PrivateGPT: A private and offline project using Large Language Models for document-based queries, featuring a FastAPI-based API with high-level and low-level functionalities for document ingestion, chat, completions, and contextual chunks retrieval. Includes RAG pipeline and extensive documentation for installation, configuration, usage, and deployment, with a GitHub repository for contributions and citation information.
Read More
Perplexity AI is a conversational search engine that uses natural language predictive text to provide answers sourced from the web, including embedded links for reference.
Read More
Discover how StreamingLLM revolutionizes language modeling by enabling LLMs to generalize to infinite sequence length without fine-tuning, outperforming sliding window recomputation by up to 22.2x speedup. Optimize models like Llama-2, MPT, Falcon, and Pythia for stable and efficient performance with up to 4 million tokens using StreamingLLM, enhanced by a placeholder token for improved streaming deployment.
Read More