embed_documents() — langchain Function Reference

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

Function python LangChainCore ApiManagement

Entity Profile

LangChainCore→ ApiManagement→ embed_documents() — langchain Function Reference

Dependency Diagram

graph TD
  2059f943_8fad_d2bc_2c40_ce532430d77f["embed_documents()"]
  b3be4e54_ae5f_c527_4e99_0843e3d30f72["CacheBackedEmbeddings"]
  2059f943_8fad_d2bc_2c40_ce532430d77f -->|defined in| b3be4e54_ae5f_c527_4e99_0843e3d30f72
  style 2059f943_8fad_d2bc_2c40_ce532430d77f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/embeddings/cache.py lines 165–199

    def embed_documents(self, texts: list[str]) -> list[list[float]]:
        """Embed a list of texts.

        The method first checks the cache for the embeddings.
        If the embeddings are not found, the method uses the underlying embedder
        to embed the documents and stores the results in the cache.

        Args:
            texts: A list of texts to embed.

        Returns:
            A list of embeddings for the given texts.
        """
        vectors: list[list[float] | None] = self.document_embedding_store.mget(
            texts,
        )
        all_missing_indices: list[int] = [
            i for i, vector in enumerate(vectors) if vector is None
        ]

        for missing_indices in batch_iterate(self.batch_size, all_missing_indices):
            missing_texts = [texts[i] for i in missing_indices]
            missing_vectors = self.underlying_embeddings.embed_documents(missing_texts)
            self.document_embedding_store.mset(
                list(zip(missing_texts, missing_vectors, strict=False)),
            )
            for index, updated_vector in zip(
                missing_indices, missing_vectors, strict=False
            ):
                vectors[index] = updated_vector

        return cast(
            "list[list[float]]",
            vectors,
        )  # Nones should have been resolved by now