mastodontech.de ist einer von vielen unabhängigen Mastodon-Servern, mit dem du dich im Fediverse beteiligen kannst.
Offen für alle (über 16) und bereitgestellt von Markus'Blog

Serverstatistik:

1,5 Tsd.
aktive Profile

#rag

7 Beiträge7 Beteiligte0 Beiträge heute

🗣️ Kicking off in about 45 min at 5pm AZ time (MST/PDT)! I’ll be giving a talk on “The Future of Information Retrieval: A Deep Dive into RAG” with the .NET Virtual User Group and others. If you’re curious about how retrieval-augmented generation is reshaping search, swing by: meetup.com/dotnet-virtual-user

MeetupThe Future of Information Retrieval: A Deep-Dive into RAG | Southeast Valley, Thu, Jul 10, 2025, 5:00 PM | MeetupRetrieval Augmented Generation (RAG) may be the most important new software technology for business applications in a generation. RAG is revolutionizing the way we approach

CopilotKit é um ‘framework’ open‑source em TypeScript para criar copilotos de IA em minutos. Oferece:

• Abstrações genéricas para LLMs e adaptadores para OpenAI, Anthropic, Azure, etc.
• Pipeline de RAG com gestão automático de contexto.
• Suporte a CoAgents paralelos e orquestração de fluxos conversacionais.
• Módulos de UI generativa e hooks para React/Vue.

📎docs.copilotkit.ai/

#AI#TypeScript#RAG

#ContextEngineering - Unlocking #AgenticAI’s True Potential

> Today's #LLMs are far more complex with context size of millions of tokens and the ability for calling external systems, tools, and even #agentic orchestration with multi-agent #AI systems. #Context has therefore evolved beyond the prompt to include System Prompt, User Input/Prompt, Memory, Retrieved Information (#RAG etc.), information on tools (#MCP), responses from tools, and structured output format

deepgains.substack.com/p/conte

Deep Gains · Context Engineering - Unlocking Agentic AI’s True PotentialVon Arun S

🌘 AI 評估常見問題 (與解答) – Hamel 的部落格
➤ 解開 AI 評估的疑難雜症
hamel.dev/blog/posts/evals-faq/
這篇文章整理了作者在 AI 評估課程中,來自 700 多位工程師和產品經理的常見問題。文章涵蓋了 RAG 的應用、模型選擇、評估工具、評估指標以及錯誤分析的重要性等議題,並強調了針對特定應用場景建立客製化評估工具的重要性。作者建議以二元評估(通過/失敗)取代傳統的 1-5 分評分,並強調理解失敗模式和有效上下文獲取是提升 LLM 應用效能的關鍵。
+ 內容非常實用,讓我對 AI 評估有了更清晰的認識。客製化評估工具的建議尤其有價值。
+ 文章深入淺出,解釋了 RAG 的本質,並指出了許多常見的誤解。對於正在開發 AI 應用的工程師來說,是一篇必讀的文章。
#人工智慧 #評估 #LLM #RAG

Hamel's BlogFrequently Asked Questions (And Answers) About AI Evals – Hamel’s BlogFAQ from our course on AI Evals.

"As frontier model context windows continue to grow, with many supporting up to 1 million tokens, I see many excited discussions about how long context windows will unlock the agents of our dreams. After all, with a large enough window, you can simply throw everything into a prompt you might need – tools, documents, instructions, and more – and let the model take care of the rest.

Long contexts kneecapped RAG enthusiasm (no need to find the best doc when you can fit it all in the prompt!), enabled MCP hype (connect to every tool and models can do any job!), and fueled enthusiasm for agents.

But in reality, longer contexts do not generate better responses. Overloading your context can cause your agents and applications to fail in suprising ways. Contexts can become poisoned, distracting, confusing, or conflicting. This is especially problematic for agents, which rely on context to gather information, synthesize findings, and coordinate actions.

Let’s run through the ways contexts can get out of hand, then review methods to mitigate or entirely avoid context fails."

dbreunig.com/2025/06/22/how-co

Drew Breunig · How Long Contexts FailTaking care of your context is the key to building successful agents. Just because there’s a 1 million token context window doesn’t mean you should fill it.