@kumologica/kumologica-contrib-vectorstore
v0.0.1
Published
Node implements memory vector store
Downloads
70
Readme
Kumologica contribution node: kumologica-contrib-VectorStore
Overview
This Kumologica node client provides stateful interaction with a memory vector store, retaining data throughout the container lifecycle.
Features
- Text Chunking: Supports various text splitters to chunk input documents efficiently.
- Embedding Support: Compatible with OpenAI, VoyageAI, and Fake Embeddings for vector generation.
- Similarity Search: Enables similarity search with scoring and Maximal Marginal Relevance (MMR).
- Get/Set Operations: Includes operations to persist and load vectors from your chosen storage.
This node is ideal for applications requiring vector storage, similarity searches, and integration with popular embedding providers.
Installation
From command line
Go to the project directory and run from the console:
npm install @kumologica/kumologica-contrib-vectorstore
Dependencies
Kumologica Designer and OpenAI or Voyage API KEY is required. Follow below instructions:
Kumologica Designer
You need Kumologica Designer to use Memory Vector Store Node.
To install Kumologica SDK run following command:
npm install -g @kumologica/sdk
After successful installation run following command to open Kumologica Designer:
kl open
OpenAI API KEY
Follow https://platform.openai.com/docs/quickstart to sign up and generate the key.
VoyageAI API Key
See FAQ https://docs.voyageai.com/docs/faq how to get api key.
More information
For more information about Kumologica SDK Installation see: Kumologica SDK Installation
Visit kumologica.com for information about sdk, designer, documentation, tutorials, support and professional services.