From the course: Advanced RAG Applications with Vector Databases
Demo: Embedding and storing data
“
- [Instructor] The code in this video should be very familiar. This is the exact same code that we ran through in chapter 2 to embed and store our images there. Let's briefly review. We're using langchain to get our OpenCLIPEmbeddings and storing all of our vectors into FAISS. What we're doing here is we're grabbing all of these images, encoding them into a Base64 encoding for the LLM, creating documents from all of these images, and then using the OpenCLIPEmbeddings along with all the documents to store into the FAISS vector database.
Contents
-
-
-
-
-
Introduction to the types of multimodality2m 23s
-
Ways to do multimodal RAG4m 13s
-
Introduction to multimodal embedding models3m 4s
-
Demo: Embedding and storing data40s
-
Demo: Query images with text3m 5s
-
Challenge: Find anomalies in your embeddings1m 24s
-
Solution: Find anomalies in your embeddings2m 3s
-
-