embed_documents return in same order as texts passed in?

[dean-boi]

Hi all,

Is the list of embeddings returned from the embed_documents method ordered (on the HuggingFaceEmbeddings class)? Like in the same order as the list of texts passed in?

Docs:
https://api.python.langchain.com/en/latest/embeddings/langchain.embeddings.huggingface.HuggingFaceEmbeddings.html#langchain.embeddings.huggingface.HuggingFaceEmbeddings.embed_documents

Code:
https://api.python.langchain.com/en/latest/_modules/langchain/embeddings/huggingface.html#HuggingFaceEmbeddings.embed_documents

Thanks :]

[dosubot[bot]]

🤖

Hi,

Yes, the embed_documents method on the HuggingFaceEmbeddings class returns a list of embeddings in the same order as the list of texts passed in.

Here's the relevant part of the code:

def embed_documents(self, texts: List[str]) -> List[List[float]]:
    """Compute doc embeddings using a HuggingFace transformer model.

    Args:
        texts: The list of texts to embed.

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

    texts = list(map(lambda x: x.replace("\n", " "), 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, **self.encode_kwargs)

    return embeddings.tolist()

In this method, the texts argument is a list of texts to be embedded. The method then calls the encode or encode_multi_process method of the sentence_transformers.SentenceTransformer client with these texts as inputs. The responses from the client, which are the embeddings for the texts, are returned in the same order as the input texts.

You can find this code in the following files in the LangChain repository:

• libs/langchain/langchain/embeddings/huggingface_hub.py
• libs/langchain/langchain/embeddings/huggingface.py

I hope this answers your question. Let me know if you need further clarification.

Sources

• libs/langchain/langchain/embeddings/huggingface_hub.py
• libs/langchain/langchain/embeddings/huggingface.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.