UnstructuredReader --- ModuleNotFoundError: No module named 'unstructured'

[venkee70]

Running the below code & getting an Error

import os
from dotenv import load_dotenv
from llama_index.readers.web import SimpleWebPageReader
from llama_index.core import SimpleDirectoryReader
from llama_index.core import (
    Document,
    VectorStoreIndex,
    ServiceContext,
    StorageContext,
    download_loader,
)
from llama_index.core.node_parser import SimpleNodeParser
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.vector_stores.pinecone import PineconeVectorStore
from pinecone import Pinecone, ServerlessSpec
from llama_index.readers.file import UnstructuredReader

load_dotenv()
pc = Pinecone(api_key=os.environ.get("PINECONE_API_KEY"))

"""
pc.create_index(
    name="llamaindex-doc-help",
    dimension=1536,
    metric="cosine",
    spec=ServerlessSpec(
        cloud=os.environ.get("PINECONE_CLOUD"),
        region=os.environ.get("PINECONE_ENVIRONMENT"),
    ),
)
"""

if __name__ == "__main__":

    print("*****" * 10)
    print("Hello World LLama Index course")
    print(f"OPENAI_API_KEY is : {os.environ['OPENAI_API_KEY']}")
    print(f"PINECONE_API_KEY is : {os.environ['PINECONE_API_KEY']}")
    print(f"PINECONE_ENVIRONMENT is : {os.environ['PINECONE_ENVIRONMENT']}")
    print(f"PINECONE_CLOUD is : {os.environ['PINECONE_CLOUD']}")
    print("*****" * 10)

    dir_reader = SimpleDirectoryReader(input_dir="./llamaindex-docs-tmp",file_extractor={".html": UnstructuredReader()})
    documents = dir_reader.load_data()
    pass

~~~end of code ~~~~~

ERROR
~~~~~~

**************************************************
Hello World LLama Index course
OPENAI_API_KEY is : xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
PINECONE_API_KEY is : xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
PINECONE_ENVIRONMENT is : xxxxxxxx
PINECONE_CLOUD is : xxxxx
**************************************************
Traceback (most recent call last):
  File "C:\Users\Ramana\.virtualenvs\doc-help-llamaindex-DW5cxznO\lib\site-packages\llama_index\core\readers\file\base.py", line 533, in load_file
    docs = reader.load_data(input_file, **kwargs)
  File "C:\Users\Ramana\.virtualenvs\doc-help-llamaindex-DW5cxznO\lib\site-packages\llama_index\readers\file\unstructured\base.py", line 71, in load_data
    from unstructured.partition.auto import partition
ModuleNotFoundError: No module named 'unstructured'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "P:\MyProjects\doc-help-llamaindex\ingestion.py", line 45, in <module>
    documents = dir_reader.load_data()
  File "C:\Users\Ramana\.virtualenvs\doc-help-llamaindex-DW5cxznO\lib\site-packages\llama_index\core\readers\file\base.py", line 683, in load_data
    SimpleDirectoryReader.load_file(
  File "C:\Users\Ramana\.virtualenvs\doc-help-llamaindex-DW5cxznO\lib\site-packages\llama_index\core\readers\file\base.py", line 537, in load_file
    raise ImportError(str(e))
ImportError: No module named 'unstructured'

Process finished with exit code 1

[venkee70]

After debugging, found that python library "unstructured" needs to be installed. Adding that using "pipenv install unstructured" resolved the issue