app.py

from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_groq import ChatGroq 
import langchain_community.vectorstores
from pinecone import Pinecone, ServerlessSpec
from dotenv import load_dotenv
import os
from langchain_core.prompts import PromptTemplate
from langchain.schema.runnable import RunnablePassthrough
from langchain.schema.output_parser import StrOutputParser
import gradio as gr

class ChatBot():
    load_dotenv()
    # loader = DirectoryLoader('data', glob="*.md")
    loader = TextLoader('data.txt', encoding = 'UTF-8')
    documents = loader.load()
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=600)
    docs = text_splitter.split_documents(documents)

    embeddings = HuggingFaceEmbeddings() 

    load_dotenv()
    # Initialize Pinecone client
    pc = Pinecone(
        api_key=os.environ.get("PINECONE_API_KEY")
    )

    # Define Index Name
    index_name = "noqs-chatbot"

    # Checking Index
    if index_name not in pc.list_indexes().names():
        # Create new Index
        pc.create_index(name=index_name,
                         metric="cosine",
                           dimension=768,
                            spec=ServerlessSpec(
                                cloud="aws",
                                region="us-east-1"
                        ))

        docsearch = langchain_community.vectorstores.Pinecone.from_documents(docs, embeddings, index_name=index_name)
    else:
        # Link to the existing index
        docsearch = langchain_community.vectorstores.Pinecone.from_existing_index(index_name, embeddings)

    # Define the repo ID and connect to a model on Groq API
    model_id = "llama3-8b-8192" 
    llm = ChatGroq(
        model=model_id, 
        temperature=0.5,
        max_tokens=600
    )
    
    # Creating prompt response template
    template = """
        You are a knowledgeable assistant for NoQs Digital. The Manager of our company is Mr. Adit Agarwal. Users will ask you questions about our company, and you must use the given context to answer their questions accurately. Follow these guidelines:
        Always base your answers on the provided context. Do not make up information.
        If the context does not contain the answer, simply say, "I don't know based on the provided information."
        Offer detailed and thorough responses, but stay relevant to the user's question.
        Maintain a professional tone in your responses.
        You have to answer like a Customer Care Specialist.
        If someone answer about program A just answer politelly that due to high demand we are currently not offering program A.

        Context: {context}

        User Question: {question}

        Answer:
    """


    prompt = PromptTemplate(
        template=template, 
        input_variables=["context", "question"]
    )

    # Chaining llm and prompt
    rag_chain = (
        {"context": docsearch.as_retriever(),  "question": RunnablePassthrough()} 
        | prompt 
        | llm
        | StrOutputParser() 
    )

bot = ChatBot()

# def chat_function(prompt):
#     user_input = prompt
#     result = bot.rag_chain.invoke(user_input)
#     return result

def chat_function(prompts,history):
    user_input = prompts 
    result = bot.rag_chain.invoke(user_input)
    return result


iface = gr.ChatInterface(
    fn=chat_function,
    textbox = gr.Textbox(placeholder="Enter message here", container=False, scale = 7),
    chatbot= gr.Chatbot(height=400),
    title="NoQs Chatbot",
    examples=[
        ["Hello, What are the Internship oportunities at NoQs?"],
        ["Why should I work at NoQs"],
        ["How do I contact you?"],
        ["Can I schedule a meet with Mr. Adit?"],
        ["Can you provide me the Internship Repository and other important links"],
        ["Tell me the difference between your programs"]
    ]
)
iface.launch(share  = True)