From dd1d818a82bb7ad89e97982c1477e6aaba69664f Mon Sep 17 00:00:00 2001
From: xuxiang <418720028@qq.com>
Date: Tue, 2 Jan 2024 08:50:13 +0800
Subject: [PATCH] Fixing the Issue with DashScopeEmbeddings Handling More than
 25 Rows of Data (#14662)

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change,
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

This change addresses the issue where DashScopeEmbeddingAPI limits
requests to 25 lines of data, and DashScopeEmbeddings did not handle
cases with more than 25 lines, leading to errors. I have implemented a
fix to manage data exceeding this limit efficiently.

---------

Co-authored-by: xuxiang <xuxiang@aliyun.com>
---
 .../embeddings/dashscope.py                   | 35 +++++++++++--------
 .../embeddings/test_dashscope.py              | 33 +++++++++++++++--
 2 files changed, 52 insertions(+), 16 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/dashscope.py b/libs/community/langchain_community/embeddings/dashscope.py
index 9b1b7db8874..0042c05debc 100644
--- a/libs/community/langchain_community/embeddings/dashscope.py
+++ b/libs/community/langchain_community/embeddings/dashscope.py
@@ -45,20 +45,27 @@ def embed_with_retry(embeddings: DashScopeEmbeddings, **kwargs: Any) -> Any:
 
     @retry_decorator
     def _embed_with_retry(**kwargs: Any) -> Any:
-        resp = embeddings.client.call(**kwargs)
-        if resp.status_code == 200:
-            return resp.output["embeddings"]
-        elif resp.status_code in [400, 401]:
-            raise ValueError(
-                f"status_code: {resp.status_code} \n "
-                f"code: {resp.code} \n message: {resp.message}"
-            )
-        else:
-            raise HTTPError(
-                f"HTTP error occurred: status_code: {resp.status_code} \n "
-                f"code: {resp.code} \n message: {resp.message}",
-                response=resp,
-            )
+        result = []
+        i = 0
+        input_data = kwargs["input"]
+        while i < len(input_data):
+            kwargs["input"] = input_data[i : i + 25]
+            resp = embeddings.client.call(**kwargs)
+            if resp.status_code == 200:
+                result += resp.output["embeddings"]
+            elif resp.status_code in [400, 401]:
+                raise ValueError(
+                    f"status_code: {resp.status_code} \n "
+                    f"code: {resp.code} \n message: {resp.message}"
+                )
+            else:
+                raise HTTPError(
+                    f"HTTP error occurred: status_code: {resp.status_code} \n "
+                    f"code: {resp.code} \n message: {resp.message}",
+                    response=resp,
+                )
+            i += 25
+        return result
 
     return _embed_with_retry(**kwargs)
 
diff --git a/libs/community/tests/integration_tests/embeddings/test_dashscope.py b/libs/community/tests/integration_tests/embeddings/test_dashscope.py
index 4c189c53550..82e507c863c 100644
--- a/libs/community/tests/integration_tests/embeddings/test_dashscope.py
+++ b/libs/community/tests/integration_tests/embeddings/test_dashscope.py
@@ -15,10 +15,39 @@ def test_dashscope_embedding_documents() -> None:
 
 def test_dashscope_embedding_documents_multiple() -> None:
     """Test dashscope embeddings."""
-    documents = ["foo bar", "bar foo", "foo"]
+    documents = [
+        "foo bar",
+        "bar foo",
+        "foo",
+        "foo0",
+        "foo1",
+        "foo2",
+        "foo3",
+        "foo4",
+        "foo5",
+        "foo6",
+        "foo7",
+        "foo8",
+        "foo9",
+        "foo10",
+        "foo11",
+        "foo12",
+        "foo13",
+        "foo14",
+        "foo15",
+        "foo16",
+        "foo17",
+        "foo18",
+        "foo19",
+        "foo20",
+        "foo21",
+        "foo22",
+        "foo23",
+        "foo24",
+    ]
     embedding = DashScopeEmbeddings(model="text-embedding-v1")
     output = embedding.embed_documents(documents)
-    assert len(output) == 3
+    assert len(output) == 28
     assert len(output[0]) == 1536
     assert len(output[1]) == 1536
     assert len(output[2]) == 1536