Generative AI is transformative, but in most cases it needs to be combined with your data to deliver something truly useful - this is the topic of retrieval augmented generation (RAG). This talk will discuss how to make RAG applications that delivers quality results in production, at scale. Some topics:

• Why RAG?
• RAG is about relevance.
• Do you even need vector embeddings?
• Do you even need vector indexes?
• Using personal data effectively.
• Quality and cost tradeoffs.
• Letting your LLM train your relevance model.

LLMs like GPT can give useful answers to many questions, but there are also well-known issues with their output: The responses may be outdated, inaccurate, or outright hallucinations, and it’s hard to know when you can trust them. And they don’t know anything about you or your organization's private data (we hope). RAG can help reduce the problems with “hallucinated” answers, and make the responses more up-to-date, accurate, and personalized - by injecting related knowledge, including non-public data.

In this talk, we’ll go through what RAG means and demo some ways you can implement it, including vector search, multi-vector, filtering, ranking and hybrid search.

LLMs like GPT can give useful answers to many questions, but there are also well-known issues with their output: The responses may be outdated, inaccurate, or outright hallucinations, and it’s hard to know when you can trust them. And they don’t know anything about you or your organization's private data (we hope). RAG can help reduce the problems with “hallucinated” answers, and make the responses more up-to-date, accurate, and personalized - by injecting related knowledge, including non-public data.

In this talk, we’ll go through what RAG means and demo some ways you can implement it, including vector search, multi-vector, filtering, ranking and hybrid search.

Generative AI is transformative, but in most cases it needs to be combined with your data to deliver something truly useful - this is the topic of retrieval augmented generation (RAG). This talk will discuss how to make RAG applications that delivers quality results in production, at scale. Some topics:

• Why RAG?
• RAG is about relevance.
• Do you even need vector embeddings?
• Do you even need vector indexes?
• Using personal data effectively.
• Quality and cost tradeoffs.
• Letting your LLM train your relevance model.

Retrieval Augmented Generation (RAG) is about combining large language models with your data. This talk will discuss how to make RAG applications that delivers quality results that makes business sense. Covering the topics:

• Why RAG?
• RAG is about relevance.
• Do you even need vector embeddings?
• Do you even need vector indexes?
• Using personal data effectively.
• Quality and cost tradeoffs.
• Let your LLM train your relevance model.