How to use bigger embedding model for example "nvidia/NV-Embed-v2" as an embedding model in SemanticChunker?

[dilli-prasad-amur5]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

model_name = "sentence-transformers/all-MiniLM-L6-v2"

# model_name = 'BAAI/bge-large-en-v1.5'
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": False}

hf_embeddings = HuggingFaceEmbeddings(
    model_name= model_name,
    model_kwargs= model_kwargs,
    encode_kwargs= encode_kwargs,
)

text_splitter = SemanticChunker(hf_embeddings)

Description

I am using the above code to do the semantic chunking but i need to use the bigger embedding models like "nvidia/NV-Embed-v2" to group the text. I tried to use this bigger model in SemanticChunking option and getting error in doing so.

System Info

sentence-transformers 3.3.1
langchain 0.3.14
langchain-community 0.3.14
langchain-core 0.3.29
langchain-experimental 0.3.4
langchain-huggingface 0.1.2