PinnedShimpali Deshpande·5h agoNaive RAG vs Mellea RAG: Making Retrieval Failures Visible with IBM’s MelleaMy first Mellea cookbook was about not trusting a model’s raw output. The second applies the same instinct one step earlier, to what the…
Shimpali Deshpande·Nov 13Function-Calling and Data Extraction with LLMs: What the Model Sees, and How Far to Trust What…Article 3 of “From Transformers to Agents”, my learning journey through AI.
Shimpali Deshpande·Oct 24Prompting Fundamentals for LLMs: Getting the Task Done Without Burning Your UsageArticle 2 of “From Transformers to Agents”, my learning journey through AI.A response icon1A response icon1
Shimpali Deshpande·Sep 29How Transformer LLMs WorkArticle 1 of my “From Transformers to Agents” series: what I’m learning from DeepLearning.AI’s How Transformer LLMs Work
Shimpali Deshpande·Sep 14What I Learned Building With IBM’s Mellea: Writing LLM Code You Can Actually TrustA few weeks into my own AI/ML learning plan (the kind of thing you do in the evenings after a full day of work), I wanted something that…