aembed_documents() — langchain Function Reference

Architecture documentation for the aembed_documents() function in base.py from the langchain codebase.

Function python LangChainCore LanguageModelBase calls 1 called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ aembed_documents() — langchain Function Reference

Dependency Diagram

graph TD
  61442dce_e074_a559_4f56_e5a72f5d3c6c["aembed_documents()"]
  2f237d29_e276_c4ef_3a56_7139ce49b50e["OpenAIEmbeddings"]
  61442dce_e074_a559_4f56_e5a72f5d3c6c -->|defined in| 2f237d29_e276_c4ef_3a56_7139ce49b50e
  ac620fcf_32ca_85e5_d295_7f3998895c75["aembed_query()"]
  ac620fcf_32ca_85e5_d295_7f3998895c75 -->|calls| 61442dce_e074_a559_4f56_e5a72f5d3c6c
  b1a193e7_39a7_c737_2248_ba3dd74ba93c["_aget_len_safe_embeddings()"]
  61442dce_e074_a559_4f56_e5a72f5d3c6c -->|calls| b1a193e7_39a7_c737_2248_ba3dd74ba93c
  style 61442dce_e074_a559_4f56_e5a72f5d3c6c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/embeddings/base.py lines 713–746

    async def aembed_documents(
        self, texts: list[str], chunk_size: int | None = None, **kwargs: Any
    ) -> list[list[float]]:
        """Asynchronously call OpenAI's embedding endpoint to embed search docs.

        Args:
            texts: The list of texts to embed.
            chunk_size: The chunk size of embeddings.

                If `None`, will use the chunk size specified by the class.
            kwargs: Additional keyword arguments to pass to the embedding API.

        Returns:
            List of embeddings, one for each text.
        """
        chunk_size_ = chunk_size or self.chunk_size
        client_kwargs = {**self._invocation_params, **kwargs}
        if not self.check_embedding_ctx_length:
            embeddings: list[list[float]] = []
            for i in range(0, len(texts), chunk_size_):
                response = await self.async_client.create(
                    input=texts[i : i + chunk_size_], **client_kwargs
                )
                if not isinstance(response, dict):
                    response = response.model_dump()
                embeddings.extend(r["embedding"] for r in response["data"])
            return embeddings

        # Unconditionally call _get_len_safe_embeddings to handle length safety.
        # This could be optimized to avoid double work when all texts are short enough.
        engine = cast(str, self.deployment)
        return await self._aget_len_safe_embeddings(
            texts, engine=engine, chunk_size=chunk_size, **kwargs
        )