Uploaded August 2024 | Updated September 2026, 52 minutes ago
One of the most promising use cases is Retrieval Augmented Generation (RAG), as it enables teams across all industries to leverage the power of LLMs with their own data. But it's one thing to develop a prototype - another to use RAG in production.
Join us for this online hands-on session to learn more about Retrieval Augmented Generation and how to use it more effectively in production.
What You Will Learn
Learn all about Advanced RAG use cases and how the power of vector databases and Weaviate can be leveraged in different scenarios.
Zain will break down RAG into three phases and for each, he will show a way to improve it:
1. Indexing Data:
- Chunking techniques - fixed length, semantic and LLM-based chunking
- Meta-data Filtered Search - filtering retrieved results based on metadata added to chunks
2. Retrieval:
- Query rewriting - optimize queries for retrieval and LLMs
- Hybrid Search - combine BM25 + vector search
- Finetune Embedding Models
3. Generation:
- Autocut - removing retrieved results based on similarity distance gaps
- Reranking results - using cross-encoder or multivector embedding models
- Finetuning LLMs
In addition to a great hands-on experience, you will get answers to your questions!
One of the most promising use cases is Retrieval Augmented Generation (RAG), as it enables teams across all industries to leverage the power of LLMs with their own data. But it's one thing to develop a prototype - another to use RAG in production.
Join us for this online hands-on session to learn more about Retrieval Augmented Generation and how to use it more effectively in production.
What You Will Learn
Learn all about Advanced RAG use cases and how the power of vector databases and Weaviate can be leveraged in different scenarios.
Zain will break down RAG into three phases and for each, he will show a way to improve it:
1. Indexing Data:
- Chunking techniques - fixed length, semantic and LLM-based chunking
- Meta-data Filtered Search - filtering retrieved results based on metadata added to chunks
2. Retrieval:
- Query rewriting - optimize queries for retrieval and LLMs
- Hybrid Search - combine BM25 + vector search
- Finetune Embedding Models
3. Generation:
- Autocut - removing retrieved results based on similarity distance gaps
- Reranking results - using cross-encoder or multivector embedding models
- Finetuning LLMs
In addition to a great hands-on experience, you will get answers to your questions!
