-
Hi,
I'm part of the Amazon Lucene team. I was trying to get KNN queries to work with LRUQueryCache. From my understanding, if I have isCacheable to return true from my query class then it will taken …
-
# Summary
Using HNSWFlat Index with METRIC_Canberra to search brings different results ***sometime*** when running on CPU and GPU.
# Platform
OS: Ubuntu 24.04 LTS
Faiss version:…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/apache/kvrocks/issues) and found no similar issues.
### Motivation
In the context of index, the absence of a lockin…
-
run knowhere benchmark crash, index type HNSW, data type fp16
```
#0 0x00007ffff66849e5 in _mm_load_si128(long long __vector(2) const*) (__P=0x7ffeffac1218) at /usr/lib/gcc/x86_64-linux-gnu/9/inclu…
-
Per #31.
-
Building wheels for collected packages: faiss-cpu
Building wheel for faiss-cpu (pyproject.toml) ... error
error: subprocess-exited-with-error
× Building wheel for faiss-cpu (pyproject.toml)…
-
I'm having trouble finding the right parameters for an hnsw index. Here's the rough outline of my table ontology:
```
vectorized_document {
id: bigint pk
text: text
embedding: vector(n)
…
-
### Description
Currently the only way for users to do a brute-force or exact search with KNN is with a script query. This requires some knowledge of the function names and scoring methodologies.
…
-
this is my code using llamaindex==0.10.68 and qdrant client==1.11.3 with use_async= True it gives error without it it works
self.client = qdrant_client.QdrantClient(
host=config.q…
-
I am trying to achieve a search where some tuples have more weight than others. Let's say I have my table:
```
Document:
- id
- embedding
- is_important : boolean
```
If the document is impo…