import os

import openai

from langchain.chains import LLMChain
from langchain.chat_models import ChatOpenAI

from langchain.embeddings import OpenAIEmbeddings
from langchain.prompts import PromptTemplate
from langchain_pinecone import PineconeVectorStore

prompt_template = """Answer the question using the given context to the best of your ability. 
If you don't know, answer I don't know.
Context: {context}
Topic: {topic}

Use the following example format for your answer:
[FORMAT]
Answer:
    The answer to the user question.
Reference:
    The list of references to the specific sections of the documents that support your answer.    
[END_FORMAT]
"""


PROMPT = PromptTemplate(template=prompt_template, input_variables=["context", "topic"])


class LangOpen:
    def __init__(self, model_name: str) -> None:
        self.index = self.initialize_index("langOpen")
        self.llm = ChatOpenAI(temperature=0.3, model=model_name)
        self.chain = LLMChain(llm=self.llm, prompt=PROMPT)

    def initialize_index(self, index_name):
        embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
        index_name = "openai-embeddings"
        vectorstore = PineconeVectorStore(index_name=index_name, embedding=embeddings)
        return vectorstore


    def get_response(self, query_str):
        print("query_str: ", query_str)
        print("model_name: ", self.llm.model_name)
        docs = self.index.similarity_search(query_str, k=4)
        inputs = [{"context": doc.page_content, "topic": query_str} for doc in docs]
        result = self.chain.apply(inputs)[0]["text"]
        return result