cpcdoy / rust-sbert Goto Github PK
View Code? Open in Web Editor NEWRust port of sentence-transformers (https://github.com/UKPLab/sentence-transformers)
License: Apache License 2.0
Rust port of sentence-transformers (https://github.com/UKPLab/sentence-transformers)
License: Apache License 2.0
Hi,
Just wanted to know whether this project supports all other models present in below link
https://public.ukp.informatik.tu-darmstadt.de/reimers/sentence-transformers/v0.2/
Hi @cpcdoy,
I was wondering whether there are any plans to also port some of the auxiliary code around the models from sentence-transformers, like semantic_search. This is probably one of the main use cases of both libraries, so many people might be interested in it in the future.
edit: I saw a contributor also works on https://github.com/lerouxrgd/ngt-rs which should do the trick. @lerouxrgd, an example of combining rust-sbert and ngt-rs would be really really useful for this!
Sorry, very green to rust.
how does performance of the huggingface vs rust tokenizers compare?
Is cuda supported?
Docker build failed:
v0vten@Ursu14-Focal-Mango:~/tools/rust-sbert$ docker build -t tch-converter -f utils/Dockerfile .
[+] Building 111.2s (11/12) docker:default
=> [internal] load .dockerignore 0.0s
=> => transferring context: 102B 0.0s
=> [internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 820B 0.0s
=> [internal] load metadata for docker.io/library/python:3.8-slim 0.0s
=> CACHED [1/8] FROM docker.io/library/python:3.8-slim 0.0s
=> [internal] load build context 0.0s
=> => transferring context: 63.22kB 0.0s
=> [2/8] RUN apt-get update && apt-get install -y clang curl unzip libssl-dev pkg-config make 27.1s
=> [3/8] RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y --default-toolchain 1.43.1-x86_64-unknown-linux- 27.9s
=> [4/8] RUN pip install torch==1.6.0+cpu -f https://download.pytorch.org/whl/torch_stable.html 16.8s
=> [5/8] COPY Cargo.toml Cargo.lock ./ 0.0s
=> [6/8] COPY src/bin ./src/bin 0.0s
=> ERROR [7/8] RUN touch src/lib.rs && cargo build --bin=convert-tensor 39.3s
------
> [7/8] RUN touch src/lib.rs && cargo build --bin=convert-tensor:
0.377 Updating crates.io index
39.23 error: failed to select a version for the requirement `regex = "= 1.9.1"`
39.23 candidate versions found which didn't match: 1.8.4, 1.8.3, 1.8.2, ...
39.23 location searched: crates.io index
39.23 required by package `rust_tokenizers v7.0.2`
39.23 ... which is depended on by `sbert v0.4.0 (/)`
------
Dockerfile:33
--------------------
31 | COPY src/bin ./src/bin
32 |
33 | >>> RUN touch src/lib.rs && cargo build --bin=convert-tensor
34 |
35 | COPY utils/prepare_distilbert.py ./
--------------------
ERROR: failed to solve: process "/bin/sh -c touch src/lib.rs && cargo build --bin=convert-tensor" did not complete successfully: exit code: 101
Hi,
first of all: thanks for that amazing port. I finally managed to get it working even under windows.
Are there any recommendations for further usage of the computed vectors in regards to similarity measurements?
My plan now would have been to embed a given search query as well and then calculate the cosine similarity between search query and dataset entry for each entry from the processed "dataset".
Is there anything against this approach? Are there any more advanced libraries that you know of?
Thanks in advance for the support. I would be open for contribution in any case.
Kind regards
Julian
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.