LangChain Reference home page

GitHub
Main Docs

Overview
Vector Stores
Caches
Chat History
Stores
Checkpointers
Callbacks

Google GenAI (Gemini)

Google Vertex AI

IBM

⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

Overview Vector Stores Caches Chat History Stores Checkpointers Callbacks

Google GenAI (Gemini)

Google Vertex AI

Language

Theme

Pythonlangchain-azure-cosmosdb_vectorstore_documentdbCosmosDBVectorSearchCompressionHALF

Attribute●Since v1.0

HALF

Copy

HALF = 'half'

View source on GitHub

Half precision compression