euclidesdb

euclidesdb copied to clipboard

Due to the limitations of the PyTorch version of the prebuilt container, I wanted to build it myself by running: `docker build -t euclides_package package/` Even after modifying the whole...

davesean

Hi, thanks for creating this tool. I got an error while installation. It was on a Ubuntu GPU EC2 instance. Even though this looks like a Pytorch error, any idea...

wendilinplay

Docker based server returns error on Add Image and Find Similar calls - using Python Client API

4

1) Add Image grpc._channel._Rendezvous:

senthilmk

Java client

1

**Work In Progress** [](https://travis-ci.org/mycaule/euclidesdb) See #6. - [ ] Structure of the folders : `/source/proto `and `python/examples/image` have to be shared at higher level in the folder hierarchy, I temporarily...

mycaule

Create NodeJS client API

1

Create the NodeJS client API package.

perone

Create Java client API

2

Create the Java client API package.

perone

Implement integration and builds for using GPU version of libtorch.

perone

About the scalability

2

Thank you for creating this. In case of millions or billions of feature vectors, how should we scale? Where is the index stored (in RAM or disk...)? How fast it...

LiberiFatali

Segmentation fault (core dumped)

6

I have launched EuclidesDB on local machine. Have added 48042 items into annoy index. But then I can't get similar images using `db.find_similar_image(img, ["resnet18"], 7)` ``` channel = euclides.Channel("localhost", 50000)...

mlcoop

The parameter `search_k` in Annoy isn't the same as the `top_k`. This must be fixed in the search engine.

perone