This is an incredible resource on building RAG-based LLM applications 45 minute read!!!! Lots to learn
CODE
-
Data Science Interview Questions and Answers Curated List
By
–
GitHub – youssefHosni/Data-Science-Interview-Questions-Answers: Curated list of data science interview questions and answers https://
bit.ly/42FHnF3 #AI #MachineLearning #DeepLearning #LLMs #DataScience -
MapInPandas Spark 3.0 Data Transformations Guide
By
–
The answer to handling complex data transformations? mapInPandas()! Now in Spark 3.0.0, mapInPandas() allows you to complete arbitrary actions on each row of a Spark DataFrame. See how https://
bit.ly/3qOvHTo -
LLM Output Validation: Ensuring Robust and Predictable Applications
By
–
An output validation step ensures that an LLM application is robust and predictable. In this article, we look at LLM output validation and how to implement it using @guardrails_ai
. -
Bill Xing’s Presentation at GroqDay March 2023
By
–
It's #dayoftheprogrammer, so we're sharing a presentation by one of our favorite programmers, Bill Xing, at our March 2023 #GroqDay. https://
youtu.be/rXGbSMYXyG0 -
LangSmith enables visibility into Tree of Thought reasoning
By
–
Another great walk through from @CobusGreylingZA Tree of though has a lot going on under the hood – nice to be able to see all of that with langsmith
-
Explanation of backpropagation: max function implements NAND gates
By
–
This explanation was kind of polarising — some people found it pointlessly abstruse, others found it worked for them when others didn't: https://
thinc.ai/docs/backprop1
01
… If you get down to the bit with the two tables, it explains how a max function can implement nand, while a linear -
AutoTrain DreamBooth Default Parameters Work Well
By
–
nice. the default params in autotrain dreambooth always worked very well for me!
-
AutoTrain Advanced: Multi-Model Training and Hyperparameter Search
By
–
Training and doing hyperparameter search on multiple models (in screenshot: xgboost, svm and random forest) simultaneously on a tabular dataset using AutoTrain Advanced without writing a single line of code! Try AutoTrain Advanced now!