From the course: Advanced RAG Applications with Vector Databases
Solution: Cite your document sources
From the course: Advanced RAG Applications with Vector Databases
Solution: Cite your document sources
(bright music) - [Instructor] All right. Let's take a look at how we can solve this challenge. As we mentioned earlier, the names of the documents are all stored in the vector store via document metadata. This means that we can access this information when we retrieve objects from the vector store. We can get our sources via prompt engineering by adding a simple sentence to our prompt. All we have to do to solve this challenge is to tell the llm to cite its sources. And voila, it tells us which documents it found the answer in. Cite your sources. There it is. This information can be found in the first and second document titled "Our Story" and "What We Do" respectively. Now, let's tackle another challenge.
Contents
-
-
-
Introduction to preprocessing for RAG4m 57s
-
Chunking considerations5m 12s
-
Chunking examples4m 32s
-
Introduction to embeddings9m 50s
-
Embedding examples2m 57s
-
Metadata3m 12s
-
Demo: Chunking2m 32s
-
Demo: Metadata1m 23s
-
Demo: Embed and store2m
-
Demo: Querying1m 8s
-
Demo: Adding the LLM2m 1s
-
Challenge: Cite your document sources47s
-
Solution: Cite your document sources59s
-
Challenge: Change the chunk size44s
-
Solution: Change the chunk size55s
-
-
-
-