embed_query() — langchain Function Reference

Architecture documentation for the embed_query() function in cache.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ embed_query() — langchain Function Reference

Dependency Diagram

graph TD
  1bc8c67b_9021_d0d6_ca62_9ccab3ca8d7e["embed_query()"]
  b3be4e54_ae5f_c527_4e99_0843e3d30f72["CacheBackedEmbeddings"]
  1bc8c67b_9021_d0d6_ca62_9ccab3ca8d7e -->|defined in| b3be4e54_ae5f_c527_4e99_0843e3d30f72
  style 1bc8c67b_9021_d0d6_ca62_9ccab3ca8d7e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/embeddings/cache.py lines 241–262

    def embed_query(self, text: str) -> list[float]:
        """Embed query text.

        By default, this method does not cache queries. To enable caching, set the
        `cache_query` parameter to `True` when initializing the embedder.

        Args:
            text: The text to embed.

        Returns:
            The embedding for the given text.
        """
        if not self.query_embedding_store:
            return self.underlying_embeddings.embed_query(text)

        (cached,) = self.query_embedding_store.mget([text])
        if cached is not None:
            return cached

        vector = self.underlying_embeddings.embed_query(text)
        self.query_embedding_store.mset([(text, vector)])
        return vector