cache_embeddings_batch() — langchain Function Reference

Architecture documentation for the cache_embeddings_batch() function in test_caching.py from the langchain codebase.

Function python LangChainCore Runnables

Entity Profile

LangChainCore→ Runnables→ cache_embeddings_batch() — langchain Function Reference

Dependency Diagram

graph TD
  52c6999c_bbec_d108_b60f_1daf1f793bb8["cache_embeddings_batch()"]
  6b1a1e58_d1bc_2756_cc7d_9c01f64a73a2["test_caching.py"]
  52c6999c_bbec_d108_b60f_1daf1f793bb8 -->|defined in| 6b1a1e58_d1bc_2756_cc7d_9c01f64a73a2
  style 52c6999c_bbec_d108_b60f_1daf1f793bb8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/embeddings/test_caching.py lines 47–56

def cache_embeddings_batch() -> CacheBackedEmbeddings:
    """Create a cache backed embeddings with a batch_size of 3."""
    store = InMemoryStore()
    embeddings = MockEmbeddings()
    return CacheBackedEmbeddings.from_bytes_store(
        embeddings,
        store,
        namespace="test_namespace",
        batch_size=3,
    )