Le module sur le reranking a complètement changé ma façon d'aborder mes pipelines RAG, je ne pensais pas que ça ferait une telle différence sur la pertinence des résultats. L'utilisation de LangChain pour combiner recherche hybride et réécriture de requêtes est expliquée de manière très concrète.
RAG with Python: Hybrid Search, Reranking, and Rewriting
Learn to build modern Retrieval-Augmented Generation applications using LangChain, vector databases, and intelligent search techniques from the ground up.
-
💬
AI instructor
Ask about any lesson and get a clear answer instantly, anytime. -
🕐
Start anytime
No schedules or deadlines — learn at your own pace, whenever suits you. -
🌐
In English
Lessons, tasks and certificate — all fully in your language.
About this course
Large language models are powerful, but they often lack access to your specific data. Retrieval-Augmented Generation (RAG) bridges this gap, allowing you to connect AI to custom knowledge bases. In this text-based course, you will explore how to build robust RAG systems using Python. Starting with fundamental concepts, you will progress to implementing modern techniques like hybrid search, result reranking, and query rewriting to drastically improve the accuracy of AI responses. What you will learn: Understand the core architecture and terminology of Retrieval-Augmented Generation; Build foundational RAG pipelines using Python and LangChain; Implement vector databases to store and retrieve document embeddings; Apply hybrid search techniques combining keyword and semantic retrieval; Improve AI accuracy using result reranking and query rewriting patterns; Explore modern Agentic AI concepts for autonomous data retrieval. The course begins with clear definitions of AI terminology before moving into practical Python implementations. You will read through detailed explanations, examine code snippets, and practice building text-based AI retrieval systems step by step. This course is designed for beginners and aspiring developers; no prior experience with advanced machine learning is required. Start reading today to unlock the power of modern RAG and build smarter data-driven applications.
What you'll get
-
📜
Certificate of completion
Add it to your LinkedIn profile -
💬
Personal AI tutor
Stuck on a lesson? Ask your built-in tutor anything, any time. -
🎧
Audio version included
Learn on the go — no screen needed -
♾️
Lifetime access
Come back anytime, no expiry -
📱
Phone or computer
Works anywhere, any device -
💸
14-day refund
No questions asked -
⚡
Short & focused
2h 30m of practical content
Reviews (6)
Selama ini saya cuma tahu RAG sebatas 'ambil dokumen terus masukin ke prompt', tapi kursus ini benar-benar membongkar detail yang sering dilewatkan seperti hybrid search dan reranking. Bagian yang paling membuka mata saya adalah query rewriting, ternyata banyak hasil pencarian yang buruk itu bukan karena embedding jelek tapi karena pertanyaan awal dari user memang ambigu. Contoh kode dengan LangChain dijelaskan langkah demi langkah sehingga saya bisa langsung praktik di proyek sendiri tanpa kebingungan. Urutan materinya juga masuk akal, dari retrieval sederhana sampai pipeline lengkap yang menggabungkan semua teknik. Setelah menyelesaikan kursus ini, hasil pencarian RAG saya jauh lebih relevan dibanding sebelumnya.
Давно искал внятное объяснение гибридного поиска, и здесь наконец сложилась картина: как совмещать плотные эмбеддинги с BM25 и зачем потом прогонять результаты через реранкер. Особенно зашёл блок про переписывание запроса перед обращением к векторной базе — раньше я недооценивал этот шаг, а он реально поднял качество выдачи в моём проекте на LangChain. Примеры рабочие, всё запускается без танцев с бубном. Единственное, по выбору самой векторной БД хотелось бы поглубже, но в целом курс закрыл почти все мои вопросы по RAG.
أخيرًا شرح واضح لكيفية دمج البحث الهجين وإعادة الترتيب في نظام RAG بدلاً من الاكتفاء بالاسترجاع البسيط. الجزء الخاص بإعادة صياغة الاستعلامات باستخدام LangChain كان عمليًا جدًا وساعدني في تحسين دقة النتائج بشكل ملموس.
Hibrit arama ve reranking konularını bu kadar net anlatan başka bir kaynak bulamamıştım. LangChain ile query rewriting kısmını uygulamalı örneklerle göstermesi, RAG pipeline'ının neden bazen alakasız sonuç döndürdüğünü anlamamı sağladı.
Good deep dive into the parts of RAG that most tutorials skip, especially the hybrid search and reranking sections which finally explained why my retrieval results were mediocre. The LangChain code examples are solid, though the query rewriting module could use a bit more explanation on tuning the prompts.
Learners also took
🎓 With certificate
Private AI with Open-Source LLMs: Local Deployment, RAG, and Agents
Certificate
Hands-on
59 zł
→
💼 Job-ready
🎓 With certificate
Fine-Tuning OpenAI Models: Customize LLMs with Your Own Data
Certificate
Hands-on
59 zł
→
🏆 Most popular
🎓 With certificate
Developing RAG Systems with Azure OpenAI and Azure AI Search
Certificate
Hands-on
59 zł
→
💼 Job-ready
🎓 With certificate
AI Application Development with LangChain
Certificate
Hands-on
59 zł
→
Frequently asked
What do I need to take this course? +
Just a phone or computer with internet. No installs, no special hardware.
How do I pay? +
By card via Stripe. We don’t store card details — Stripe handles them securely.
Can I get a refund? +
Yes — full refund within 14 days, no questions asked.
How long will I have access? +
Forever. Once you purchase, the course is yours to revisit anytime.
Will I get a certificate? +
Yes. On completion you'll receive a certificate you can add to your LinkedIn profile.
Built for learners in
Tech
Design
Finance
Marketing
Healthcare
Education
Hospitality
Manufacturing