Search posts, tags, users, and pages
Mayur Ghadge
How to connect indexing.py file with main.py in streamlit. I am getting an error, can you please help me.
Versace
i run the indexing.py file with the terminal and the pinecone write in the file
When I Run indexing.py file with the terminal This is Code indexing.py
from langchain.document_loaders import DirectoryLoader from langchain.text_splitter import RecursiveCharacterTextSplitter import os
directory = '/data/SwiftProgrammingLanguage.pdf'
def load_docs(directory): loader = DirectoryLoader(directory) documents = loader.load() return documents
documents = load_docs(directory) len(documents)
def split_docs(documents,chunk_size=500,chunk_overlap=20): text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap) docs = text_splitter.split_documents(documents) return docs
docs = split_docs(documents) print(len(docs))
**when I run python3 indexing.py Getting error
python3 indexing.py
/Users/sarit.bahuguna/ai_chatbot/data/SwiftProgrammingLanguage.pdf
[nltk_data] Error loading punkt: <urlopen error [Errno 60] Operation
Sarit Bahuguna