app.py

import gradio as gr
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain import hub
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
import getpass
import os
from langchain_groq import ChatGroq

os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = "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"
os.environ["GROQ_API_KEY"] = "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"


# Set up Inference Client
embeddings = HuggingFaceEmbeddings()

# Load the vector database with embeddings
vectorstore = FAISS.load_local("vectorstore.db", embeddings=embeddings,allow_dangerous_deserialization=True)
# Load the vector database

retriever = vectorstore.as_retriever()

# Define LLM configuration
llm = ChatGroq(model="gemma-7b-it")  

prompt_template = """
You are an assistant for question-answering tasks.
Answer the given questions.

<context>
{context}
</context>

Question: {input}
"""

# Function to create the prompt template
prompt = ChatPromptTemplate.from_template(prompt_template)
doc_chain = create_stuff_documents_chain(llm, prompt)
chain = create_retrieval_chain(retriever, doc_chain)

# Chatbot response function
def answer_query(
    message,
    history
):
     # Check if message is a list and convert it to the first element as a string
    if isinstance(message, list):
        message = str(message[0])  # Convert the first element to a string


    # Use the RAG model to retrieve relevant context and answer the question
    response = chain.invoke({"input": message})

    # Extract the answer from the response
    answer = str(response['answer'])

     # Ensure that the answer is a string
    if isinstance(answer, list):
        answer = ' '.join([str(item) for item in answer])  # Convert list to string
    elif isinstance(answer, tuple):
        answer = ' '.join([str(item) for item in answer])  
    # Add conversation to history
    history.append((message, answer))

    # Return the updated history
    return "", history

chatbot = gr.Chatbot(placeholder="<strong>Chatbot that answers questions on agile processes</strong><br>Ask Me Anything")
# Gradio Chat Interface
with gr.Blocks() as demo:
    gr.HTML("<h1 align = 'center'>Smart Assistant</h1>")

    chatbot = gr.Chatbot()
    msg = gr.Textbox(label = "Enter your question here")
    msg.submit(answer_query,[msg,chatbot],[msg,chatbot])

if __name__ == "__main__":
    demo.launch()