🤖 ai 应用 - inarcissuss

Discussed on Hacker News

🧠LLM Apps medium.com

Scaling RAG Applications in Production: Lessons Beyond the Demo

🌀Hallucination arXiv·

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems

💻Programming GitHub·

NangoHQ/nango

Covered by DEV Community, nango.dev

🧠LLM Apps medium.com

What Actually Makes a RAG System Work in Production?

🤖AI native medium.com

When Search Can See: Building Native Semantic Image Search in ODC

🔧Tool Use medium.com

LLM vs RAG vs MCP: The Missing Architecture Layers Every AI Engineer Must Understand

🧠LLM Apps medium.com

Never Lose the Right Chunk: How Hybrid Search Improves Recall in RAG Systems

🌀Hallucination medium.com

From Toy RAG to Production RAG: Hybrid Search, Reranking and Observability

⚙️AI Engineering medium.com

Securing AI workloads in the cloud

💭Context Management HubSpot Product Blog (Live)·

Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpot

Covers Qdrant - Vector Database

🧠LLM Reasoning Turing Post·

AI Agents in 2026: Local, Physical, Responsible AI

🧠LLM Apps ultimatesystemsdesign.medium.com·

The Memory Stack Every AI Agent Needs: Buffer, RAG, Entities, Episodes, and Forgetting

⚙️AI Engineering docs.vultr.com·

Deploying Qdrant Open-Source Vector Database for AI Applications on Ubuntu 24.04

Covers 2 stories including Qdrant - Vector Database

Discussed on DEV

🌀Hallucination GitHub·

johnzfitch/human-interface-markdown: Apple Human Interface Guidelines archive (1980-2014) - 35 documents optimized for LLM consumption and human explor...

Covers 2 stories including Home

🧠LLM Reasoning Machine Learning Mastery·

Building Browser-Using AI Agents in Python

Covers 3 stories including Sample Post Title

🧠LLM Apps SecurityWeek·

When Information Becomes the Attack Surface – Understanding AI Agent Traps

🧠LLM Apps aksharmaa.medium.com·

RAG Is Not Enough:

🧠LLM Reasoning medium.com

Building agentic AI applications with a modern data mesh strategy on AWS

Lamini: Build mini-agents with 90%+ accuracy

Scaling RAG Applications in Production: Lessons Beyond the Demo

Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems

NangoHQ/nango

What Actually Makes a RAG System Work in Production?

When Search Can See: Building Native Semantic Image Search in ODC

LLM vs RAG vs MCP: The Missing Architecture Layers Every AI Engineer Must Understand

Never Lose the Right Chunk: How Hybrid Search Improves Recall in RAG Systems

From Toy RAG to Production RAG: Hybrid Search, Reranking and Observability

Securing AI workloads in the cloud

Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpot

AI Agents in 2026: Local, Physical, Responsible AI

The Memory Stack Every AI Agent Needs: Buffer, RAG, Entities, Episodes, and Forgetting

Deploying Qdrant Open-Source Vector Database for AI Applications on Ubuntu 24.04

johnzfitch/human-interface-markdown: Apple Human Interface Guidelines archive (1980-2014) - 35 documents optimized for LLM consumption and human explor...

Building Browser-Using AI Agents in Python

When Information Becomes the Attack Surface – Understanding AI Agent Traps

RAG Is Not Enough:

Beyond the Spotlight: Why AI Agents Need both Keywords and Context to Fly!