Create lanchain pdf rag

lanchain pdf rag

@@ -0,0 +1,68 @@
+
+
+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
+
+