added comments in app.py

app.py

@@ -3,6 +3,8 @@ import os
 api_token = os.getenv("HF_TOKEN")
 
 
+# adding all the imports
+
 from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -15,10 +17,13 @@ from langchain.memory import ConversationBufferMemory
 from langchain_community.llms import HuggingFaceEndpoint
 import torch
 
+# add more llms if needed
+
 list_llm = ["meta-llama/Meta-Llama-3-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.2"]  
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
 
 # Load and split PDF document
+
 def load_doc(list_file_path):
     # Processing for one document only
     # loader = PyPDFLoader(file_path)
@@ -34,14 +39,20 @@ def load_doc(list_file_path):
     doc_splits = text_splitter.split_documents(pages)
     return doc_splits
 
+    
+
 # Create vector database
+
 def create_db(splits):
     embeddings = HuggingFaceEmbeddings()
     vectordb = FAISS.from_documents(splits, embeddings)
     return vectordb
 
 
+    
+
 # Initialize langchain LLM chain
+
 def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, progress=gr.Progress()):
     if llm_model == "meta-llama/Meta-Llama-3-8B-Instruct":
         llm = HuggingFaceEndpoint(
@@ -77,7 +88,10 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
     )
     return qa_chain
 
+
+
 # Initialize database
+
 def initialize_database(list_file_obj, progress=gr.Progress()):
     # Create a list of documents (when valid)
     list_file_path = [x.name for x in list_file_obj if x is not None]
@@ -87,7 +101,11 @@ def initialize_database(list_file_obj, progress=gr.Progress()):
     vector_db = create_db(doc_splits)
     return vector_db, "Database created!"
 
+
+
+
 # Initialize LLM
+
 def initialize_LLM(llm_option, llm_temperature, max_tokens, top_k, vector_db, progress=gr.Progress()):
     # print("llm_option",llm_option)
     llm_name = list_llm[llm_option]