Upload 2 files

app.py

@@ -0,0 +1,137 @@
+import streamlit as st
+import os
+from dotenv import load_dotenv
+load_dotenv()
+
+os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")    
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_PROJECT"]= "RAG Document Q&A"
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+from langchain_groq import ChatGroq
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_core.prompts import ChatPromptTemplate, PromptTemplate, MessagesPlaceholder
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain.document_loaders import PyPDFLoader
+
+from langchain.vectorstores import FAISS
+from langchain.chains import create_retrieval_chain, create_history_aware_retriever
+from langchain_core.chat_history import BaseChatMessageHistory
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+
+
+
+st.title("Conversational RAG With PDF uploads and chat history")
+st.write("Upload PDFs and chat with their content")
+
+api_key = st.text_input("Enter your Groq API key:", type="password")
+
+if api_key:
+    llm=ChatGroq(groq_api_key=api_key, model_name="openai/gpt-oss-20b")
+
+    session_id= st.text_input("Session ID", value="default_session")
+
+    if 'store' not in st.session_state:
+        st.session_state.store={}
+
+    uploaded_files=st.file_uploader("Choose A PDF file", type="pdf", accept_multiple_files=True)
+
+    if uploaded_files:
+        documents=[]
+        for uploaded_file in uploaded_files:
+            tempdf=f"./temp.pdf"
+            with open(tempdf, "wb") as file:
+                file.write(uploaded_file.getvalue())
+                file_name = uploaded_file.name
+            
+            loader= PyPDFLoader(tempdf)
+            docs = loader.load()
+            documents.extend(docs)
+
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=5000, chunk_overlap=500)
+        splits = text_splitter.split_documents(documents)
+        vectorstore =  FAISS.from_documents(documents=splits, embedding=OpenAIEmbeddings())
+        retriever = vectorstore.as_retriever()
+
+        contextualize_q_system_prompt=(
+            "Given a chat history and the latest user question"
+            "which might reference context in the chat history, "
+            "formulate a standalone question which can be understood "
+            "without the chat history. Do NOT answer the question, "
+            "just reformulate it if needed and otherwise return it as is."
+        )
+
+        contextualize_q_prompt = ChatPromptTemplate.from_messages(
+                [
+                    ("system", contextualize_q_system_prompt),
+                    MessagesPlaceholder("chat_history"),
+                    ("human", "{input}"),
+                ]
+            )
+        
+        history_aware_retriever= create_history_aware_retriever(llm, retriever, contextualize_q_prompt)
+
+        ## Answer question
+
+        # Answer question
+        system_prompt = (
+                "You are an assistant for question-answering tasks. "
+                "Use the following pieces of retrieved context to answer "
+                "the question. If you don't know the answer, say that you "
+                "don't know. Use three sentences maximum and keep the "
+                "answer concise."
+                "\n\n"
+                "{context}"
+            )
+        qa_prompt = ChatPromptTemplate.from_messages(
+                [
+                    ("system", system_prompt),
+                    MessagesPlaceholder("chat_history"),
+                    ("human", "{input}"),
+                ]
+            )
+        
+        question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
+
+        rag_chain=create_retrieval_chain(history_aware_retriever, question_answer_chain)
+
+        def get_session_history(session:str)->BaseChatMessageHistory:
+            if session_id not in st.session_state.store:
+                st.session_state.store[session_id]=ChatMessageHistory()
+            return st.session_state.store[session_id]
+        
+
+        conversational_rag_chain = RunnableWithMessageHistory(
+            rag_chain, get_session_history,
+            input_messages_key="input",
+            history_messages_key="chat_history",
+            output_messages_key="answer"
+        )
+        user_input = st.text_input("Enter your questions:")
+        if user_input:
+            session_history=get_session_history(session_id)
+            response = conversational_rag_chain.invoke(
+                {"input": user_input},
+                config={
+                    "configurable": {"session_id":session_id}
+                },  # constructs a key "abc123" in `store`.
+            )
+            #st.write(st.session_state.store)
+            st.write("Assistant:", response['answer'])
+            #st.write("Chat History:", session_history.messages)
+else:
+    st.warning("Please enter the GRoq API Key")
+        
+
+
+
+
+
+
+
+
+
+

requirements.txt

@@ -1,3 +1,37 @@
-altair
-pandas
-streamlit
+langchain
+python-dotenv
+ipykernel
+langchain-community
+langchain_openai
+dotenv
+langchain_text_splitters
+chromadb
+sentence_transformers
+langchain_huggingface
+faiss-cpu
+langchain_chroma
+grandalf
+huggingface_hub
+streamlit
+langchain_groq
+fastapi
+uvicorn
+langserve
+sse_starlette
+bs4
+pypdf
+arxiv
+wikipedia
+duckduckgo-search
+validators
+youtube_transcript_api
+unstructured
+pytube
+numexpr
+mysql-connector-python
+SQLAlchemy
+langchain_nvidia_ai_endpoints
+pinecone-client
+pinecone-text
+pinecone-notebooks
+pinecone