-
In order to improve the speed of the build pipeline and reduce build dependencies, it would be great to create new Dockerfiles that would build dlib and faiss for arm64 and x64 and return as an artifa…
-
Creating a search engine which searches semantically rather than previous versions of keyword-based searching.
- The application will have a vector database to query from (Choices are FAISS, ChromaD…
-
https://en.wikipedia.org/wiki/Nearest_neighbor_search
+ k-nearest neighbors
+ approximate nearest neighbor
+ nearest neighbor distance ratio
+ fixed-radius near neighbors
+ all nearest neighbors
ytgui updated
4 years ago
-
When I use GPT to read a large local data set of several hundred MB in hybrid mode, GPT will start reading. When I check the Activity Monitor on my Mac, I can see that the memory usage of python3.…
-
Hello!
Thanks for sharing your work. While running the model I found a few issues:
1. If I understand correctly, I should first run the retriever with `eval_mhop_retrieval.py` , then process the…
-
### *Project idea 2: DocArray wrap ANN libraries*
| Info | details |
| ---------------- | -----------------------------------------…
-
Hello!
I was wondering if someone can confirm that this package still runs under pytroch lts or current stable (1.11.1)?
I'm getting a curious error. Note this is for CPU training. Maybe someon…
-
Hi I just install Immich and found your tool. I have it running via Docker. I am able to connect to my Immich instance and configure the URL and API and started the Create/Update FAISS index, which se…
hurtz updated
7 months ago
-
**Describe the bug**
Followed the instructions but could not get
```
conda env create -f environment.yml
```
to work because of
```
ResolvePackageNotFound:
- cudatoolkit=11.6.0
- faiss-…
-
Hi, thanks for your excellent work.
I run the K-means algorithm (faiss-gpu based) over L2-normalized pretext features (i.e., MoCo v2 checkpoint). The result on the training dataset is around 66% AC…