Skip To Main Content
Import Faiss on Muck Rack

Import Faiss

As seen in: DEV Community, DZone, CSDN, Blogarama
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Import Faiss’s profile

Articles by Import Faiss

25 Best AI Project Ideas for Students with Source Code: Beginner to Advanced (2026)

|
By Import Faiss
| Blogarama
Last Updated on August 2, 2026 by Triumphoid Team The best AI projects for students in 2026 are projects that combine a real problem, measurable results, clean source code and a working demo. Beginners should start with spam detection, sentiment analysis or house-price prediction. Intermediate students can build object detection, resume parsing or text summarisation tools. Advanced students should consider RAG systems, AI agents, MCP assistants, multimodal applications and LLM fine-tuning.
Open in Who Shared Issue with article?

Welcome EmbeddingGemma, Google's new efficient embedding model

|
By Import Faiss, Sentence TransformerModel CardData, Sentence TransformersTextEmbedder, Query Embedders
| huggingface.co
Loss Function from sentence_transformers.losses import CachedMultipleNegativesRankingLoss loss = CachedMultipleNegativesRankingLoss(model, mini_batch_size=8) This code defines the loss function for training, using . CMNRL is effective for retrieval tasks, as it uses in-batch negatives to efficiently train the model to distinguish between correct and incorrect pairs.
Open in Who Shared Issue with article?

How I Built a Custom AI Document Assistant That Understands 1000s of PDFs and Talks Like a Human

|
By Import Faiss
The Real Problem: Why Traditional Search Fails for Technical Docs Ever tried finding a specific piece of info from 500+ PDFs? Even with filenames like Report_Final_v2_NEW_Latest.pdf, good luck. Search tools don't understand content. They match keywords.
Open in Who Shared Issue with article?

Model Context Protocol (MCP) Tutorial

|
By Import Openai, Import Faiss
| DEV Community
Model Context Protocol (MCP) is actually a concept that is a few months old, but getting so hot nowadays as AI development evolves day by day. Let me look at what is Model Context Protocol (MCP) and deep dive into Model Context Protocol (MCP) with tutorial with implementation code examples.
Open in Who Shared Issue with article?

Building A Generative AI Platform: A Deep Dive into Architecture and Implementation

|
By Import Faiss
| DEV Community
As a developer in the AI space, understanding the architecture of generative AI platforms is crucial. These systems are at the forefront of modern AI applications, capable of producing human-like text, images, and more. In this article, we'll explore the technical aspects of building such a platform, focusing on the key components and their implementation.
Open in Who Shared Issue with article?

Enhancing Query Performance With AI

|
By Import Faiss
| DZone Verified
In today's data-driven world, conventional search approaches frequently struggle with intricate queries and delivering pertinent results. The advent of AI-powered vector search presents a game-changing query efficiency and precision advancement. Azure Cosmos DB for PostgreSQL emerges as a robust platform that embraces AI-driven vector search, empowering users to elevate their query capabilities significantly.
Open in Who Shared Issue with article?

向量数据库：faiss的常用三种数据索引方式（IndexFlatL2，IndexIVFFlat，IndexIVFPQ）的使用和持久化+索引融合的实现及库函数解读_faiss.indexflatl2-CSDN博客

|
By Import Faiss, Tempfilename filename
| CSDN
常用的三种索引方式 Faiss 中有常用的三种索引方式：IndexFlatL2、IndexIVFFlat 和 IndexIVFPQ。 使用欧氏距离（L2）进行精确检索。 适用于较小规模的数据集，采用暴力检索的方式，即计算查询向量与所有数据库向量之间的距离，然后返回相似度最高的前 k 个向量。 import faiss d = 200 index = faiss.IndexFlatL2(d) data = ... index.add(data) k = 500 query = ...
Open in Who Shared Issue with article?

大规模向量检索库Faiss学习总结记录_Together_CZ的博客-CSDN博客

|
By Import Faiss
| CSDN
因为最近要使用到faiss来做检索和查询，所以这里只好抽出点时间来学习下，本文主要是自己最近学习的记录，来源于网络资料查询总结，仅用作个人学习总结记录。 Faiss的全称是Facebook AI Similarity Search，是FaceBook的AI团队针对大规模相似度检索问题开发的一个工具，使用C++编写，有python接口，对10亿量级的索引可以做到毫秒级检索的性能。 简单来说，Faiss的工作，就是把我们自己的候选向量集封装成一个index数据库，它可以加速我们检索相似向量TopK的过程，其中有些索引还支持GPU构建，可谓是强上加强。 faiss官方项目地址在这里，如下所示： 安装的话有cpu和gpu两个版本，根据自己需要选择即可，我直接使用的是cpu版本的： pip install faiss-cpu==1.7.3 faiss整体流程图如下所示： Faiss检索相似向量TopK的工程基本都能分为三步： 1、得到向量库； 2、用faiss 构建index，并将向量添加到index中； 3、用faiss index 检索。...
Open in Who Shared Issue with article?

Best Practices For Faiss With Langchain

|
By Import Faiss
| restack.io
Explore effective strategies for integrating FAISS with LangChain to enhance AI customization and performance. The framework for autonomous intelligence To effectively set up FAISS (Facebook AI Similarity Search) with Langchain, it is essential to follow a structured approach that ensures optimal performance and usability.
Open in Who Shared Issue with article?

Explore Facebook's Open-Source AI Tools

|
By Import Faiss
| restack.io
Discover Facebook's GitHub projects for DIY AI tools designed for non-programmers, enhancing accessibility and innovation. The framework for autonomous intelligence Facebook has made significant strides in the realm of open-source projects, contributing to a variety of tools and frameworks that empower developers and enhance the overall tech ecosystem. By exploring Facebook's open-source GitHub projects, developers can access a wealth of resources that facilitate innovation and collaboration.
Open in Who Shared Issue with article?

Build Semantic Search Engine with AI

|
By Import Faiss
| restack.io
Learn to create a semantic search engine using transformers and FAISS for enhanced information retrieval. The framework for autonomous intelligence SentenceTransformers is a powerful Python framework designed for generating state-of-the-art embeddings for sentences, texts, and images. This framework provides access to numerous pre-trained models available on the Hugging Face Hub, making it easier for developers to implement semantic search capabilities in their applications.
Open in Who Shared Issue with article?
Show More