app.py

from llama_index.core import SimpleDirectoryReader
from llama_index.core.node_parser import SentenceSplitter
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core import SummaryIndex, VectorStoreIndex
from llama_index.core.tools import QueryEngineTool
from llama_index.core.query_engine.router_query_engine import RouterQueryEngine
from llama_index.core.selectors import LLMSingleSelector
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.groq import Groq
from llama_index.core import Settings
from langchain.embeddings.huggingface import HuggingFaceEmbeddings

import os
from dotenv import load_dotenv
load_dotenv()

GROQ_API_KEY = os.getenv("groqkey")

embed_model= HuggingFaceEmbeddings(model_name="BAAI/bge-large-en-v1.5")



llm = Groq(model="llama3-70b-8192", api_key=GROQ_API_KEY)

Settings.llm = llm
Settings.embed_model = embed_model

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader("files",required_exts=[".pdf", ".csv"]).load_data()

from llama_index.core import VectorStoreIndex, StorageContext
from llama_index.vector_stores.qdrant import QdrantVectorStore
import qdrant_client

client = qdrant_client.QdrantClient(
    location=":memory:",
)

vector_store = QdrantVectorStore(
    collection_name = "paper",
    client=client,
    enable_hybrid=True,
    batch_size=20,
)

storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(
    documents,
    embed_model=embed_model,
    storage_context=storage_context,
)

from llama_index.core.memory import ChatMemoryBuffer

memory = ChatMemoryBuffer.from_defaults(token_limit= 3000)

chat_engine = index.as_chat_engine(
    chat_mode="context",
    memory=memory,
    system_prompt=(
        "You are an AI assistant who answers the user questions"
    ),
)



def is_greeting(user_input):

    greetings = ["hello", "hi", "hey", "good morning", "good afternoon", "good evening", "greetings"]
    user_input_lower = user_input.lower().strip()
    return any(greet in user_input_lower for greet in greetings)

def is_bye(user_input):
    greetings = ["bye","thanks", "thank you", "thanks a lot", "bye bye", "have a good day"]
    user_input_lower = user_input.lower().strip()
    return any(greet in user_input_lower for greet in greetings)

import gradio as gr
def chat_with_ai(user_input, chat_history):
    if is_greeting(str(user_input)):
        response = 'hi,how can i help you?'
        chat_history.append((user_input, response))
        return chat_history, ""
    if is_bye(str(user_input)):
        response = "you're welcome"
        chat_history.append((user_input, response))
        return chat_history, ""
    response = chat_engine.chat(user_input)
    full_text = response.response

    references = response.source_nodes
    ref,pages = [],[]
    for i in range(len(references)):
      if references[i].metadata['file_name'] not in ref:
        ref.append(references[i].metadata['file_name'])
      # pages.append(references[i].metadata['page_label'])
    complete_response = str(full_text) + "\n\n" + "references: " + str(ref)
    if ref !=[] :
      chat_history.append((user_input, complete_response))
      ref = []
    elif ref==[] :
      chat_history.append((user_input,str(response)))

    return chat_history, ""


def gradio_chatbot():
    with gr.Blocks() as demo:
        gr.Markdown("# Chat Interface for llama3.1_70B with Groq and llama_index")

        chatbot = gr.Chatbot(label="llamaindex Chatbot")
        user_input = gr.Textbox(
            placeholder="Ask a question...", label="Enter your question"
        )

        submit_button = gr.Button("Send")

        chat_history = gr.State([])

        submit_button.click(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])

        user_input.submit(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])

    return demo

gradio_chatbot().launch(debug=True)