_embed() — langchain Function Reference

Architecture documentation for the _embed() function in huggingface.py from the langchain codebase.

Function python LangChainCore Runnables called by 2

Entity Profile

LangChainCore→ Runnables→ _embed() — langchain Function Reference

Dependency Diagram

graph TD
  b7c83ab3_15c9_f495_f1c6_d2b68282f2a6["_embed()"]
  bc29a19b_53a3_8e06_ab58_d933298d898b["HuggingFaceEmbeddings"]
  b7c83ab3_15c9_f495_f1c6_d2b68282f2a6 -->|defined in| bc29a19b_53a3_8e06_ab58_d933298d898b
  6c6f5815_8b28_d2f4_cafa_af0cebf3ee04["embed_documents()"]
  6c6f5815_8b28_d2f4_cafa_af0cebf3ee04 -->|calls| b7c83ab3_15c9_f495_f1c6_d2b68282f2a6
  1f5cc8d7_bd9b_af04_9e37_b08ce61f8ec2["embed_query()"]
  1f5cc8d7_bd9b_af04_9e37_b08ce61f8ec2 -->|calls| b7c83ab3_15c9_f495_f1c6_d2b68282f2a6
  style b7c83ab3_15c9_f495_f1c6_d2b68282f2a6 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.py lines 107–143

    def _embed(
        self, texts: list[str], encode_kwargs: dict[str, Any]
    ) -> list[list[float]]:
        """Embed a text using the HuggingFace transformer model.

        Args:
            texts: The list of texts to embed.
            encode_kwargs: Keyword arguments to pass when calling the
                `encode` method for the documents of the SentenceTransformer
                encode method.

        Returns:
            List of embeddings, one for each text.

        """
        import sentence_transformers  # type: ignore[import]

        texts = [x.replace("\n", " ") for x in texts]
        if self.multi_process:
            pool = self._client.start_multi_process_pool()
            embeddings = self._client.encode_multi_process(texts, pool)
            sentence_transformers.SentenceTransformer.stop_multi_process_pool(pool)
        else:
            embeddings = self._client.encode(
                texts,
                show_progress_bar=self.show_progress,
                **encode_kwargs,
            )

        if isinstance(embeddings, list):
            msg = (
                "Expected embeddings to be a Tensor or a numpy array, "
                "got a list instead."
            )
            raise TypeError(msg)

        return embeddings.tolist()  # type: ignore[return-type]