lanchain pdf rag

import PyPDF2
from langchain import LLMChain
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import Llama

# Function to read and extract text from PDF files
def extract_text_from_pdfs(pdf_files):
    pdf_texts = []
    for pdf_file in pdf_files:
        with open(pdf_file, 'rb') as file:
            reader = PyPDF2.PdfFileReader(file)
            text = ""
            for page_num in range(reader.numPages):
                text += reader.getPage(page_num).extractText()
            pdf_texts.append(text)
    return pdf_texts

# Function to create vector store from extracted texts
def create_vector_store(texts):
    embeddings = OpenAIEmbeddings()
    vector_store = FAISS.from_texts(texts, embeddings)
    return vector_store

# Function to create RAG application
def create_rag_application(pdf_files):
    # Step 1: Extract text from PDFs
    pdf_texts = extract_text_from_pdfs(pdf_files)
    
    # Step 2: Create vector store
    vector_store = create_vector_store(pdf_texts)
    
    # Step 3: Load LLAMA model
    llm = Llama(model_name="llama-3.1")
    
    # Step 4: Create LLMChain with vector store and LLAMA model
    rag_chain = LLMChain(llm=llm, vector_store=vector_store)
    
    return rag_chain

# Example usage
pdf_files = ["/Users/teagardan/Documents/Teagardan/Mission USA/CURSOR AI/LANGCHAIN LLM RAG"]  # List of 100 PDF file paths
rag_application = create_rag_application(pdf_files)

import ollama

# Function to create RAG application using Ollama
def create_rag_application_with_ollama(pdf_files):
    # Step 1: Extract text from PDFs
    pdf_texts = extract_text_from_pdfs(pdf_files)
    
    # Step 2: Create vector store
    vector_store = create_vector_store(pdf_texts)
    
    # Step 3: Load LLAMA model using Ollama
    llm = ollama.Llama(model_name="llama-3.1")
    
    # Step 4: Create LLMChain with vector store and LLAMA model
    rag_chain = LLMChain(llm=llm, vector_store=vector_store)
    
    return rag_chain

# Example usage with Ollama
pdf_files = ["/Users/teagardan/Documents/Teagardan/Mission USA/CURSOR AI/LANGCHAIN LLM RAG"]  # List of 100 PDF file paths