From 7c175e3fdaed71c9d031b7f62eabcade075695ed Mon Sep 17 00:00:00 2001
From: cold-eye <48782821+cold-eye@users.noreply.github.com>
Date: Sat, 1 Mar 2025 11:10:41 -0800
Subject: [PATCH] Update ascend.py (#30060)

add batch_size to fix oom when embed large amount texts

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---
 .../langchain_community/embeddings/ascend.py       | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/libs/community/langchain_community/embeddings/ascend.py b/libs/community/langchain_community/embeddings/ascend.py
index c8cb059177b..940b84bbfc5 100644
--- a/libs/community/langchain_community/embeddings/ascend.py
+++ b/libs/community/langchain_community/embeddings/ascend.py
@@ -30,6 +30,7 @@ class AscendEmbeddings(Embeddings, BaseModel):
     document_instruction: str = ""
     use_fp16: bool = True
     pooling_method: Optional[str] = "cls"
+    batch_size: int = 32
     model: Any
     tokenizer: Any
 
@@ -119,7 +120,18 @@ class AscendEmbeddings(Embeddings, BaseModel):
             )
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]:
-        return self.encode([self.document_instruction + text for text in texts])
+        try:
+            import numpy as np
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import numpy, please install with `pip install -U numpy`."
+            ) from e
+        embedding_list = []
+        for i in range(0, len(texts), self.batch_size):
+            texts_ = texts[i : i + self.batch_size]
+            emb = self.encode([self.document_instruction + text for text in texts_])
+            embedding_list.append(emb)
+        return np.concatenate(embedding_list)
 
     def embed_query(self, text: str) -> List[float]:
         return self.encode([self.query_instruction + text])[0]