A Step-by-Step Guide to Discover and Harness the Power of Vector Databases
Dominik Polzer
Follow
Towards Data Science
3 hours ago
—
Intro
What’s so special about Vector Databases?
How will we map the meaning of a sentence to a numerical representation?
How does that help our LLM app?
Why can’t we just give the LLM all the info now we have?
Hands-On Tutorial — Text to Embeddings and Distance Metrics
1. Text to Embeddings
2. Plot 384 dimensions in 2 using PCA
3. Calculate the space metrics
Towards Vector Stores
Tips on how to speed up the Similarity Search?
What are different Vector Stores we are able to select from?
Hands-On Tutorial — Arrange your first Vector Store
1. Install chroma
2. Get/create a chroma client and collection
3. Add some text documents to the gathering
4. Extract all entries from database to excel file
5. Query the gathering
Summary
References
Vector databases are a hot topic immediately. Firms keep raising money to develop their vector databases or so as to add vector search capabilities to their existing SQL or NoSQL databases.
Vector Databases make it possible to quickly search and compare large collections of vectors. That is so interesting since the newest embedding models are highly able to understanding the semantics/meaning behind words and translating them into vectors. This permits us to efficiently compare sentences with one another.