langchain1.py

#!/usr/bin/env python3

from dotenv import load_dotenv
from langchain.document_loaders import PyPDFLoader
#from langchain.document_loaders import PDFMinerLoader
#from langchain.document_loaders import Docx2txtLoader
from langchain.llms import OpenAI
from langchain.chains.summarize import load_summarize_chain
from langchain.text_splitter import CharacterTextSplitter
from langchain.prompts import PromptTemplate
import textwrap
import os


try:
    LLM_KEY = os.environ.get("OPENAI_API_KEY")
except Exception as e:
    print(f"ERROR: Cannot read OpenAI API key from the environment")
    raise(e)

filenames = [
        "AMD Technical Update - Speculative Return Stack Overflow.pdf",
        "AMD Technical Guidance for Mitigating BTC (Branch Type Confusion).pdf",
        ]

filename = f"{os.environ.get('HOME')}/Downloads/{filenames[0]}"

print(f"Reading file {filename}")

text = ""
#loader = Docx2txtLoader(filename)
#loader = PDFMinerLoader(filename)
#loader = PDFMinerLoader(file_path=filename,
#                        extract_images=False,
#                        concatenate_pages=True)

loader = PyPDFLoader(filename)
text = loader.load_and_split()

# Define prompt
prompt_template = """Write a concise summary of the following:
"{text}"
CONCISE SUMMARY:"""

prompt_template = PromptTemplate(template=prompt_template,
                        input_variables=["text"])

# Define the LLM - here we are using OpenAI's ChatGPT
llm = OpenAI(temperature=0)

chain = load_summarize_chain(llm,  chain_type="stuff", prompt=prompt_template)
summarized_text = chain.run(text)
summarized_text = textwrap.fill(summarized_text,
                             width=100,
                             break_long_words=False,
                             replace_whitespace=False)
print(summarized_text)