Here's another @LightningAI Studio that introduces DSPy! It's adapted from DSPy tutorials on their GitHub, with additional support of local LLMs on the studios using Ollama. Check this out
@akshay_pachaar
-
Lightning AI Studio Reproducible Environment Code Shared
By
–
You can find all the code & details in the @LightningAI studio shared below! The studio comes with a reproducible environment, no setup is required! Take it for a spin now:
-
Fine-tuned T-5 Small RAG Outperforms Vanilla Mistral
By
–
Evaluate finetuned T-5 small RAG program **Notice the score, it beats a vanilla Mistral RAG
-
Fine-tune T-5 Small RAG Model with Checkpoint Save
By
–
Define a T-5 small RAG & Finetune it The code below will perform finetuning & provide a checkpoint for the best model weights saved during the process. Check this out
-
Evaluating RAG System Powered by Mistral-7B LLM
By
–
Evaluate RAG powered by Mistral Let's first evaluate our RAG program that uses Mistral-7B as LLM ** Notice the score, this is what we want to beat! Check this out
-
Defining RAG Pipeline with DSPy Program
By
–
Define the RAG program Let's define a basic DSPy program which is a RAG pipeline for answer generation. It's like defining a model that we want to finetune & evaluate. Check this out
-
RAG Evaluation: Building Compass for AI Systems
By
–
A RAG without evaluation is like a ship without a compass, drifting aimlessly on vast oceans without direction.
— Akshay 🚀 (@akshay_pachaar) 12 mai 2024
I'm working on a couple of @LightningAI⚡️ Studio:
– Synthetic eval data generation
– And RAG Evaluation
Will be using ragas & @ArizePhoenix!
Here's a sneak peak: pic.twitter.com/Fq0hVS8QjAA RAG without evaluation is like a ship without a compass, drifting aimlessly on vast oceans without direction. I'm working on a couple of @LightningAI Studio: – Synthetic eval data generation
– And RAG Evaluation Will be using ragas & @ArizePhoenix
! Here's a sneak peak: -
Build AI Agents: Automate Complex Enterprise Workflows Free Workshop
By
–
Learn how to build AI agents! A FREE workshop covering: – Streamlining complex workflows
– Integration agents with enterprise systems
-Automate processes across customer support, marketing, tech support, IT, sales, and content creation. RSVP now: https://
eventbrite.com/e/complex-ai-a
gents-using-gen-ai-to-automate-complex-tasks-tickets-891222860567?aff=oddtdtcreator
… -
RAG Trustworthiness Scores: Evaluating LLM Response Accuracy
By
–
RAG with Trustworthiness scores! Even with sources/citations, it can be challenging to determine the accuracy of a generated RAG response right away. Cleanlab offers an impressive “Trustworthy Language Model” that assigns a trustworthiness score to each answer generated by
-
AI Engineering Newsletter and Python Machine Learning Resources
By
–
If you interested in: – Python – Machine Learning – AI Engineering Find me → @akshay_pachaar My weekly Newsletter on AI Engineering, Join 9k+ readers: @ML_Spring Cheers!