tooluniverse.embedding_database module

Embedding Database Tool for ToolUniverse

A unified tool for managing embedding databases with FAISS vector search and SQLite metadata storage. Supports creating databases from documents, adding documents, searching, and loading existing databases. Uses OpenAI’s embedding models for text-to-vector conversion, with support for Azure OpenAI.

class tooluniverse.embedding_database.EmbeddingDatabase

Bases: BaseTool

Unified embedding database tool supporting multiple operations: - create_from_docs: Create new database from documents - add_docs: Add documents to existing database - search: Search for similar documents - load_database: Load existing database from path

__init__(tool_config)

run(arguments)

Main entry point for the tool