# from langchain.document_loaders import TextLoader,DirectoryLoader
# from langchain.text_splitter import RecursiveCharacterTextSplitter
# from langchain_google_genai import GoogleGenerativeAIEmbeddings

# embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
# import os
# print(os.path.exists("Data/"))  # Check if directory exists
# print(os.listdir("Data/"))      
# loader = TextLoader("Data/tkrupt.txt")
# docs = loader.load()
# splitter = RecursiveCharacterTextSplitter(chunk_size = 500 , chunk_overlap = 100)
# chunks = splitter.split_documents(docs)
# print(len(chunks))
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_pinecone import PineconeVectorStore
google_api_key = "AIzaSyAhgj1-KUauE7QhOOUdVJrvffZ9mHNvCms"
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001",google_api_key="AIzaSyAhgj1-KUauE7QhOOUdVJrvffZ9mHNvCms")
llm = ChatGoogleGenerativeAI(
    model="gemini-1.5-pro",
    temperature=0.5,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    api_key=google_api_key
)
from dotenv import load_dotenv
load_dotenv()
doc_search = PineconeVectorStore.from_existing_index(
    index_name='customer-support',
    embedding=embeddings
)
retriever = doc_search.as_retriever(searh_type = 'similarity', search_kwards={'k':3})
# print(retriever.invoke("What services they provide ? "))
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
system_prompt = (
    "You are a helpful assistant as Tkrupt which is a software solution delivering company"
    "Use the following context to answer the question"
    "If you dont know the answer , just say you dont know the answer"
    "\n\n"
    "{context}"
)
prompt = ChatPromptTemplate(
    [
        ("system",system_prompt),
        ('human',"{input}")
    ]
)

question_answer_chain = create_stuff_documents_chain(llm, prompt)
rag_chain = create_retrieval_chain(retriever, question_answer_chain)
print(rag_chain.invoke({'input':"what is supra GTA ?"})['answer'])