Avi Chawla
Search documents
X @Avi Chawla
Avi Chawla· 2025-10-04 19:18
RT Avi Chawla (@_avichawla)9 MCP, Agents, and RAG projects for AI engineers: https://t.co/glppKndo1c ...
X @Avi Chawla
Avi Chawla· 2025-10-04 06:31
If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. ...
X @Avi Chawla
Avi Chawla· 2025-10-04 06:31
Find all these projects in our AI Engineering Hub, along with 70 more hands-on projects: https://t.co/z9IxdiEm8w(don't forget to star it ⭐ ) ...
X @Avi Chawla
Avi Chawla· 2025-10-04 06:31
9 MCP, Agents, and RAG projects for AI engineers: https://t.co/glppKndo1c ...
X @Avi Chawla
Avi Chawla· 2025-10-03 19:56
RT Avi Chawla (@_avichawla)I never use Pandas' describe method.Skimpy is a much better (and open-source) alternative that provides a comprehensive data summary, including data shape, column data types, stats, distribution chart, etc. https://t.co/i19N6BdUgs ...
X @Avi Chawla
Avi Chawla· 2025-10-03 06:52
Data Analysis Tools - The industry suggests using Skimpy as a superior open-source alternative to Pandas' describe method for comprehensive data summarization [1] - Skimpy offers detailed data insights, including data shape, column data types, statistics, and distribution charts [1]
X @Avi Chawla
Avi Chawla· 2025-10-03 06:33
Feature scaling is not always necessary in ML.Logistic regression (trained using SGD), SVM, MLP, and kNN classifiers usually do better with feature scaling.Tree-based models, Naive bayes, and Gradient Boosting are unaffected. https://t.co/vzy2RzLBW8 ...
X @Avi Chawla
Avi Chawla· 2025-10-02 19:40
RT Avi Chawla (@_avichawla)RAG can’t keep up with real-time data.Airweave builds live, bi-temporal knowledge bases so that your Agents always reason on the freshest facts.Supports fully agentic retrieval with semantic and keyword search, query expansion, and more across 30+ sources.100% open-source. https://t.co/0ne2MeCLbY ...
X @Avi Chawla
Avi Chawla· 2025-10-02 18:03
Looks like grok missed. Let me explain with an example.Suppose a company policy changes its parental leave from 12 weeks to 16 weeks, effective Jan 1 2025.If you query “What was the policy on Dec 15 2024?”, the database says 12 weeks.If you query “What is the policy on Feb 1 2025?”, it says 16 weeks.Temporal lets you see what the actual policy is at different times.Now imagine the HR team only updated the database on Jan 20 2025 to reflect the Jan 1 change mentioned above.If you query “What did we believe t ...