Run serverless GPU workloads with fast cold starts on bare-metal servers, anywhere in the world

🏗️ Fine-tune, build, and deploy open-source LLMs easily!

A holistic way of understanding how Llama and its components run in practice, with code and detailed documentation.

[deprecated] AI Gateway - core infrastructure stack for building production-ready AI Applications

A diverse, simple, and secure all-in-one LLMOps platform

An AI assisted kubectl helper

Implement RAG (using LangChain and PostgreSQL) for Go applications to improve the accuracy and relevance of LLM outputs

Interactive Fiction in the Age of AI

Go package and example utilities for using Ollama / LLMs

AWS Go SDK examples for Amazon Bedrock

Inference Llama 2 in one file of pure go

Go framework for language model-powered applications with composability and chaining. Inspired by LangChain.

With an emphasis on pluggable architecture and platform flexibility, Thor is a highly modular chat engine integrated into Go.

🧠 Cache implementation for storing and retrieving results of language model (LLM) requests

This repository is a work in progress (WIP).

Vectoria is an embedded vector database.

LLM + temphia

A declarative DSL (domain-specific language) for IDD (Inference-Driven-Development) and testing on any codebase in any programming language

Onefile can both serialize and deserialize code, enabling the conversion of project files into a single text file and vice versa for seamless integration with LLM queries.

Open science package for LLM-powered semantic synthesis and precise extraction of information from unstructured texts.