Hugging Face Instruct Embeddings not woking

Question

I am fresher in the prompt engineering. Suddenly, I am facing a problem in the HuggingFaceInstructEmbeddings. I am using langchain and GoogleGenerativeAI in vscode. My python version 3.10.0 and langchain version 0.1.2. Here is my code-

from langchain_google_genai import GoogleGenerativeAI   
from dotenv import load_dotenv 
import os
from langchain.chains import RetrievalQA
from langchain.document_loaders.csv_loader import CSVLoader    
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import FAISS

load_dotenv()
google_api_key= os.getenv('GOOGLE_API_KEY')
llm = GoogleGenerativeAI(model="models/text-bison-001", google_api_key=google_api_key, temperature = 0.7)

loader = CSVLoader(file_path="codebasics_faqs.csv", source_column="prompt")
docs = loader.load()

instructor_embeddings = HuggingFaceInstructEmbeddings(
    query_instruction="Represent the query for retrieval: "
)
vectordb = FAISS.from_documents(documents = docs, embeddings = instructor_embeddings)
retriever = vectordb.as_retriever()
rdocs = vectordb.get_relevent_documents("do I get a job gurantee?")
print(rdocs)

This code is showing the following error

File "c:\Users\USER\Desktop\project\tut_langchain\tut_googleplam.py", line 5, in <module>
    from langchain.document_loaders.csv_loader import CSVLoader
  File "D:\Program Files\Python310\lib\site-packages\langchain\document_loaders\csv_loader.py", line 1, in <module>
    from langchain_community.document_loaders.csv_loader import (
  File "D:\Program Files\Python310\lib\site-packages\langchain_community\document_loaders\__init__.py", line 163, in <module>    from langchain_community.document_loaders.pebblo import PebbloSafeLoader
  File "D:\Program Files\Python310\lib\site-packages\langchain_community\document_loaders\pebblo.py", line 5, in <module>    
    import pwd
ModuleNotFoundError: No module named 'pwd'

So, I don't understand what should do now? And how to solve this issue.

Answer 1

One solution to avoid the ModuleNotFoundError: No module named 'pwd' error is run your python app in a docker container, because pwd only run on unix environments

Answer 2

The pwd module is specific to Unix systems and is not available on Windows.

If you're developing on a Windows machine, you could try to use a virtual machine or Docker.

If your code allows， you could modify the langchain_community package to remove or replace the parts of the code that require the pwd module. However, this could be complex depending on the package's code.