Advanced Retrieval Techniques for Language Models: A Comprehensive Approach

I'm excited to introduce this course on Advanced Retrieval built in partnership with Chroma and taught by Anton Trov, co-founder of Chroma. In this course, you will learn sophisticated techniques that utilize Large Language Models (LLMs) to get the most relevant context for a retrieval or ment generation system. For example, using a technique called query expansion with LLM, given a use of query, we search the database to find the relevant context and give the LLM to help it write an accurate answer.

But how do you find the most relevant context in traditional text web search if you search for one concept, say AI? It may carry out query expansion and add related keywords like machine learning or new networks to retrieve additional relevant documents. In this course, you will learn how to use an LLM to rewrite or create additional queries that reflect the intent of the user query further. Given a mass of retrievable documents, you don't necessarily want to include all of that in the LLM context; instead, you will learn too how to use another LLM to select the most relevant parts to form the final context to give to the retrieval system.

These sophisticated techniques as seen in this course give a significant boost to retrieval accuracy. Our instructor, Anton Trov, is a founder and head of Technology at Chroma, which is one of the leading open-source back-to-databases. He works every day with users who are building retrieval-based applications and has seen a lot of what does and doesn't work. I look forward to sharing that practical experience with you here.

Thank you, Andrew, and I'm really looking forward to sharing these techniques with you; it's such an exciting time to be working in retrieval for AI. One of the things few people appreciate until they've worked on it a few times is pitfalls and common failure modes when doing retrieval for LLMs while vector databases are a great tool for retrieval, there are also common failure modes that I often see AI developers run into.

A very common bug is if you get documents that are semantically similar to the query but don't actually have the information needed for an answer. As Andrew mentioned, we will explain in detail how you can use an LLM to carry out query expansion to improve retrieval performance. We will also talk about how to use a text model to score and rank the retrieved results and how to adapt the text embeddings of the query directly using data from user feedback.

These techniques make the retrieval step of LLM much more effective and I hope you will take and enjoy the course.

"WEBVTTKind: captionsLanguage: enI'm excited to introduce this course on Advanced retrieval built in partnership with chroma and taught by Anton trov co-founder of chroma in this course you learn sophisticated techniques that use in LM to get the most relevant context for a rag or retrieval of ment generation system for example using a technique called query expansion with rag given a use of query we search the database to find the relevant context the give the LM to help it write an accurate answer but how do you find the most relevant context in traditional text web search if you search for one concept say AI it may carry out query expansion and add in related keywords like machine learning or new networks to retrieve additional relevant documents in this course you learn how to use an LM to rewrite or create additional queries that reflect the intent of the user query further given a mass of retriev documents you don't necessarily want to include all of that in the LM context so you learn too how to use another LM to select the most relevant parts to form the final context to give to rag these sophisticated techniques as you see in this course give a significant boost to rag accuracy your instructor Anon trov is a founder and head of Technology of chroma which is one of the leading open source backto databases he works everyday with user who are building retrieval based applications and so has seen a lot of what does and doesn't work I look forward to sharing that practical experience with us here thank you Andrew and I'm really looking forward to sharing these techniques with you it's such an exciting time to be working in retrieval for AI one of the things few people appreciate until they've worked on it a few times is pitfalls One Way encounter when doing retrieval for rag while vectro databases are a great tool for retrieval there are also common failure modes that I often see AI developers run into a very common bug is if you get documents that are semantically similar to The query so they talk about the topics in the query but don't actually have the information needed for an answer as Andrew mentioned we'll explain in detail how you can use an llm to carry out query expansion to improve retrieval performance we'll talk about how to use a text model to score and rank the retrieved results and we'll also talk about how to adapt the text embeddings of the query directly using data from user feedback these techniques makes the retrieval step of rag much more effective and I hope you will take and enjoy the courseI'm excited to introduce this course on Advanced retrieval built in partnership with chroma and taught by Anton trov co-founder of chroma in this course you learn sophisticated techniques that use in LM to get the most relevant context for a rag or retrieval of ment generation system for example using a technique called query expansion with rag given a use of query we search the database to find the relevant context the give the LM to help it write an accurate answer but how do you find the most relevant context in traditional text web search if you search for one concept say AI it may carry out query expansion and add in related keywords like machine learning or new networks to retrieve additional relevant documents in this course you learn how to use an LM to rewrite or create additional queries that reflect the intent of the user query further given a mass of retriev documents you don't necessarily want to include all of that in the LM context so you learn too how to use another LM to select the most relevant parts to form the final context to give to rag these sophisticated techniques as you see in this course give a significant boost to rag accuracy your instructor Anon trov is a founder and head of Technology of chroma which is one of the leading open source backto databases he works everyday with user who are building retrieval based applications and so has seen a lot of what does and doesn't work I look forward to sharing that practical experience with us here thank you Andrew and I'm really looking forward to sharing these techniques with you it's such an exciting time to be working in retrieval for AI one of the things few people appreciate until they've worked on it a few times is pitfalls One Way encounter when doing retrieval for rag while vectro databases are a great tool for retrieval there are also common failure modes that I often see AI developers run into a very common bug is if you get documents that are semantically similar to The query so they talk about the topics in the query but don't actually have the information needed for an answer as Andrew mentioned we'll explain in detail how you can use an llm to carry out query expansion to improve retrieval performance we'll talk about how to use a text model to score and rank the retrieved results and we'll also talk about how to adapt the text embeddings of the query directly using data from user feedback these techniques makes the retrieval step of rag much more effective and I hope you will take and enjoy the course\n"