import tempfile, os
from rest_framework import viewsets, filters
from django_filters.rest_framework import DjangoFilterBackend
from endpoint_teste.models import EndpointTesteModel
from endpoint_teste.serializer import EndpointTesteSerializer, PDFUploadSerializer
from setup.environment import default_model
from drf_spectacular.utils import extend_schema

from rest_framework.decorators import api_view, parser_classes
from rest_framework.parsers import MultiPartParser
from rest_framework.response import Response

from langchain_backend.main import get_llm_answer
from .serializer import TesteSerializer
from langchain_huggingface import HuggingFaceEndpoint

class EndpointTesteViewSet(viewsets.ModelViewSet):
    """Mostrará todas as tarefas"""
    queryset = EndpointTesteModel.objects.order_by("id").all()
    serializer_class = EndpointTesteSerializer
    filter_backends = [DjangoFilterBackend, filters.SearchFilter]
    search_fields = ["id"]

@api_view(["GET", "POST"])
def getTeste(request):
    if request.method == "POST":
        serializer = TesteSerializer(data=request.data)
        if serializer.is_valid(raise_exception=True):
            data = request.data
            pdf_url = None
            if data["pdf_url"]:
                pdf_url = data["pdf_url"]
            resposta_llm = get_llm_answer(data["system_prompt"], data["user_message"], pdf_url)
            return Response({
                "Resposta": resposta_llm
            })
    if request.method == "GET":
        # hugging_face_token = os.environ.get("hugging_face_token")
        # API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B"
        # headers = {"Authorization": "Bearer " + hugging_face_token}
        # def query(payload):
        #     response = requests.post(API_URL, headers=headers, json=payload)
        #     return response.json()
            
        # output = query({
        #     "inputs": "Can you please let us know more details about your something I don't know",
        # })
        # print('output: ', output)
        # print('output: ', dir(output))
        llm = HuggingFaceEndpoint(
            repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
            task="text-generation",
            max_new_tokens=100,
            do_sample=False,
            huggingfacehub_api_token = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
        )
        result = llm.invoke("Hugging Face is")
        print('result: ', result)
        return Response(result)

@extend_schema(
    request=PDFUploadSerializer,
)
@api_view(["POST"])
@parser_classes([MultiPartParser])
def getPDF(request):
    if request.method == "POST":
        serializer = PDFUploadSerializer(data=request.data)
        if serializer.is_valid(raise_exception=True):
            listaPDFs = []
            print('\n\n')
            data = request.data
            print('data: ', data)
            embedding = serializer.validated_data.get("embedding", "gpt")
            model = serializer.validated_data.get("model", default_model)

            # pdf_file = serializer.validated_data['file']
            for file in serializer.validated_data['files']:
                print("file: ", file)
                file.seek(0)
                # Create a temporary file to save the uploaded PDF
                with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
                    # Write the uploaded file content to the temporary file
                    for chunk in file.chunks():
                        temp_file.write(chunk)
                    temp_file_path = temp_file.name  # Get the path of the temporary file
                    listaPDFs.append(temp_file_path)
                # print('temp_file_path: ', temp_file_path)
                print('listaPDFs: ', listaPDFs)

            resposta_llm = None
            # resposta_llm = get_llm_answer(data["system_prompt"], data["user_message"], temp_file_path, model=model, embedding=embedding)
            resposta_llm = get_llm_answer(data["system_prompt"], data["user_message"], listaPDFs, model=model, embedding=embedding)

            for file in listaPDFs:
                os.remove(file)
            # os.remove(temp_file_path)

            return Response({
                "Resposta": resposta_llm
            })