uform
ucall
uform | ucall | |
---|---|---|
8 | 13 | |
894 | 994 | |
9.3% | 2.0% | |
9.2 | 6.4 | |
10 days ago | 26 days ago | |
Python | C | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
uform
-
CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data
question: any good on-device size image embedding models?
tried https://github.com/unum-cloud/uform which i do like, especially they also support languages other than English. Any recommendations on other alternatives?
- Multimodal Embeddings for JavaScript, Swift, and Python
- Show HN: UForm v2 Featuring Multimodal Matryoshka, Multimodal DPO, and ONNX
- UForm v1: Multimodal Chat in 1.5B Parameters
-
Show HN: I scraped 25M Shopify products to build a search engine
As you scale, you may benefit from these two projects I maintain, and the Big Tech uses :)
https://github.com/unum-cloud/usearch - for faster search
https://github.com/unum-cloud/uform - for cheaper multi-lingual multi-modal embeddings
-
Show HN: U)Search Images demo in 200 lines of Python
[2]: https://github.com/unum-cloud/uform
- Show HN: UForm v2 โ tiny CLIP-like embeddings in 21 languages and Graphcore API
-
Unum: Vector Search engine in a single file
Ouch! Thatโs fat! Which model is that?
We have built a few video-search system by now, using USearch and UForm for embedding. They are only 256 dims and you can concatenate a few from different parts of the video. Any chance it would help?
https://github.com/unum-cloud/uform
ucall
- Show HN: U)Search Images demo in 200 lines of Python
-
Faster JSON-RPC on Linux kernel 5.19+ with io_uring and simdjson
Type checking was included, and union support is trivial to add. We have just added a feature request and will release it in a few days.
- FLiP Stack Weekly for 13 March 2023
-
Show HN: Up to 100x Faster FastAPI with simdjson and io_uring on Linux 5.19
You are right! For the convenience of Python users, we have to introspect the messages and parse JSON into Python objects. Every member of every dictionary being allocated on heap.
To make it as fast as possible we don't use PyBind, NanoBind, SWIG, or any high-level tooling. Our Python bindings are a pure CPython integration. There is just no way to beat that combo, not that I know.
https://github.com/unum-cloud/ujrpc/blob/main/src/python.c
-
Lightweight RPC with `simdjson` and `io_uring` on Linux 5.19 and newer
TLDR: UJRPC reaches 230K TCP/IP round-trips per second on 1 socket. Faster than gRPC and much faster than FastAPI.
- Up to 100x Faster FastAPI with simdjson and io_uring on Linux 5.19+
What are some alternatives?
CogVLM - a state-of-the-art-level open visual language model | ๅคๆจกๆ้ข่ฎญ็ปๆจกๅ
frontman - Frontman is an open-source API gateway written in Go that allows you to manage your microservices and expose them as a single API endpoint. It acts as a reverse proxy and handles requests from clients, routing them to the appropriate backend service.
usearch - Fast Open-Source Search & Clustering engine ร for Vectors & ๐ Strings ร in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram ๐
msgspec - A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML
kuzu - Embeddable property graph database management system built for query speed and scalability. Implements Cypher.
japronto - Screaming-fast Python 3.5+ HTTP toolkit integrated with pipelining HTTP server based on uvloop and picohttpparser.
LinkBERT - [ACL 2022] LinkBERT: A Knowledgeable Language Model ๐ Pretrained with Document Links
simdjson - Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
neural-file-sorter - A neural network based file sorter. Trains an autoencoder to sort images or audio based on the similarity of their encodings, or uses the OpenAI CLIP model.
FrameworkBenchmarks - Source for the TechEmpower Framework Benchmarks project
semantic-search-app-template - Tutorial and template for a semantic search app powered by the Atlas Embedding Database, Langchain, OpenAI and FastAPI
Muonbase - Document Database