-
I suggest we put the `findMediod()` function inside the **Vamana** class as a **method**. Additionally we can add an attribute to the class also, so that every time we load a vamana index from a file …
-
Initial Vamana build has limited features and several items to improve performance or usability. Once these items are addressed, we can consider moving it out of the "experimental" namespace. They inc…
-
I assume it should be in aux_utils.cpp/int build_disk_index(...){ }
maybe somewhere after diskann::build_merged_vamana_index(
data_file_to_use.c_str(), diskann::Metric::L2, L, R, p_val,
…
-
Add DiskANN search functionality for the current Vamana build. Already have a GreedySearch kernel as part of build, but need to edit, optimize, and possibly add more options.
If possible, would be go…
-
### What happened?
hi Team ,
Like other vector DB I am looking what Libraries and Index type from below is supported by ChromaDB
HNSWlib
DiskANN / Vamana
ScaNN
FAISS-IVFP
NGT
Also are al…
-
I suggest we convert our **Vamana Index** to a class. Since the whole idea of the **Vamana** is actually a modified **graph** data structure, I believe that building a suitable class for the **Vamana*…
-
**Vamana** algorithm is the main thing we need to implement. Since this is the main feature of the project I suggest we all work together on this.
- [x] Create the **function prototype** for the **…
-
#### Introduction
Vector databases have gained significant importance due to the rise of AI, machine learning, and deep learning applications. These databases store high-dimensional vectors repre…
-
### Description
I came across this compelling sounding [JVector project](https://foojay.io/today/jvector-1-0/) which looks to have awesome QPS performance.
It uses [DiskANN](https://www.microsoft.…
-
I suggest we make our **main** file execution more flexible by changing some, and adding extra flags to the arguments. Specifically what I suggest is to use key-value pairs for the arguments. For exam…