Search Latent Space

Results for “retrieval augmented generation”

Articles, conversations, profiles, and grounded writeups.

?
Search tips

Keyword matches words; semantic matches meaning and exact titles or names; hybrid combines both. In keyword mode, use quotation marks for exact phrases. Author matches published credits. Year applies to posts; wiki entries have no author or publication year. You can also use author:"Ada" or type:podcast in non-regex searches.

Reset filters

Select Apply filters to update results.

445 results

not much happened today

…niche status and anticipated software hurdles. Theme 4. Scaling Retrieval-Augmented Generation (RAG) for Massive Datasets How to scale RAG to 20 million documents ? (Score: 137, Comments: 136): To scale RAG (Retrieval-Augmented Generation) …

AI News · 2025-02-11
AI News—2025-02-11
Perplexity starts Shopping for you

…mentioned: GitHub - microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system: A modular graph-based Retrieval-Augmented Generation (RAG) system - microsoft/graphrag LLM Agents (Berkeley MOOC) ▷…

AI News · 2024-11-20
AI News—2024-11-20
not much happened today

…GPUs. Users expressed interest in enhancing these models with retrieval-augmented generation (RAG) capabilities and tools for improved knowledge and reflection. The model's fine-tuning process was discussed, with llama-factory being used…

AI News · 2024-12-31
AI News—2024-12-31
Llama 3.1 Leaks: big bumps to 8B, minor bumps to 70b, and SOTA OSS 405b model

…changes from previous versions. 4. Knowledge Graphs and Retrieval-Augmented Generation (RAG) Triplex cuts KG costs by 98%: Triplex from SciPhi.AI cuts knowledge graph extraction costs by 98%, outperforming GPT-4 at 1/60th the price by using…

AI News · 2024-07-23
AI News—2024-07-23
Gemini launches context caching... or does it?

…AI, including Meta-Reasoning Prompting (MRP), improvements in retrieval-augmented generation with the ERASE methodology, and sparse communication topologies in multi-agent debates. These offer insights into optimizing computational costs…

AI News · 2024-06-18
AI News—2024-06-18
not much happened today

…in adopting persistent memory for deeper interactions. Recipe Generation Goes Both Ways: Discussion centered on top-down vs bottom-up approaches for building advanced recipes with minimal cost. The group weighed how retrieval modes and…

AI News · 2024-12-25
AI News—2024-12-25
OpenAI Realtime API and other Dev Day Goodies

…this a significant opportunity for engineers working with retrieval-augmented generation. Radical AI Founders Masterclass Kicks Off Soon: The Radical AI Founders Masterclass begins October 9, 2024, featuring sessions on transforming AI…

AI News · 2024-10-02
AI News—2024-10-02
Shall I compare thee to a Sonnet's day?

…(MoA) approach in just 50 lines of code. @togethercompute Retrieval Augmented Generation (RAG) Fine-Tuning RAG fine-tuning outperforms larger models: Fine-tuned Mistral 7B models using RAG match or beat larger models like GPT-4o & Claude 3 …

AI News · 2024-06-26
AI News—2024-06-26
LMSys advances Llama 3 eval analysis

…most recent advancements in generative modeling. Simplifying Retrieval-Augmented Generation: The GitHub repository bugthug404/simple_rag presents Simple Rag, a project aiding in the development of retrieval-augmented generation which can be…

AI News · 2024-05-10
AI News—2024-05-10
DeepSeek's Open Source Stack

…both, according to this response. Debate continues whether a Retrieval Augmented Generation (RAG) system could be considered an "environment" with which the LLM interacts. OpenRouter (Alex Atallah) Discord Perplexity API Exposes Copyright…

AI News · 2025-03-08
AI News—2025-03-08
DeepSeek #1 on US App Store, Nvidia stock tanks -17%

…RAG Tactics Spark Dev Conversations: Developers delve into retrieval-augmented generation methods, discussing vector stores and embeddings like voyage-code-3. Codebase Indexing: A Bare-Bones Approach?: Some users criticize codebase indexing…

AI News · 2025-01-28
AI News—2025-01-28
BitNet was a lie?

…Language Models and NLP tools through one easy-to-use API. Retrieval Augmented Generation (RAG) — Cohere: Generate text with external data and inline citations using Retrieval Augmented Generation and Cohere's Chat API. Cohere ▷…

AI News · 2024-11-13
AI News—2024-11-13
Your place in Latent Space

Join Latent Space.

Sign in with Google, or get the newsletter by email.

Loading Google sign-in…

or subscribe by email

Free. Change your preferences or unsubscribe any time.