Daily Dose of Data Science

Daily Dose of Data Science

Home
Sponsor
Premium
Archive
Leaderboard
About

Vector Databases

[Hands-on] Audio RAG with 200x Cheaper Vector DB Costs
...while also outperforming OpenAI and Cohere.
 • 
Avi Chawla
0:28
Contextualized Chunk Embedding Model
Cut vector DB costs by ~200x.
 • 
Avi Chawla
1
Make RAG systems 32x Memory Efficient!
...explained with step-by-step code!
 • 
Avi Chawla
0:13
Faster Neighbor Search Using Inverted File Index
...actively used in vector DBs.
 • 
Avi Chawla
5 Chunking Strategies For RAG
...explained in a single frame.
 • 
Avi Chawla
10 MCP, AI Agents, and RAG projects for AI Engineers
...with open-source code.
 • 
Avi Chawla
3
A Crash Course on Building RAG Systems – Part 1
Beginner-friendly and with implementation.
 • 
Avi Chawla
0:45
5 Chunking Strategies For RAG
...explained in a single frame.
 • 
Avi Chawla
5
Approximate Nearest Neighbor Search Using Inverted File Index
Speedup traditional kNN.
 • 
Avi Chawla
The Utility of Vector Databases in LLMs
...and what made them so special almost overnight?
 • 
Avi Chawla
3
Full-model Fine-tuning vs. LoRA vs. RAG
A visual summary
 • 
Avi Chawla
Approximate Nearest Neighbor Search Using Inverted File Index
Speedup traditional kNN.
 • 
Avi Chawla
3
© 2025 Avi Chawla
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture