aadd_documents() over milvus fails with RecursionError

[MichaelSkralivetsky]

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

from langchain_milvus import Milvus
from langchain_core.embeddings import DeterministicFakeEmbedding
embeddings = DeterministicFakeEmbedding(size=4096)
vectorstore_dvbrby = Milvus(collection_name="kozizbzo", embedding_function=embeddings, connection_args={'uri': 'http://ip:port'})

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

documents = [
    document_1
]
uuids = [str(uuid4()) for _ in range(len(documents))]

import asyncio
async def add_documents_async(documents):
    await vectorstore_dvbrby.aadd_documents(documents, ids=uuids)

task = asyncio.create_task(add_documents_async(documents))
await task

### Error Message and Stack Trace (if applicable)

RecursionError Traceback (most recent call last)
Cell In[8], line 6
3 await vectorstore_dvbrby.aadd_documents(documents, ids=uuids)
5 task = asyncio.create_task(add_documents_async(documents))
----> 6 await task

Cell In[8], line 3, in add_documents_async(documents)
2 async def add_documents_async(documents):
----> 3 await vectorstore_dvbrby.aadd_documents(documents, ids=uuids)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_milvus/vectorstores/milvus.py:1557, in Milvus.aadd_documents(self, documents, **kwargs)
1555 texts = [doc.page_content for doc in documents]
1556 metadatas = [doc.metadata for doc in documents]
-> 1557 return await self.aadd_texts(texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/vectorstores/base.py:258, in VectorStore.aadd_texts(self, texts, metadatas, ids, **kwargs)
252 ids_: Iterator[Optional[str]] = iter(ids) if ids else cycle([None])
254 docs = [
255 Document(id=id_, page_content=text, metadata=metadata_)
256 for text, metadata_, id_ in zip(texts, metadatas_, ids_)
257 ]
--> 258 return await self.aadd_documents(docs, **kwargs)
259 return await run_in_executor(None, self.add_texts, texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_milvus/vectorstores/milvus.py:1557, in Milvus.aadd_documents(self, documents, **kwargs)
1555 texts = [doc.page_content for doc in documents]
1556 metadatas = [doc.metadata for doc in documents]
-> 1557 return await self.aadd_texts(texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/vectorstores/base.py:258, in VectorStore.aadd_texts(self, texts, metadatas, ids, **kwargs)
252 ids_: Iterator[Optional[str]] = iter(ids) if ids else cycle([None])
254 docs = [
255 Document(id=id_, page_content=text, metadata=metadata_)
256 for text, metadata_, id_ in zip(texts, metadatas_, ids_)
257 ]
--> 258 return await self.aadd_documents(docs, **kwargs)
259 return await run_in_executor(None, self.add_texts, texts, metadatas, **kwargs)

[... skipping similar frames: Milvus.aadd_documents at line 1557 (1487 times), VectorStore.aadd_texts at line 258 (1486 times)]

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/vectorstores/base.py:258, in VectorStore.aadd_texts(self, texts, metadatas, ids, **kwargs)
252 ids_: Iterator[Optional[str]] = iter(ids) if ids else cycle([None])
254 docs = [
255 Document(id=id_, page_content=text, metadata=metadata_)
256 for text, metadata_, id_ in zip(texts, metadatas_, ids_)
257 ]
--> 258 return await self.aadd_documents(docs, **kwargs)
259 return await run_in_executor(None, self.add_texts, texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_milvus/vectorstores/milvus.py:1557, in Milvus.aadd_documents(self, documents, **kwargs)
1555 texts = [doc.page_content for doc in documents]
1556 metadatas = [doc.metadata for doc in documents]
-> 1557 return await self.aadd_texts(texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/vectorstores/base.py:254, in VectorStore.aadd_texts(self, texts, metadatas, ids, **kwargs)
251 metadatas_ = iter(metadatas) if metadatas else cycle([{}])
252 ids_: Iterator[Optional[str]] = iter(ids) if ids else cycle([None])
--> 254 docs = [
255 Document(id=id_, page_content=text, metadata=metadata_)
256 for text, metadata_, id_ in zip(texts, metadatas_, ids_)
257 ]
258 return await self.aadd_documents(docs, **kwargs)
259 return await run_in_executor(None, self.add_texts, texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/vectorstores/base.py:255, in (.0)
251 metadatas_ = iter(metadatas) if metadatas else cycle([{}])
252 ids_: Iterator[Optional[str]] = iter(ids) if ids else cycle([None])
254 docs = [
--> 255 Document(id=id_, page_content=text, metadata=metadata_)
256 for text, metadata_, id_ in zip(texts, metadatas_, ids_)
257 ]
258 return await self.aadd_documents(docs, **kwargs)
259 return await run_in_executor(None, self.add_texts, texts, metadatas, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/documents/base.py:285, in Document.init(self, page_content, **kwargs)
282 """Pass page_content in as positional or named arg."""
283 # my-py is complaining that page_content is not defined on the base class.
284 # Here, we're relying on pydantic base class to handle the validation.
--> 285 super().init(page_content=page_content, **kwargs)

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/load/serializable.py:125, in Serializable.init(self, *args, **kwargs)
123 def init(self, *args: Any, **kwargs: Any) -> None:
124 """"""
--> 125 super().init(*args, **kwargs)

[... skipping hidden 1 frame]

File ~/.pythonlibs/mlrun-base/lib/python3.9/site-packages/langchain_core/documents/base.py:47, in BaseMedia.cast_id_to_str(cls, id_value)
44 @field_validator("id", mode="before")
45 def cast_id_to_str(cls, id_value: Any) -> Optional[str]:
46 if id_value is not None:
---> 47 return str(id_value)
48 else:
49 return id_value

RecursionError: maximum recursion depth exceeded while calling a Python object

### Description

RecursionError is not expected. 

### System Info

System Information

OS: Linux
OS Version: #1 SMP Wed Sep 11 18:02:00 EDT 2024
Python Version: 3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 16:33:10)
[GCC 12.3.0]

Package Information

langchain_core: 0.3.25
langchain: 0.3.12
langchain_community: 0.3.12
langsmith: 0.1.129
langchain_chroma: 0.2.0
langchain_milvus: 0.1.7
langchain_text_splitters: 0.3.3

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.10.6
async-timeout: 4.0.3
chromadb: 0.5.23
dataclasses-json: 0.6.7
fastapi: 0.115.5
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
numpy: 1.26.4
orjson: 3.10.7
packaging: 24.0
pydantic: 2.10.3
pydantic-settings: 2.6.1
pymilvus: 2.5.0
PyYAML: 6.0.2
requests: 2.32.3
SQLAlchemy: 1.4.54
tenacity: 9.0.0
typing-extensions: 4.12.2

[keenborder786]

@MichaelSkralivetsky, take care of in the following PR: langchain-ai/langchain-milvus#29

[zc277584121]

merged the PR