Recent
A Survey of Open Source DeepResearch Implementation Solutions
·4647 words·22 mins
DeepResearch
DeepSearch
Agent
LLM
Dify
LangChain
HuggingFace
Zilliz
Intelligent Agents
Large Language Model Applications
Analyzing open source DeepResearch implementations based on source code, including the engineering architecture, Agent design, prompts, and core processes of solutions such as Dify, LangChain, HuggingFace, and Zilliz Cloud.
A Brief Look at Chain of Thought and Reinforcement Learning in DeepSeek-R1 and Kimi k1.5 Papers
·1302 words·7 mins
AI
LLM
CoT
Reinforcement Learning
DeepSeek
Kimi
Model Distillation
Chain of Thought
A brief overview of the technical features in reasoning capabilities of DeepSeek-R1 and Kimi k1.5: DeepSeek employs GRPO algorithm and model distillation to enhance reasoning performance, while Kimi explores the integration of long-form Chain of Thought with reinforcement learning.
Building a LightRAG Knowledge Base with TiDB Vector
·1445 words·7 mins
RAG
LLM
AI
TiDB
Engineering Practice
After reviewing LightRAG, I found that its persistence support was still limited, missing the most important TiDB (not really). So I took some time to contribute and write about it.
From paper to source code: a detailed explanation of the RAG algorithm
·9743 words·46 mins
RAG
LLM
AI
This article aims to explore the architectural design and specific code implementation of the RAG algorithm through the interpretation of papers and source code. This article mainly discusses GraphRAG, LightRAG and RAPTOR RAG, and also mentions Contextual Retrieval proposed by Anthropic and the evaluation method of the RAG algorithm. In the end, it is recommended that different methods be selected according to the size of the knowledge base document.
Rerank Models
·2502 words·12 mins
search
AI
RAG
With the popularity of the Transformer architecture, many Embedding and Rerank models are now based on this architecture. Taking this opportunity, we will sort out the process and history of the research, and take stock of the architectures adopted by several well-known Rerank models and the companies that developed them. Finally, we will return to the topic and briefly discuss whether Rerank should be used in RAG scenarios.
HTTP/2 and CONTINUATION Flood
·2348 words·12 mins
network
security vulnerability
HTTP/2
This article mainly introduces the HTTP/2 protocol and its CONTINUATION Flood problem. The article shows how to parse the Frame structure in Http2-related code through the golang.org/x/net source code, and analyzes in detail the three security risks of the CONTINUATION Flood attack and the corresponding solutions.
Mixed Expert (MoE) Model Notes
·1388 words·7 mins
MoE
Large Model
AI
Paper Reading
This article mainly sorts out the relevant concepts of the hybrid expert model (MoE), and introduces the architectures and optimization methods of several open source MoE models, such as GShard, Switch Transformers, DeepSeek-MoE, and LLaMA-MoE. The characteristics and optimization methods of these models are also introduced.
Vector similarity search methods
·3244 words·7 mins
Search algorithm
RAG
Vector database
This paper provides a detailed introduction to various vector similarity search methods, such as KD trees, IVF inverted indexes, HNSW and LSH. It provides a detailed introduction from data structures to algorithm implementations by analyzing the specific implementations in the source codes of Annoy, Faiss, PGVector and FALCONN.
Java & Go thread model comparison
·5397 words·11 mins
Java language
Go language
thread management
source code analysis
This paper compares in detail the threading models and scheduling mechanisms of the Java and Go programming languages. It analyzes their specific implementations and design ideas from a source code perspective, especially the 1:1 correspondence between Java’s Thread and operating system threads, and the n:m relationship between Go’s goroutine managed through the GPM model.