Optimizing RAG With LLMS: Exploring Chunking Techniques and Reranking for Enhanced Results скачать в хорошем качестве

Optimizing RAG With LLMS: Exploring Chunking Techniques and Reranking for Enhanced Results

Large Language Models have the power to answer questions specific to your data. There are a few limitations, like the limited input token length and retrieval of the wrong context. Chunking is used in LLMs to break down long text documents into smaller sections. For example, you can chunk a PDF document by the headings or use a text splitter. Implementing ranking models is an effective strategy to enhance search quality. With these techniques in mind, we can use LLMs in production and interact with your specific data. Unstructured will chunk the documents and store the objects in the Weaviate vector database. Weaviate is used to orchestrate the inference for the embeddings and the Cohere Reranking API. We will then evaluate the results in Phoenix and spot the cases where the retrieval failed. Join this session to learn more about: Strategies for optimizing Retrieval Augmented Generation (RAG) Using chunking techniques to streamline processing Implementing ranking models to enhance search quality 0:00 Welcome! 0:50 Introduction 1:50 Unstructured 5:22 Weaviate 11:10 Search and Retrieval: An Overview 15:55 Unstructured X Weaviate X Arize Python Demo 16:20 Unstructured Python Demo 23:45 Weaviate Python Demo 32:00 Arize Python Demo 43:00 Audience Q&A