AI Knowledge Base

DeepSeek R1 has demonstrated strong inference capabilities in its first release. In this blog post, we share the details of using DeepSeek R1 to build Retrieval-Augmented Generatio...

This diagram clearly depicts the architectural blueprint for a modern, sophisticated Question Answering (QA) or Retrieval-Augmented Generation (RAG) system. It ...

In recent years, Artificial Intelligence (AI) technologies have sparked a profound change in the programming field. From v0 and bolt.new to programming tools that integrate Agent technology, such as Cursor and Windsurf, AI Coding has demonstrated a significant role in the development of software...

在日新月异的翻译技术浪潮中，ChatGPT (Chat Generative Pre-trained Transformer) 的横空出世无疑吸引了全球目光。作为一种先进的 大语言模型 (Large ...

Understanding the three key concepts of MCP Server, Function Call, and Agent is essential in the burgeoning field of Artificial Intelligence (AI), especially Large Language Modeling (LLM). They are the cornerstones of AI systems...

Abstract Well-designed prompts are essential to enhance the reasoning capabilities of large language models (LLMs) while aligning their outputs with the task requirements of different domains. However, manually designing hints requires expertise and iterative experimentation. Existing hint optimization methods aim to automate this process, but they are strictly ...

Recently, Anthropic has introduced a new tool called "think", which is designed to enhance the capabilities of the Claude model for complex problem solving. In this paper, we will delve into the design philosophy of the "think" tool, its performance, and the practical application of the most...

技术核心：Retrieval Interleaved Generation (RIG) 什么是 RIG？ RIG 是一种创新的生成方法，旨在解决大语言模型在处理统计数据时的“幻觉”（hallucina...

Gemma 3 Key Information Summary I. Key Metrics Parameters Details Model size 100 million to 27 billion parameters in four versions: 1B, 4B, 12B, 27B Architecture Transformer-based decoder-specific architecture inherited from Gem...

Large Language Models (LLMs) are evolving rapidly, and their reasoning ability has become a key indicator of their intelligence level. In particular, models with long reasoning capabilities, such as OpenAI's o1, DeepSeek-R1, QwQ-32B, and Kimi K1.5 ...

INTRODUCTION In recent years, Large Language Models (LLMs) have made impressive progress in the field of Artificial Intelligence (AI), and their powerful language comprehension and generation capabilities have led to a wide range of applications in several domains. However, LLMs still face many challenges when dealing with complex tasks that require invoking external tools...

By Krish Maniar and William Fu-Hinthorn When writing cue words, we try to communicate our intentions to Large Language Models (LLMs) so that they can apply these instructions on complex data. However, clearly expressing all the fine details at once...

In this paper, we present a summary report of Kapa.ai's recent exploration of inference models such as OpenAI's o3-mini in the Retrieval-Augmented Generation (RAG) system...

Background A recent article titled Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learnin...

The purpose of this paper is to explain in detail the basic concepts, overall process, and key techniques of Embedding fine-tuning from multiple perspectives, and to explore its practical utility in the legal domain. Through this paper, readers will understand how to utilize specialized data in the legal domain to pre-trained Embedding models for ...

Large Language Models (LLMs) like Claude are not created by humans writing program code; they are trained on massive amounts of data. In the process, the models learn their own problem-solving strategies. These strategies are hidden in the billions of times the model generates each word...

Abstract Information retrieval systems are critical for efficient access to large document collections. Recent approaches utilize Large Language Models (LLMs) to improve retrieval performance through query augmentation, but typically rely on expensive supervised learning or distillation techniques that require significant computational resources and manually labeled data ...

The GraphRAG project aims to extend the range of questions that AI systems can answer on private datasets by exploiting implicit relationships in unstructured text. A key advantage of GraphRAG over traditional vector RAG (or "semantic search") is its ability to answer questions about...

INTRODUCTION In recent years, multi-intelligent systems (MAS) have attracted much attention in the field of artificial intelligence. These systems attempt to solve complex, multi-step tasks through the collaboration of multiple Large Language Model (LLM) intelligences. However, despite the high expectations of MAS, their performance in practical applications...