Get Started with ChromaDB Image Search (Multimodal Embeddings)
Ғылым және технология
How to start using ChromaDB Multimodal (images) semantic searches on a vector database. We’ll load some images and query for objects in the images. We’ll also cover how to use the Where Metadata filter to limit the relevance of the search results. Everything works locally and is free. Don't need to sign up for a cloud vector database account or learn Langchain first.
Buy Me a Coffee: www.buymeacoffee.com/johnnycode
Get the code: github.com/johnnycode8/chroma...
ChromaDB Playlist: • ChromaDB Vector Databa...
00:00 Create new Conda environment
01:23 Install ChromaDB
01:43 Create new ChromaDB database
03:00 Install Pillow and OpenCLIP
03:43 Location of OpenCLIP embedding model
04:35 Add images to ChromaDB database
06:26 Query ChromaDB
08:54 ImageLoader depends on physical images
09:28 ChromaDB real-world usage
11:20 Problem with vector databases
11:50 Using Where Filter on Metadata
Пікірлер: 9
Really awesome video man. Keep it up. You got a subscriber 👍
Please help me out with a subscribe if this video helped you 😀 Need a more basic ChromaDB text-search tutorial? Check out my other video: kzread.info/dash/bejne/g4eLlK5xlM7His4.html
Great video! Clean and proffesional!
Awesome vid. Can you please do a video/tutorial to read driver lisences of different states.
Same here, very awesome explanation. You have another subscriber 👍
Please make more videos on chromadb with real life use cases like the one you did with chromadb + restaurant search
Thanks!
@johnnycode
4 ай бұрын
Thank you!!! 😃
I had some difficulty with the sentence transformers (sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-mpnet-base-v2")) I am running on a macos (apple silicon M3) and I could not get this code to work without setting the OMP_NUM_THREADS env variable to 1. Things do not seem to work in multithread mode. Thanks very much.