NVIDIAEmbeddings embed_documents failing to generate embeddings

[conaku]

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

from langchain_community.document_loaders.pdf import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
import os

os.environ['REQUEST_CA_BUNDLE']="chain.pem"
embedding = NVIDIAEmbeddings(base_url = "https://ashish-embedqa-deployment-2/v1",model="nv-embedqa-e5-v5",model_type="passage", verify="chain.pem")
pdf_files = [os.path.join("./data", file) for file in os.listdir("./data") if file.endswith('.pdf')]
loaders = [PyPDFLoader(pdf_file) for pdf_file in pdf_files]
docs = []
for loader in loaders:
    docs.extend(loader.load())
text_splitter = RecursiveCharacterTextSplitter()
all_splits = text_splitter.split_documents(docs)
page_contents = [doc.page_content for doc in all_splits]
embedding.embed_documents(page_contents)

Description

I am getting below error.
requests.exceptions.SSLError: HTTPSConnectionPool(host='ashish-embedqa-deployment-2', port=443): Max retries exceeded with url: /v1//embeddings (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1006)')))

System Info

pip freeze|grep -i langchain
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.11
langchain-milvus==0.1.1
langchain-nvidia-ai-endpoints==0.1.2
langchain-text-splitters==0.2.2

[dosubot[bot]]

The error you're encountering is related to SSL certificate verification. Here are a few steps you can take to resolve this issue without disabling SSL verification entirely:

1. Ensure the CA Bundle Path is Correct:
   Verify that the path to your CA bundle (chain.pem) is correct and accessible.

2. Use a Custom CA Bundle:
   You can provide a custom CA bundle that includes the necessary certificates. Modify your code to pass the verify parameter with the path to the CA bundle file when making requests.

Here is an example of how you can adjust your code:

from langchain_community.document_loaders.pdf import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
import os

# Ensure the CA bundle path is correct
ca_bundle_path = "path/to/your/chain.pem"
os.environ['REQUEST_CA_BUNDLE'] = ca_bundle_path

embedding = NVIDIAEmbeddings(
    base_url="https://ashish-embedqa-deployment-2/v1",
    model="nv-embedqa-e5-v5",
    model_type="passage",
    verify=ca_bundle_path  # Use custom CA bundle
)

pdf_files = [os.path.join("./data", file) for file in os.listdir("./data") if file.endswith('.pdf')]
loaders = [PyPDFLoader(pdf_file) for pdf_file in pdf_files]
docs = []
for loader in loaders:
    docs.extend(loader.load())
text_splitter = RecursiveCharacterTextSplitter()
all_splits = text_splitter.split_documents(docs)
page_contents = [doc.page_content for doc in all_splits]
embedding.embed_documents(page_contents)

Make sure to replace "path/to/your/chain.pem" with the actual path to your CA bundle file. This ensures that SSL certificates are verified using the specified CA bundle ^[1][2].

To continue talking to Dosu, mention @dosu.