AI 知识库 | 文章列表

TDS

Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality

✅ completed ⭐ ★★★★★★ 2026-06-10

TDS

Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs

✅ completed ⭐ ★★★★★★ 2026-06-11

TDS

Why Decade-Old Residual Connections Still Power All of AI (And Why That’s a Problem)

✅ completed ⭐ ★★★★★★ 2026-06-12

TDS

When PyMuPDF Can’t See the Table: Parse PDFs for RAG with Azure Layout

✅ completed ⭐ ★★★★★★ 2026-06-12

TDS

Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload

✅ completed ⭐ ★★★★★★ 2026-06-13

TDS

Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG

✅ completed ⭐ ★★★★★★ 2026-06-14

TDS

The System Always Knows: Why Local Efficiency and System Performance Are Not the Same Problem

✅ completed ⭐ ★★★★★★ 2026-06-15

TDS

I Built 11 Models to Predict the 2026 World Cup. They Crown Four Different Champions.

✅ completed ⭐ ★★★★★★ 2026-06-15

TDS

The Protocol That Cleaned Up Our Agent Architecture

✅ completed ⭐ ★★★★★★ 2026-06-15

TDS

RAG Questions Need Parsing Too: Turn the User’s String Into Briefs for Retrieval and Generation

✅ completed ⭐ ★★★★★★ 2026-06-16

TDS

LLM Fallbacks Break Agent Pipelines — I Built the Missing Recovery Layer

✅ completed ⭐ ★★★★★★ 2026-06-16

TDS

Run a Local LLM with OpenClaw on Your Mac Mini

✅ completed ⭐ ★★★★★★ 2026-06-16

TDS

Your Churn Threshold Is a Pricing Decision

✅ completed ⭐ ★★★★★★ 2026-06-17

TDS

The Power and Pitfalls of Vector-Based Image Search

✅ completed ⭐ ★★★★★★ 2026-06-18

TDS

Dispatching the Parsed RAG Question: Chunk Strategy, Model Tier, Activations, Audit

✅ completed ⭐ ★★★★★★ 2026-06-18

TDS

Proteins: A Mosaic Pattern to Rule Them All?

✅ completed ⭐ ★★★★★★ 2026-06-18

TDS

GPU-Resident Top-K for Agentic RAG: I Built a CUDA Kernel So My Retrieval Step Would Stop Bouncing Off the GPU

✅ completed ⭐ ★★★★★★ 2026-06-19

TDS

Building a Custom GStreamer Plugin for NVIDIA DeepStream

✅ completed ⭐ ★★★★★★ 2026-06-19

VentureBeat

Writer Launches Ai Agents That Can Act Without Prompts Taking On Amazon Microsoft And Salesforce

✅ completed ⭐ ★★★★★★ 2026-06-23

VentureBeat

Claude Codes Goals Separates The Agent That Works From The One That Decides Its Done

✅ completed ⭐ ★★★★★★ 2026-06-23

📄 文章列表

Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality

Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs

Why Decade-Old Residual Connections Still Power All of AI (And Why That’s a Problem)

When PyMuPDF Can’t See the Table: Parse PDFs for RAG with Azure Layout

Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload

Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG

The System Always Knows: Why Local Efficiency and System Performance Are Not the Same Problem

I Built 11 Models to Predict the 2026 World Cup. They Crown Four Different Champions.

The Protocol That Cleaned Up Our Agent Architecture

RAG Questions Need Parsing Too: Turn the User’s String Into Briefs for Retrieval and Generation

LLM Fallbacks Break Agent Pipelines — I Built the Missing Recovery Layer

Run a Local LLM with OpenClaw on Your Mac Mini

Your Churn Threshold Is a Pricing Decision

The Power and Pitfalls of Vector-Based Image Search

Dispatching the Parsed RAG Question: Chunk Strategy, Model Tier, Activations, Audit

Proteins: A Mosaic Pattern to Rule Them All?

GPU-Resident Top-K for Agentic RAG: I Built a CUDA Kernel So My Retrieval Step Would Stop Bouncing Off the GPU

Building a Custom GStreamer Plugin for NVIDIA DeepStream

Writer Launches Ai Agents That Can Act Without Prompts Taking On Amazon Microsoft And Salesforce

Claude Codes Goals Separates The Agent That Works From The One That Decides Its Done