that when I am using `qdrant` locally then `on_disk_payload` parameter cannot be set to True, which makes the RAM usage very high while indexing large number of documents.
For my useca…
-
**Description**
Configure vectordb index creation (hnsw, ivfflat).
Configure semantic search with pgvector (search params such as "m", "ef_construction" for hnsw, "probes" for ivfflat) through .env …
-
Hi,
Think pgvector isnt the issue nevertheless any leads would be useful.
Setup that works:
##Ubuntu 14.9-1.pgdg20.04+1 ## on 8 cpu, 32g RAM VM.
"checkpoint_completion_target" "0.9"
"e…
-
1：机器上分区对应的meta信息与etcd不一致，手动将机器上的meta信息调整为与etcd一致，然后重启，重启后发现meta信息又恢复到了之前的错误meta信息
机器上的meta信息如下：
{"id":1,"name":"pic512","version":462,"db_id":1,"enabled":true,"partitions":[{"id":1,"space_id":1,"d…
-
# Introducing Loading Layer in Native KNN Engines
# 1. Goal
[FAISS](https://github.com/facebookresearch/faiss/tree/main/faiss) and [Nmslib](https://github.com/nmslib/nmslib), two native engines,…
-
I am using IVFFLAT for 1200 dimensional embeddings of vector type. I have 20 million rows.
The query that is slow takes a user provided vector and finds the top 100 matching vectors. There are 4200…
-
# Summary
It fails to add vector to HNSW index in window platform. Same script works for Mac.
# Platform
x64
OS: Window Server 2022
Faiss version: 1.8.0
Installed from: pip install fai…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version: v2.4.4
- Deployment mode(standalone or cluster):
- MQ type(rocksmq…
yhmo updated
2 months ago
-
```
umap.__version__ == 0.4.6
```
In the following example, UMAP is applied to random data with tiny variations around a fixed value. Arbitrary labels are assigned to the data in order ('a' for t…
-
Hi. I've created an HNSW index on a table with a UUID primary key. Does this type of primary key affect the memory usage of the HNSW index? If I change the primary key type to an integer, will the siz…
bbkgh updated
4 months ago