Ravi Theja·Mar 23, 2024Deploying Navarasa-2.0 — a Gemma model in 15 Indian LanguagesDeploying Navarasa-2.0 — a Gemma model in 15 Indian Languages
Ravi Theja·Mar 18, 2024Introducing Navarasa 2.0 — Indic Gemma 7B/2B Instruction tuned model on 15 Indian LanguagesNavarasa 2.0 — Indic Gemma 7B/2B Instruction tuned model on 15 Indian LanguagesA response icon1A response icon1
Ravi Theja·Mar 6, 2024Introducing Indic Gemma 7B/2B Instruction tuned model on 9 Indian Languages — NavarasaIntroducing Indic Gemma 7B/2B Instruction tuned model on 9 Indian Languages — NavarasaA response icon1A response icon1
InLlamaIndex BlogbyRavi Theja·Jan 31, 2024LlamaIndex: Enhancing Retrieval Performance with Alpha Tuning in Hybrid Search in RAGUnlock the power of Hybrid Search in RAG applications by mastering the art of tuning Alpha, balancing keyword and vector search for optimalA response icon1A response icon1
InLlamaIndex BlogbyRavi Theja·Jan 15, 2024Building Multi-Tenancy RAG System with LlamaIndexExplore building a secure Multi-Tenancy RAG System with LlamaIndex: Ensuring data privacy by isolating user-specific document access.A response icon1A response icon1
InLlamaIndex BlogbyRavi Theja·Dec 15, 2023LlamaIndex: RAG Evaluation Showdown with GPT-4 vs. Open-Source Prometheus ModelIn this blog post, we’ll show you how to integrate the Prometheus model with the LlamaIndex framework for evaluation, comparing it with…A response icon2A response icon2
InLlamaIndex BlogbyRavi Theja·Nov 28, 2023OpenAI Cookbook: Evaluating RAG systemsThe OpenAI Cookbook is a resource for evaluating Retrieval-Augmented Generation (RAG) systems using the LlamaIndex tool.
InLlamaIndex BlogbyRavi Theja·Nov 17, 2023GPT4-V Experiments with General, Specific questions and Chain Of Thought prompting(COT) techniques.This blog post explores whether GPT-4 Visual’s image analysis capabilities can be enhanced for interpreting data visualizations like bar…
InLlamaIndex BlogbyRavi Theja·Nov 16, 2023Improving Retrieval Performance by Fine-tuning Cohere Reranker with LlamaIndexThis blog post explores enhancing Retrieval performance by Fine-tuning a cohere reranker with LlamaIndex.A response icon1A response icon1
InLlamaIndex BlogbyRavi Theja·Nov 3, 2023Boosting RAG: Picking the Best Embedding & Reranker modelsEvaluate embeddings and rerankers on your dataset to find the best retrieval mix for RAG pipeline.A response icon8A response icon8
