Results for “retrieval augmented generation”

…Discord Rethinking PDF Finetuning with RAG: A member proposed Retrieval Augmented Generation (RAG) as a smarter alternative to traditional JSONL finetuning for handling PDFs, claiming it can eliminate the finetuning step entirely.…

…insights on whether these trends are due to model design, retrieval-augmented generation (RAG), or simply resource scaling. Aeonmoru discusses observed performance drops in the o3 model at specific context window cutoffs (noting small dips …

…with long-term memory, manager/subagent structure, and PR generation; early users like Modal describe it as more useful than typical homegrown triage automations @cognition, @walden_yan, @russelljkaplan. The common pattern is less “chat…

…a webinar for Thursday at 9am PT, showcasing innovative uses of Retrieval-Augmented Generation (RAG) by the recent hackathon winners. The webinar reveals advanced knowledge synthesis and reasoning applications like ADU Planner and Counselor…

…commenter argues that smaller models specialized in search and retrieval augmented generation (RAG) will gain prominence due to their ability to rapidly access and utilize up-to-date information, contrasting with the rigidity of large…

…Glossary here.GitHub - jonfairbanks/local-rag: Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.: Ingest files for retrieval …

…Unsloth users celebrated a new article on using Unsloth for Retrieval Augmented Finetuning (RAFT) your LLM, complete with a full Llama32 1bn RAFT notebook. Tinygrad users benchmarked Qwen3 0.6B, hitting 92.92 TPS with BEAM=2 CUDA=1 on an…

…deployment positioning via @baseten. Agent Harnesses, Skill Retrieval, and RL Post-Training ToolingByteDance Seed’s HarnessDev reframes agent evaluation around the harness, not just task completion: @omarsar0 highlighted a new paper on…

…Graphs and RAG Microsoft Research open sourced GraphRAG, a retrieval augmented generation (RAG) technique that extracts knowledge graphs from sources and clusters them for improved LLM answers, though it increases token usage and inference …

…and a user shared an impressive Unsloth notebook for Retrieval Augmented Finetuning (RAFT) on Llama 3.2 1B (GitHub notebook). Users also troubleshooted a performance drop in unsloth/phi-4 after LoRA adapter merging, with a contributor…

…by Muse Spark, adding interruption, language switching, image generation, and live camera-grounded interaction. Embedding and retrieval model updates were notable: Jina released jina-embeddings-v5-omni, a universal embedding model for text,…

…from direct uploads vs. text input, with speculation that Retrieval Augmented Generation (RAG) is utilized—Claude may rely on other models like GPT-4-32k for file processing and referencing. Generative Capabilities & API Utilization: Users …