Mehul JainRAG: Part 7: EvaluationHow would you trust your development? When evaluating RAG, it’s essential to consider various metrics that assess both the retrieval and…Apr 15Apr 15
Mehul JainRAG: Part 6: Prompting and InferencingPrompting is the bridge between us and powerful LLMs, allowing us to harness their capabilities effectively. If done correctly, we can get…Apr 11Apr 11
Mehul JainRAG: Part 5: RetrievalRetrieval is a crucial aspect of any information retrieval system, particularly in search engines, QnA. RAG combines information retrieval…Apr 9Apr 9
Mehul JainRAG: Part 4: IndexingIndexing in terms of RAG is the process of organizing a vast amount of text data in a way that allows the RAG system to quickly find the…Apr 5Apr 5
Mehul JainRAG: Part 3: EmbeddingsRepresentation of the text as a vector is the most crucial part of any NLP problem. In Rag, we convert chunks of documents to these vectors…Apr 5Apr 5
Mehul JainRAG: Part 2: ChunkingThe information is endless, and we have limited resources to digest this information. Similarly, in the domain chatbot, we have a ton of…Apr 51Apr 51
Mehul JainReinforcement Learning: Part 10: Policy-Gradient Methods — REINFORCE, Actor-CriticIn the previous blog, we saw how we can use parametrized value functions and featurization to learn a policy.Aug 3, 2023Aug 3, 2023
Mehul JainReinforcement Learning: Part 9: Featurization using State aggregation, Course coding, Tile coding…In the previous blog, we saw how we can use a parametrized algorithm to learn the environment in such as manner that we can generalize as…Jul 29, 2023Jul 29, 2023