embeddings:AttributeError: 'tuple' object has no attribute 'embed_documents'

[Hikizzz]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

embeddings=HuggingFaceBgeEmbeddings(model_name="BAAI/bge-m3"),
vector_a,vector_b = embeddings.embed_documents([text1, text2])

Error Message and Stack Trace (if applicable)

Traceback (most recent call last):
File "/home/HwHiAiUser/aircasLLM/src/langchain/toolkit.py", line 126, in
print(textSimChain.invoke({
File "/usr/local/miniconda3/envs/dg/lib/python3.10/site-packages/langchain_core/runnables/base.py", line 4713, in invoke
return self._call_with_config(
File "/usr/local/miniconda3/envs/dg/lib/python3.10/site-packages/langchain_core/runnables/base.py", line 1927, in call_with_config
context.run(
File "/usr/local/miniconda3/envs/dg/lib/python3.10/site-packages/langchain_core/runnables/config.py", line 396, in call_func_with_variable
return func(input, **kwargs) # type: ignore[call-arg]
File "/usr/local/miniconda3/envs/dg/lib/python3.10/site-packages/langchain_core/runnables/base.py", line 4567, in invoke
output = call_func_with_variable_args(
File "/usr/local/miniconda3/envs/dg/lib/python3.10/site-packages/langchain_core/runnables/config.py", line 396, in call_func_with_variable
return func(input, **kwargs) # type: ignore[call-arg]
File "/home/HwHiAiUser/aircasLLM/src/langchain/toolkit.py", line 73, in textSimChain
vector_a,vector_b = embeddings.embed_documents([text1, text2])
AttributeError: 'tuple' object has no attribute 'embed_documents'

Description

• I'm trying to encoding two strings to vector using embeddings.embed_documents().but not works
• I have done itcorrectly on ubuntu18,x86 pc with nvidia gpu and intel cpu,using ollamaEmbedding().
• but when transferring it to .ky10.aarch64,it doesn‘t work.
• i have tested lastest version and my old version,including langchain(v0.2.1,0.3.4),langchain_core(v0.2.26,v0.3.3),langchain_community(v0.2.10,v0.3.3)
• i have test HuggingFaceBgeEmbeddings,HuggingFaceEmbeddings,AscendEmbeddings(using npu on this server)，the erro information is same.
• i have test online models(autoDownload by HuggingFaceEmbeddings) and local model,include BAAI/bge-m3 and aspire/acge_text_embedding.
• other langchain library or functions work including langchain_core.runnables,langchain_openai,....
• i have checked https://github.com/langchain-ai/langchain/issues/26759 and https://github.com/langchain-ai/langchain/issues/23215.but it seems helpless
• it seems the error **only occurs in funtcntions decorated by "@chain" !**I make a custiomEmbedding class inherited from embeddings and baseModel from langchain_core and test it isolated i,it works.but putting it in a chainFuction，it works bad.

System Info

System Information

OS: Linux
OS Version: #1 SMP Sun Jun 28 14:27:40 CST 2020
Python Version: 3.10.15 (main, Oct 3 2024, 07:21:53) [GCC 11.2.0]

Package Information

langchain_core: 0.3.12
langchain: 0.3.4
langchain_community: 0.3.3
langsmith: 0.1.136
langchain_chroma: 0.1.2
langchain_huggingface: 0.0.3
langchain_ollama: 0.1.1
langchain_openai: 0.1.19
langchain_text_splitters: 0.3.0
langserve: 0.2.2

Optional packages not installed

langgraph

Other Dependencies

aiohttp: 3.10.10
async-timeout: 4.0.3
chromadb: 0.5.15
dataclasses-json: 0.6.7
fastapi: 0.115.2
httpx: 0.27.2
huggingface-hub: 0.26.0
jsonpatch: 1.33
numpy: 1.26.4
ollama: 0.3.3
openai: 1.52.0
orjson: 3.10.9
packaging: 24.1
pydantic: 2.7.4
pydantic-settings: 2.6.0
pyproject-toml: 0.0.10
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
sentence-transformers: 2.7.0
SQLAlchemy: 2.0.36
sse-starlette: 1.8.2
tenacity: 8.5.0
tiktoken: 0.8.0
tokenizers: 0.20.1
transformers: 4.45.2
typing-extensions: 4.12.2

[isLenk]

Hello, it appears you have a comma on the first line: embeddings=HuggingFaceBgeEmbeddings(model_name="BAAI/bge-m3"),

class A:
    def embed_documents(self, texts):
        return texts

V=A(),
a,b = V.embed_documents([1,2])

AttributeError: 'tuple' object has no attribute 'embed_documents'

Does the issue persist without it?