The example KDB.AI notebooks provided aim to demonstrate examples of the use of the KDB.AI vector database in a number of scenarios ranging from getting started guides to industry specific use-cases.
⚠️ Notebook Execution Environment: Currently the notebooks presented here can only be used by users engaged in the KDB.AI Early Access Program.
KDB.AI is a time-based vector database that allows developers to build scalable, reliable and real-time applications by providing advanced search, recommendation and personalization for Generative AI applications. KDB.AI is a key component of full-stack Generative AI applications that use Retrieval Augmented Generation (RAG).
Built by KX the creators of kdb+, KDB.AI provides users with the ability to combine unstructured vector embedding data with structured time-series datasets to allow for hybrid use-cases which benefit from the rigor of conventional time-series data analytics and the usage patterns provided by vector databases within the Generative AI space.
KDB.AI supports the following feature set:
- Multiple index types: Flat, IVF, IVFPQ and HNSW.
- Multiple distance metrics: Euclidean, Inner-Product, Cosine.
- Top-N and metadata filtered retrieval
- Python and REST Interfaces
Additionally for testing the following integrations are presently included
The following notebooks and sections are included within this repository at this time:
- Quickstart: A quick introduction to the KDB.AI APIs
- Document Search
- Image Search
- Recommendation System
- Pattern Matching
- Retreival Augmented Generation
- Sentiment Analysis
- ChatGPT Retrieval Plugin: Example showing a question and answer session using a ChatGPT retrieval plugin using KDB.AI Vector Database.
- Langchain: Example showing a question and answer session using a Langchain integration with the KDB.AI Vector Database.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent