from .model import InformationExtractedFromABillReceipt as PydanticModel

from langchain.chains import LLMChain
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import PydanticOutputParser, OutputFixingParser
from langchain.prompts import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    SystemMessagePromptTemplate,
)

model = ChatOpenAI(
    temperature=0,
    n=1,
    model_kwargs={
        "stop": None,
        "top_p": 1,
        "frequency_penalty": 0,
        "presence_penalty": 0,
    },
)

# Build category chain
system_message_prompt = SystemMessagePromptTemplate.from_template(
    "You are an information extraction engine that outputs details from OCR processed "
    "documents like uids, total, tax, addresses, bank details, invoice details, "
    "participant registration details. Fields with formats specified as date, time, or "
    "datetime should be ISO 8601 compliant.\n"
    "{format_instructions}"
)
human_message_prompt = HumanMessagePromptTemplate.from_template("{text}")
chat_prompt = ChatPromptTemplate.from_messages(
    [system_message_prompt, human_message_prompt]
)
output_parser = PydanticOutputParser(pydantic_object=PydanticModel)
print(output_parser.get_format_instructions())
# exit()
fixing_parser = OutputFixingParser.from_llm(llm=model, parser=output_parser)
chain = LLMChain(llm=model, prompt=chat_prompt, output_parser=fixing_parser)