Latest Open Source Projects
potpie
VITA
VITA
TLDR: VITA-1.5 is an open-source interactive multimodal LLM. It features reduced interaction latency, enhanced multimodal performance, improved speech processing, and a progressive training strategy. It outperforms on various benchmarks and can be trained and used for inference.
story-adapter
story-adapter
TLDR: This repository contains the official implementation of 'Story-Adapter', a training-free and computationally efficient framework for long story visualization. It uses an iterative paradigm and a global reference cross-attention module to enhance the generative capability of long stories.
multi-agent-orchestrator
multi-agent-orchestrator
TLDR: The multi-agent-orchestrator is an open-source framework for orchestrating multiple AI agents to handle complex conversations. It features intelligent intent classification, dual language support, flexible agent responses, context management, extensible architecture, and universal deployment. It comes with pre-built agents and classifiers and offers a variety of examples and quick start guides.
aisuite
aisuite
TLDR: A Python package called aisuite provides a simple, unified interface to multiple Generative AI providers. It allows developers to use multiple LLM through a standardized interface similar to OpenAI's, enabling easy interaction and comparison of results. Currently supports various providers and offers installation options. Comes with an MIT license and welcomes contributions.
RAG
RAG
TLDR: An implementation of the paper 'Searching for Best Practices in Retrieval-Augmented Generation'. Provides installation instructions and a way to run evaluations. If used, requires citing the associated paper.
oumi
oumi
TLDR: Everything you need to build state-of-the-art foundation models, end-to-end.
awesome-llm-apps
awesome-llm-apps
TLDR: A curated collection of LLM apps built with RAG and AI agents. Features apps using models from various sources and includes projects in different domains. Also provides instructions for getting started and welcomes contributions.
RD-Agent
RD-Agent
TLDR: Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through our open source R&D automation tool RD-Agent, which lets AI drive data-driven AI.
kotaemon
kotaemon
TLDR: An open-source clean & customizable RAG UI for chatting with documents. Serves end users for QA on their documents and developers for building RAG pipelines. Features include clean UI, support for various LLMs, customizable UI for developers, and more.