Chunking in RAG (with hands-on in LangChain and LlamaIndex) - RAG video series
Retrieval Augmented Generation or RAG is becoming the go-to approach to address the shortcomings of LLMs like hallucinations and model training cut-off. In the video series on RAG, this video is about chunking the input text to be ingested into the Vector DB used in the RAG pipeline.
Hope it's useful.
⌚️ ⌚️ ⌚️ TIMESTAMPS ⌚️ ⌚️ ⌚️
0:00 - Intro
0:13 - RAG refresher
1:04 - Ingestion in RAG
1:27 - What is Chunking?
2:05 - Why Chunking?
4:06 - Fixed-Size Chunking
7:15 - Recursive Chunking
10:18 - Document / Code Chunking
12:17 - Semantic Chunking
16:40 - Conclusion
RELATED LINKS
Introduction to RAG - • Retrieval Augmented Generation (RAG) expla...
Building RAG app using LangFlow - • Build a RAG app using LangFlow + @streamli...
RAG paper - https://arxiv.org/abs/2005.11401
🛠 🛠 🛠 MY SOFTWARE TOOLS 🛠 🛠 🛠
✍️ Notion - https://affiliate.notion.so/aibites-yt
✍️ Notion AI - https://affiliate.notion.so/ys9rqzv2vdd8
MY KEY LINKS
YouTube: / @aibites
Twitter: / ai_bites
Patreon: / ai_bites
Github: https://github.com/ai-bites
WHO AM I?
I am a Machine Learning researcher/practitioner who has seen the grind of academia and start-ups. I started my career as a software engineer 15 years ago. Because of my love for Mathematics (coupled with a glimmer of luck), I graduated with a Master's in Computer Vision and Robotics in 2016 when the AI revolution started. Life has changed for the better ever since.
#machinelearning #deeplearning #aibites