infinity
by michaelfeil
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
AI summary
Embedding API
A high-throughput, low-latency API for serving text and multimodal embeddings from various models.
- stars
- 1.6K
- forks
- 119
- watching
- 18
- awesome lists
- 2
Similar projects
Found by comparing what the projects do, not just their names.
Data retrieval API
An API to connect LLMs with vector databases for search and retrieval of data.
Vector embedding utility
A fast and efficient utility package for utilizing vector embeddings in machine learning models
ML server framework
A FastAPI-based framework for serving machine learning models in production-ready applications
Fediverse client
An API client library for interacting with multiple Fediverse platforms using a single interface.
Data API
Makes SimFin data easily accessible in R by wrapping the SimFin Web-API
Feed embedder
A client-side library for embedding Mastodon feeds into web pages without requiring a backend server
API client
A Python package providing an interface to interact with Lemmy API instances
API builder
A framework to build auto-documented REST APIs with Flask and marshmallow
rejeep/f.el686
File API
A modern API for working with files and directories in Emacs.
API framework
A data-driven micro web framework for building RESTful APIs in Haskell
Embeddings
Provides fast and efficient word embeddings for natural language processing.
API wrapper
A simple API wrapper that allows developers to easily interact with APIs by appending URL parts to the base endpoint.
Sentence embedder
An implementation of a non-parameterized approach for building sentence representations
Hierarchical embeddings
Implementation of Poincaré Embeddings algorithm in PyTorch for hierarchical representation learning
Graph API wrapper
Provides an interface to interact with Facebook's Graph API
Featured in 2 awesome lists
Each link jumps to the spot where the list mentions infinity.
