app_v1.py

import streamlit as st

# from src.helper import download_hugging_face_embeddings

from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAI
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain_huggingface import HuggingFaceEmbeddings
from src.prompt import *

from dotenv import load_dotenv
import os


#Download the Embeddings from Hugging Face
def download_hugging_face_embeddings():
    embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
    return embeddings


# Load env Variables
load_dotenv()

PINECONE_API_KEY=os.environ.get('PINECONE_API_KEY')
OPENAI_API_KEY=os.environ.get('OPENAI_API_KEY')
GOOGLE_API_KEY= os.environ.get("GOOGLE_API_KEY")

os.environ["PINECONE_API_KEY"] = PINECONE_API_KEY
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
os.environ["GOOGLE_API_KEY"] = GOOGLE_API_KEY
# Embedding model
embeddings = download_hugging_face_embeddings()


# load exisiting pinecone index
index_name = "yolotest"
Vector_store = PineconeVectorStore.from_existing_index(
    index_name=index_name,
    embedding=embeddings
)

# Retriever
retriever = Vector_store.as_retriever(search_type="similarity", search_kwargs={"k":5})

# llm
# llm = OpenAI(api_key=OPENAI_API_KEY, temperature=0, max_tokens=500)
llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro",temperature=0,max_tokens=None,timeout=None)

# streamlit 
st.title("RAG Application built on Gemini Model")
query = st.chat_input("Say something: ") 
prompt = query


prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt),
        ("human", "{input}"),
    ]
)


if query:
    question_answer_chain = create_stuff_documents_chain(llm, prompt)
    rag_chain = create_retrieval_chain(retriever, question_answer_chain)

    response = rag_chain.invoke({"input": query})

    st.write(response["answer"])