aembed_documents() — langchain Function Reference

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

Function python LangChainCore MessageInterface calls 1 called by 1

Entity Profile

LangChainCore→ MessageInterface→ aembed_documents() — langchain Function Reference

Dependency Diagram

graph TD
  0451d400_70ed_ded5_006c_e334458a80ae["aembed_documents()"]
  8ffbd15a_923a_c258_fc8b_25df9b4cba69["MistralAIEmbeddings"]
  0451d400_70ed_ded5_006c_e334458a80ae -->|defined in| 8ffbd15a_923a_c258_fc8b_25df9b4cba69
  b4b1a205_f414_00ed_dbb1_d40d4e5baef9["aembed_query()"]
  b4b1a205_f414_00ed_dbb1_d40d4e5baef9 -->|calls| 0451d400_70ed_ded5_006c_e334458a80ae
  1ebd0b7d_e260_a53f_7605_d0c94c73ee54["_get_batches()"]
  0451d400_70ed_ded5_006c_e334458a80ae -->|calls| 1ebd0b7d_e260_a53f_7605_d0c94c73ee54
  style 0451d400_70ed_ded5_006c_e334458a80ae fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/mistralai/langchain_mistralai/embeddings.py lines 272–305

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

        Args:
            texts: The list of texts to embed.

        Returns:
            List of embeddings, one for each text.
        """
        try:

            @self._retry
            async def _aembed_batch(batch: list[str]) -> Response:
                response = await self.async_client.post(
                    url="/embeddings",
                    json={
                        "model": self.model,
                        "input": batch,
                    },
                )
                response.raise_for_status()
                return response

            batch_responses = await asyncio.gather(
                *[_aembed_batch(batch) for batch in self._get_batches(texts)]
            )
            return [
                list(map(float, embedding_obj["embedding"]))
                for response in batch_responses
                for embedding_obj in response.json()["data"]
            ]
        except Exception:
            logger.exception("An error occurred with MistralAI")
            raise