This module provides text embedding capabilities for Large Language Models, specifically supporting Chinese text processing.

Overview

The LLM module offers:

• Text Embeddings: Generate text embeddings using SentenceTransformer models
• Chinese Language Support: Optimized for Chinese text with GanymedeNil/text2vec-large-chinese
• OpenAI API Mocking: Mock OpenAI embedding APIs for testing purposes
• PyTest Integration: Fixtures for embedding-related testing

Key Features

• High-quality Chinese text embeddings
• OpenAI Embedding API compatibility
• Vector similarity operations
• Test fixture support for embeddings

Embedding Model Setup

Initialize the Chinese text embedding model for vector representations.

mock_embed_create[source]

mock_embed_create(**kwargs)

OpenAI Embedding API Mock

Mock implementation of OpenAI's embedding API using the Chinese text model.

mock_openai_embed[source]

mock_openai_embed(monkeypatch)