BestHub
Sign in
Tagged articles
35 articles
Page 1 of 1
AI Architect Hub
AI Architect Hub
May 3, 2026 · Artificial Intelligence

Choosing the Right Vector Database: Milvus, Chroma, Weaviate, Qdrant, FAISS Compared

This article compares five popular vector databases—Chroma, Milvus, Weaviate, Qdrant, and FAISS—detailing their positions, strengths, weaknesses, suitable scenarios, a selection‑dimension matrix, common pitfalls, code implementations for a unified RAG pipeline, best‑practice recommendations, and thought questions to guide engineers in choosing and migrating vector stores.

ChromaFAISSMilvus
0 likes · 23 min read
Choosing the Right Vector Database: Milvus, Chroma, Weaviate, Qdrant, FAISS Compared
AI Architect Hub
AI Architect Hub
Apr 27, 2026 · Artificial Intelligence

Why HNSW Can Speed Up Search 50× Compared to Brute‑Force? A Hands‑On Guide to Building Vector Indexes

The article explains why brute‑force vector search is painfully slow, introduces Flat, IVF, and HNSW index structures, compares their speed, memory and accuracy, shows common pitfalls, provides production‑grade Python code, and presents benchmark results that demonstrate HNSW’s superior speed‑accuracy trade‑off.

AIFAISSHNSW
0 likes · 12 min read
Why HNSW Can Speed Up Search 50× Compared to Brute‑Force? A Hands‑On Guide to Building Vector Indexes
Data STUDIO
Data STUDIO
Apr 2, 2026 · Artificial Intelligence

Building a Dual‑Stack Memory Agent: Situational + Semantic Memory for Long‑Term AI Understanding

This tutorial walks through designing and implementing a dual‑stack memory architecture for AI agents—combining episodic vector‑based situational memory with graph‑based semantic memory—using LangChain, FAISS, and Neo4j, and demonstrates a complete end‑to‑end workflow with code examples.

Agent MemoryFAISSKnowledge Graph
0 likes · 14 min read
Building a Dual‑Stack Memory Agent: Situational + Semantic Memory for Long‑Term AI Understanding
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Mar 26, 2026 · Artificial Intelligence

How to Build a Full‑Stack RAG Chatbot Using LangChain, FAISS & Langfuse

This guide walks through an end‑to‑end RAG implementation with LangChain, covering multi‑format document loading, recursive text splitting, embedding selection, FAISS vector storage, ConversationalRetrievalChain setup, prompt engineering, source citation, Langfuse observability, and best‑practice configuration management.

FAISSLLMOpsLangChain
0 likes · 13 min read
How to Build a Full‑Stack RAG Chatbot Using LangChain, FAISS & Langfuse
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 26, 2026 · Artificial Intelligence

Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains

This article explains why combining BM25 with dense vector search using Reciprocal Rank Fusion (RRF) improves recall for both exact‑term and semantic queries in a financial‑insurance document corpus, details the underlying algorithms, parameter choices such as k=60, provides Python implementations, and shows measurable performance gains in production.

BM25FAISSHybrid Retrieval
0 likes · 28 min read
Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains
DeepHub IMBA
DeepHub IMBA
Mar 18, 2026 · Artificial Intelligence

CRAG Architecture Explained: Fixing Erroneous Retrieval Results Before the Generator

The article analyzes how most RAG pipelines blindly feed retrieved documents to LLMs, introduces CRAG's lightweight evaluator with confidence thresholds, describes its sentence‑level decomposition, filtering, and dual‑knowledge routing, and provides a full implementation walkthrough with a real insurance query example.

CRAGFAISSLLM
0 likes · 13 min read
CRAG Architecture Explained: Fixing Erroneous Retrieval Results Before the Generator
AI Tech Publishing
AI Tech Publishing
Feb 19, 2026 · Artificial Intelligence

Add Long-Term Memory to Your Agent with Lightweight RAG (Lesson 5)

This tutorial shows how to equip an AI agent with long‑term memory using Retrieval‑Augmented Generation (RAG), covering the concepts of vector embeddings, FAISS indexing, building and querying a knowledge base, and providing complete Python code examples.

AgentEmbeddingFAISS
0 likes · 13 min read
Add Long-Term Memory to Your Agent with Lightweight RAG (Lesson 5)
BirdNest Tech Talk
BirdNest Tech Talk
Oct 27, 2025 · Artificial Intelligence

How LangChain’s Indexing API Enables Efficient Incremental Updates for RAG Systems

This article explains how LangChain's Indexing API adds state management and synchronization to the classic load‑split‑embed‑store RAG pipeline, detailing the RecordManager component, the index function workflow, key parameters, implementation considerations, and best‑practice code examples for production‑grade vector stores.

FAISSIndexing APILangChain
0 likes · 12 min read
How LangChain’s Indexing API Enables Efficient Incremental Updates for RAG Systems
BirdNest Tech Talk
BirdNest Tech Talk
Oct 21, 2025 · Artificial Intelligence

How Vector Stores Enable Lightning‑Fast Semantic Search in LangChain

This article explains what vector stores are, outlines their core workflow of adding, querying, and searching embeddings, compares popular back‑ends like FAISS, Chroma, and Pinecone, and walks through a complete Chinese‑language example using LangChain’s FAISS integration with detailed code and result analysis.

AIFAISSLangChain
0 likes · 10 min read
How Vector Stores Enable Lightning‑Fast Semantic Search in LangChain
Fun with Large Models
Fun with Large Models
Aug 22, 2025 · Artificial Intelligence

Step‑by‑Step Guide: Building a PDF‑Based RAG Knowledge Base with LangChain, Streamlit, DashScope & DeepSeek

This tutorial shows how to create a lightweight Retrieval‑Augmented Generation (RAG) system that indexes multiple PDF files, stores their embeddings in a FAISS vector database, and answers user queries through a LangChain agent powered by DashScope embeddings and the DeepSeek‑Chat model, all wrapped in a Streamlit UI.

DashscopeDeepSeekFAISS
0 likes · 13 min read
Step‑by‑Step Guide: Building a PDF‑Based RAG Knowledge Base with LangChain, Streamlit, DashScope & DeepSeek
DevOps
DevOps
Apr 20, 2025 · Artificial Intelligence

Building a Medical Knowledge Base with RAG: A Step‑by‑Step Example

This article demonstrates how to construct an AI‑powered medical knowledge base for diabetes treatment by preprocessing literature, performing semantic chunking, generating BioBERT embeddings, storing them in a FAISS vector database, and using a RAG framework together with a knowledge graph to retrieve and generate accurate answers.

BioBERTFAISSKnowledge Graph
0 likes · 12 min read
Building a Medical Knowledge Base with RAG: A Step‑by‑Step Example
AI Algorithm Path
AI Algorithm Path
Feb 13, 2025 · Artificial Intelligence

How to Build a Local RAG Knowledge Base with DeepSeek‑R1 and Ollama

This article walks through setting up a local Retrieval‑Augmented Generation (RAG) system using the open‑source DeepSeek‑R1 model run via Ollama, covering installation, model selection, PDF ingestion with LangChain, semantic chunking, FAISS vector store creation, RetrievalQA chain construction, and a Streamlit UI for querying.

DeepSeek-R1FAISSLangChain
0 likes · 8 min read
How to Build a Local RAG Knowledge Base with DeepSeek‑R1 and Ollama
DataFunSummit
DataFunSummit
Apr 15, 2024 · Artificial Intelligence

Deep Learning Practices for Internet Real‑Estate Recommendation at 58.com

This article details the end‑to‑end deep‑learning pipeline used by 58.com for real‑estate recommendation, covering business background, a six‑layer architecture, vector‑based recall, various embedding and ranking models, multi‑task and multi‑scenario optimization techniques, and future directions for large‑model integration.

Deep LearningFAISSmulti-task learning
0 likes · 19 min read
Deep Learning Practices for Internet Real‑Estate Recommendation at 58.com
Architect
Architect
Aug 17, 2023 · Backend Development

Design and Implementation of Bilibili's New Customer Service System

This article details Bilibili's transition from a purchased customer‑service platform to a self‑developed system, describing the background, architectural design, core modules such as intelligent QA, seat scheduling, workbench, permission management, the use of Faiss for vector search, and future explorations with large language models, highlighting the technical challenges and solutions across backend development and AI integration.

AIBackendFAISS
0 likes · 22 min read
Design and Implementation of Bilibili's New Customer Service System
Zhuanzhuan Tech
Zhuanzhuan Tech
Sep 21, 2022 · Artificial Intelligence

Vector Retrieval and Product Quantization with Faiss

This article explains the challenges of large‑scale vector retrieval, compares Faiss index types such as brute‑force, graph‑based and product quantization, and details how product quantization works, its memory‑speed trade‑offs, hierarchical quantization, and practical hyper‑parameter tuning.

ANNEmbeddingFAISS
0 likes · 9 min read
Vector Retrieval and Product Quantization with Faiss
Alimama Tech
Alimama Tech
Aug 24, 2022 · Artificial Intelligence

Distributed High‑Performance Vector Retrieval with gpdb‑faiss‑vector Plugin on Dolphin Engine

The gpdb‑faiss‑vector plugin embeds Facebook’s Faiss library into the Dolphin (Greenplum‑compatible) engine, exposing SQL functions for distributed, high‑performance approximate nearest‑neighbor vector retrieval with caching, parallel search, configurable indexes, and sub‑millisecond latency, enabling scalable recommendation and advertising workloads.

AIFAISSSQL
0 likes · 15 min read
Distributed High‑Performance Vector Retrieval with gpdb‑faiss‑vector Plugin on Dolphin Engine
DeWu Technology
DeWu Technology
Jul 27, 2022 · Artificial Intelligence

Overview of Nearest Neighbor Search Algorithms

The article reviews how high‑dimensional vector representations in deep‑learning applications require efficient approximate nearest‑neighbor search, comparing K‑d trees, hierarchical k‑means trees, locality‑sensitive hashing, product quantization, and HNSW graphs, and discusses practical FAISS implementations and how algorithm choice depends on data size, recall, latency, and resources.

FAISSHNSWKD-Tree
0 likes · 8 min read
Overview of Nearest Neighbor Search Algorithms
ITPUB
ITPUB
Jul 16, 2022 · Artificial Intelligence

How Huya Live Uses Vector Search and Fine‑Ranking to Power Real‑Time Recommendations

This article explains Huya Live's recommendation architecture, covering business background, system design, vector retrieval challenges and solutions with ScaNN, and the fine‑ranking pipeline, while highlighting performance optimizations, scalability, and future directions for their live‑streaming platform.

FAISSHuya LiveScaNN
0 likes · 11 min read
How Huya Live Uses Vector Search and Fine‑Ranking to Power Real‑Time Recommendations
Laiye Technology Team
Laiye Technology Team
Apr 29, 2022 · Artificial Intelligence

Using Faiss for Efficient Vector Similarity Search: Installation, Index Construction, and Performance Optimization

This tutorial explains what Faiss is, how to install it, construct various indexes such as IndexFlatL2, IndexIVFFlat, and IndexIVFPQ, and demonstrates code examples for building and querying vector similarity search pipelines while discussing speed‑accuracy trade‑offs.

AIFAISSapproximate nearest neighbor
0 likes · 11 min read
Using Faiss for Efficient Vector Similarity Search: Installation, Index Construction, and Performance Optimization
Kuaishou Tech
Kuaishou Tech
Dec 10, 2021 · Artificial Intelligence

Kuaishou and Tsinghua University Win NeurIPS'21 Billion-Scale ANN Challenge with FAISS‑Optimized KST_ANN Solution

On December 6, Kuaishou and Tsinghua University’s joint team secured first place in the NeurIPS'21 Billion‑Scale Approximate Nearest Neighbor Search Challenge by leveraging a FAISS‑optimized, memory‑efficient KST_ANN algorithm that achieved over 6% higher recall on multiple billion‑scale datasets, showcasing the practical impact of large‑scale vector retrieval in AI‑driven services.

AIANNFAISS
0 likes · 5 min read
Kuaishou and Tsinghua University Win NeurIPS'21 Billion-Scale ANN Challenge with FAISS‑Optimized KST_ANN Solution
DataFunTalk
DataFunTalk
Sep 19, 2021 · Artificial Intelligence

Second‑hand Housing Recommendation System: Business Background, Vector Recall, Multi‑objective Optimization and Future Plans

This article presents the end‑to‑end practice of a second‑hand housing recommendation system at 58.com and Anjuke, covering business background, embedding‑based vector recall, multi‑objective ranking methods such as ESMM and MMOE, experimental results, and future development directions.

ESMMEmbeddingFAISS
0 likes · 14 min read
Second‑hand Housing Recommendation System: Business Background, Vector Recall, Multi‑objective Optimization and Future Plans
58 Tech
58 Tech
Apr 9, 2021 · Artificial Intelligence

Vectorized Recall and Dual‑Tower Model for Home Page Recommendation at 58.com

This article details how 58.com improved its home‑page recommendation system by introducing vectorized recall with Word2Vec, optimizing negative sampling, deploying FAISS for fast nearest‑neighbor search, and later adopting a dual‑tower deep learning model with user interest features, achieving higher click‑through and conversion rates.

FAISSWord2Vecdual-tower
0 likes · 19 min read
Vectorized Recall and Dual‑Tower Model for Home Page Recommendation at 58.com
iQIYI Technical Product Team
iQIYI Technical Product Team
Apr 10, 2020 · Big Data

Video Copyright Detection Solution Using SE-ResNeXt and Faiss in the 2019 CCF Big Data & Computational Intelligence Competition

The iQiyi team “都挺好” tackled the 2019 CCF Video Copyright Detection contest by extracting frame‑level features with SE‑ResNeXt, indexing them with Faiss, aligning temporally via a critical‑path method, and refining copy boundaries using SIFT re‑matching and a sliding‑window approach, ultimately achieving an F1 score of 0.9678 after three iterative stages of model selection, cascade detection, and feature fusion.

CCF competitionFAISSSE-ResNeXt
0 likes · 6 min read
Video Copyright Detection Solution Using SE-ResNeXt and Faiss in the 2019 CCF Big Data & Computational Intelligence Competition
58 Tech
58 Tech
Mar 30, 2020 · Artificial Intelligence

Embedding Techniques for Advertising Recall and Ranking in a Second-Hand Car Platform

This article details the commercial strategy team's exploration of embedding technologies for a second‑hand car platform, covering mainstream embedding methods, their application in advertising recall and ranking pipelines, system architecture, model optimizations, evaluation results, and future directions.

AdvertisingDSSMDeep Learning
0 likes · 22 min read
Embedding Techniques for Advertising Recall and Ranking in a Second-Hand Car Platform
360 Quality & Efficiency
360 Quality & Efficiency
Aug 23, 2019 · Artificial Intelligence

High‑Performance High‑Dimensional Vector KNN Search Using FAISS

This article introduces the background of vector representations in machine learning, explains the K‑Nearest Neighbors algorithm and its key parameters, reviews traditional tree‑based and modern high‑performance search solutions, and demonstrates how FAISS can achieve microsecond‑level KNN queries on large‑scale high‑dimensional data.

FAISShigh-dimensionalkNN
0 likes · 5 min read
High‑Performance High‑Dimensional Vector KNN Search Using FAISS
vivo Internet Technology
vivo Internet Technology
Nov 16, 2018 · Artificial Intelligence

Efficient Vector Search with Deep Learning Embeddings in Elasticsearch

The article explains how to replace keyword matching with deep‑learning document embeddings in Elasticsearch by applying PCA dimensionality reduction, indexing vectors using Lucene’s KD‑tree structures via a custom plugin, and leveraging FAISS‑style nearest‑neighbour techniques to achieve fast, semantically aware similarity search.

Deep LearningElasticsearchFAISS
0 likes · 7 min read
Efficient Vector Search with Deep Learning Embeddings in Elasticsearch
Xianyu Technology
Xianyu Technology
Sep 7, 2018 · Artificial Intelligence

Video Deduplication on Xianyu Using High‑Dimensional Vector Retrieval

The Xianyu platform combats video plagiarism by extracting key frames, converting them into 1024‑dimensional vectors, and using product quantization‑based high‑dimensional vector retrieval to achieve over 95% recall with ~100 ms latency and more than 1000 QPS, enabling scalable video, image, and product deduplication.

FAISSPQVector Retrieval
0 likes · 12 min read
Video Deduplication on Xianyu Using High‑Dimensional Vector Retrieval