from langchain_community.embeddings import HuggingFaceBgeEmbeddings - results warning - pydantic/_internal/_fields.py:132: UserWarning: Field "model_name" in HuggingFaceInferenceAPIEmbeddings has conflict with protected namespace "model_".

[sam-bercovici]

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_community.embeddings import HuggingFaceBgeEmbeddings'''
generates:
pydantic/_internal/fields.py:132: UserWarning: Field "model_name" in HuggingFaceInferenceAPIEmbeddings has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = ().
warnings.warn(

looking at pydantic/pydantic#7121 and

langchain/libs/community/langchain_community/cross_encoders/huggingface.py

Line 48 in a001006

model_config = ConfigDict(extra="forbid", protected_namespaces=())

similar is missing in HuggingFaceBgeEmbeddings

Error Message and Stack Trace (if applicable)

warning:
pydantic/_internal/fields.py:132: UserWarning: Field "model_name" in HuggingFaceInferenceAPIEmbeddings has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = ().
warnings.warn(

Description

• as noted importing HuggingFaceBgeEmbeddings generates a warning

System Info

python -m langchain_core.sys_info

System Information

OS: Linux
OS Version: #1 SMP Fri Mar 29 23:14:13 UTC 2024
Python Version: 3.12.6 | packaged by conda-forge | (main, Sep 22 2024, 14:16:49) [GCC 13.3.0]

Package Information

langchain_core: 0.3.5
langchain: 0.3.0
langchain_community: 0.3.0
langsmith: 0.1.125
langchain_anthropic: 0.2.1
langchain_chroma: 0.1.4
langchain_experimental: 0.3.0
langchain_groq: 0.2.0
langchain_huggingface: 0.1.0
langchain_openai: 0.2.0
langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.10.5
anthropic: 0.34.2
async-timeout: Installed. No version info available.
chromadb: 0.5.7
dataclasses-json: 0.6.7
defusedxml: 0.7.1
fastapi: 0.115.0
groq: 0.11.0
httpx: 0.27.2
huggingface-hub: 0.25.1
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.47.1
orjson: 3.10.7
packaging: 24.1
pydantic: 2.9.2
pydantic-settings: 2.5.2
PyYAML: 6.0.2
requests: 2.32.3
sentence-transformers: 3.1.1
SQLAlchemy: 2.0.35
tenacity: 8.5.0
tiktoken: 0.7.0
tokenizers: 0.19.1
transformers: 4.44.2
typing-extensions: 4.12.2

[nehaejaz]

Having the same warning

[etiennemillerioux]

Face the same warning too, very annoying it's dispaly it upon every single startup

[tibor-reiss]

Fixed in langchain-community 0.3.1 in #26744

[MaxRuenz]

Is that something that should also be ported to other Embeddings and Chats?
I am getting the same warnings when working with Bedrock and langchain-community 0.3.1

[sam-bercovici]

Why not have a langchain Base Model doing this instead of inheriting from Pydantic and doing this stuff repeatedly?

[scottberres-tr]

The warnings fire for model_name, model_path, model_url

These are the classes that fire a warning at startup for me.

langchain_core.embeddings.embeddings.Embeddings
langchain_core.language_models.llms.BaseLLM
langchain_community.llms.vertexai._VertexAIBase

using
langchain_core-0.3.8
langchain-0.3.1
langchain_community-0.3.1