Update app.py

app.py

@@ -1,3 +1,102 @@
+# import streamlit as st  
+# from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
+# from langchain_core.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate
+# import os 
+# import nltk 
+# import io 
+# import fitz
+# nltk.download("punkt")
+
+# st.title(':blue[Langchain:] A Rag System on “Leave No Context Behind” Paper')
+# st.header("AI Chatbot :robot_face:")
+
+# os.environ["GOOGLE_API_KEY"] = os.getenv("k4")
+# # Creating a template
+
+# chat_template = ChatPromptTemplate.from_messages([
+#     # System Message establishes bot's role and general behavior guidelines
+#     SystemMessage(content="""You are a Helpful AI Bot. 
+#     You take the context and question from user. Your answer should be based on the specific context."""),
+#     # Human Message Prompt Template
+#     HumanMessagePromptTemplate.from_template("""Answer the question based on the given context.
+#     Context:
+#     {context} 
+    
+#     Question: 
+#     {question}
+    
+#     Answer: """)
+# ])
+
+# #user's question.
+# #how many results we want to print.
+
+# from langchain_google_genai import ChatGoogleGenerativeAI  
+
+# chat_model = ChatGoogleGenerativeAI(model="gemini-1.5-pro-latest")
+
+# from langchain_core.output_parsers import StrOutputParser
+
+# output_parser = StrOutputParser()
+
+# chain = chat_template | chat_model | output_parser
+
+# from langchain_community.document_loaders import PDFMinerLoader
+# from langchain_text_splitters import NLTKTextSplitter
+# from langchain_google_genai import GoogleGenerativeAIEmbeddings 
+# from langchain_community.vectorstores import Chroma  
+# from langchain_core.runnables import RunnablePassthrough
+
+# def extract_text_from_pdf(pdf_file):
+#     document = fitz.open(stream=pdf_file, filetype="pdf")
+#     text = ""
+#     for page_num in range(len(document)):
+#         page = document.load_page(page_num)
+#         text += page.get_text()
+#     return text
+
+
+# uploaded_file = st.file_uploader("Choose a pdf file",type = "pdf")
+
+# if uploaded_file is not None:
+    
+#     pdf_file = io.BytesIO(uploaded_file.read())
+#     text = extract_text_from_pdf(pdf_file)
+#     #pdf_loader = PDFMinerLoader(pdf_file)
+#     #dat_nik = pdf_loader.load()
+#     text_splitter = NLTKTextSplitter(chunk_size = 500,chunk_overlap = 100)
+#     chunks = text_splitter.split_documents([text])
+
+#     embedding_model = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+#     db = Chroma.from_documents(chunks, embedding_model, persist_directory="./chroma_db_1")
+
+#     db.persist()
+
+#     db_connection = Chroma(persist_directory="./chroma_db_1", embedding_function=embedding_model)
+
+#     retriever = db_connection.as_retriever(search_kwargs={"k": 5})
+
+#     def format_docs(docs):
+#         return "\n\n".join(doc.page_content for doc in docs)
+
+#     rag_chain = (
+#         {"context": retriever | format_docs, "question": RunnablePassthrough()}
+#         | chat_template
+#         | chat_model
+#         | output_parser
+#     )
+
+#     user_input = st.text_area("Ask Questions to AI")
+#     if st.button("Submit"):
+#         st.subheader(":green[Query:]")
+#         st.subheader(user_input)
+#         response = rag_chain.invoke(user_input)
+#         st.subheader(":green[Response:-]")
+#         st.write(response)
+    
+##################################################### chatgpt code model #############################################
+
 import streamlit as st  
 from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
 from langchain_core.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate
@@ -10,14 +109,13 @@ nltk.download("punkt")
 st.title(':blue[Langchain:] A Rag System on “Leave No Context Behind” Paper')
 st.header("AI Chatbot :robot_face:")
 
-os.environ["GOOGLE_API_KEY"] = os.getenv("k4")
-# Creating a template
+# Set up environment variables
+os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")
 
+# Creating a template
 chat_template = ChatPromptTemplate.from_messages([
-    # System Message establishes bot's role and general behavior guidelines
     SystemMessage(content="""You are a Helpful AI Bot. 
     You take the context and question from user. Your answer should be based on the specific context."""),
-    # Human Message Prompt Template
     HumanMessagePromptTemplate.from_template("""Answer the question based on the given context.
     Context:
     {context} 
@@ -28,19 +126,18 @@ chat_template = ChatPromptTemplate.from_messages([
     Answer: """)
 ])
 
-#user's question.
-#how many results we want to print.
-
+# Initialize chat model
 from langchain_google_genai import ChatGoogleGenerativeAI  
-
 chat_model = ChatGoogleGenerativeAI(model="gemini-1.5-pro-latest")
 
+# Initialize output parser
 from langchain_core.output_parsers import StrOutputParser
-
 output_parser = StrOutputParser()
 
+# Initialize the chain
 chain = chat_template | chat_model | output_parser
 
+# Initialize document loaders and splitters
 from langchain_community.document_loaders import PDFMinerLoader
 from langchain_text_splitters import NLTKTextSplitter
 from langchain_google_genai import GoogleGenerativeAIEmbeddings 
@@ -55,26 +152,25 @@ def extract_text_from_pdf(pdf_file):
         text += page.get_text()
     return text
 
-
-uploaded_file = st.file_uploader("Choose a pdf file",type = "pdf")
+# Streamlit file uploader
+uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
 
 if uploaded_file is not None:
-    
+    # Extract text from the uploaded PDF
     pdf_file = io.BytesIO(uploaded_file.read())
     text = extract_text_from_pdf(pdf_file)
-    #pdf_loader = PDFMinerLoader(pdf_file)
-    #dat_nik = pdf_loader.load()
-    text_splitter = NLTKTextSplitter(chunk_size = 500,chunk_overlap = 100)
+    
+    # Split the document into chunks
+    text_splitter = NLTKTextSplitter(chunk_size=500, chunk_overlap=100)
     chunks = text_splitter.split_documents([text])
 
+    # Initialize embeddings and vectorstore
     embedding_model = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-
-    db = Chroma.from_documents(chunks, embedding_model, persist_directory="./chroma_db_1")
+    db = Chroma.from_documents(chunks, embedding_model, persist_directory="./chroma_db")
 
     db.persist()
 
-    db_connection = Chroma(persist_directory="./chroma_db_1", embedding_function=embedding_model)
-
+    db_connection = Chroma(persist_directory="./chroma_db", embedding_function=embedding_model)
     retriever = db_connection.as_retriever(search_kwargs={"k": 5})
 
     def format_docs(docs):
@@ -91,31 +187,8 @@ if uploaded_file is not None:
     if st.button("Submit"):
         st.subheader(":green[Query:]")
         st.subheader(user_input)
-        response = rag_chain.invoke(user_input)
-        st.subheader(":green[Response:-]")
+        response = rag_chain.invoke({"question": user_input})
+        st.subheader(":green[Response:]")
         st.write(response)
-    
-# dat = PDFMinerLoader("2404.07143.pdf")
-# dat_nik =dat.load()
-# # Split the document into chunks
-
-
-# text_splitter = NLTKTextSplitter(chunk_size=500, chunk_overlap=100)
-
-# chunks = text_splitter.split_documents(dat_nik)
-# Creating Chunks Embedding
-# We are just loading OpenAIEmbeddings
- 
-
-
-
-# vectors = embeddings.embed_documents(chunks)
-# Store the chunks in vector store
-
-
-# Creating a New Chroma Database
-
-
-
- #takes user's question.
-
+else:
+    st.write("Please upload a PDF file to get started.")