Spaces:
Running
Running
File size: 7,633 Bytes
b374298 a263183 eebeb78 a263183 eebeb78 ab34606 12d3e1a 12b0dd7 756fca0 1286e81 cb23311 ab34606 1286e81 7eb86f7 a263183 1286e81 095b5f1 eebeb78 1286e81 7eb86f7 cb23311 095b5f1 82e7990 1286e81 7eb86f7 1286e81 baeaaa5 82e7990 12b0dd7 82e7990 7eb86f7 1286e81 756fca0 8f3dc39 b374298 a263183 095b5f1 12b0dd7 095b5f1 cb23311 82e7990 1286e81 ab34606 82e7990 ab34606 82e7990 baeaaa5 095b5f1 1286e81 095b5f1 a263183 7eb86f7 095b5f1 451f8a3 7eb86f7 82e7990 7eb86f7 451f8a3 7eb86f7 ab34606 7eb86f7 b374298 756fca0 095b5f1 7eb86f7 451f8a3 7eb86f7 451f8a3 7eb86f7 451f8a3 ab34606 7eb86f7 a263183 82e7990 a263183 82e7990 a263183 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
from typing import Any, Dict, cast
from langchain.prompts import PromptTemplate
from _utils.langchain_utils.LLM_class import LLM
from _utils.gerar_relatorio_modelo_usuario.utils import (
get_full_text_and_all_PDFs_chunks,
)
from _utils.langchain_utils.Prompt_class import Prompt
from _utils.utils import print_sentry, sentry_add_breadcrumb
from setup.easy_imports import (
Response,
AsyncAPIView,
APIView,
MultiPartParser,
extend_schema,
)
from datetime import datetime
from _utils.handle_files import handle_pdf_files_from_serializer, remove_pdf_temp_files
from _utils.gerar_documento import (
gerar_documento,
)
from _utils.gerar_relatorio_modelo_usuario.prompts import prompt_auxiliar_inicio
from setup.logging import Axiom, send_axiom
from .serializer import (
GerarDocumentoComPDFProprioSerializer,
GerarDocumentoSerializer,
GerarEmentaSerializer,
)
import asyncio
from _utils.langchain_utils.Splitter_class import Splitter
class GerarDocumentoView(AsyncAPIView):
# parser_classes = [MultiPartParser]
serializer = {}
axiom_instance = Axiom()
@extend_schema(
request=GerarDocumentoSerializer,
)
async def post(self, request):
self.axiom_instance.generate_new_uuid()
print(f"\n\nDATA E HORA DA REQUISIÇÃO: {datetime.now()}")
self.axiom_instance.send_axiom("COMEÇOU NOVA REQUISIÇÃO")
self.axiom_instance.send_axiom(f"request.data: {request.data}")
serializer = GerarDocumentoSerializer(data=request.data)
if serializer.is_valid(raise_exception=True):
obj = serializer.get_obj() # type: ignore
if not serializer.validated_data:
raise ValueError("Erro no validated_data")
async def proccess_data_after_response():
# await asyncio.sleep(0)
data = cast(Dict[str, Any], serializer.validated_data)
self.serializer = data
listaPDFs = [l["link_arquivo"] for l in data["files"]]
self.axiom_instance.send_axiom(f"listaPDFs: {listaPDFs}")
resposta_llm = await gerar_documento(
obj, listaPDFs, self.axiom_instance, isBubble=True
)
self.axiom_instance.send_axiom(f"resposta_llm: {resposta_llm}")
# remove_pdf_temp_files(listaPDFs)
# asyncio.create_task(proccess_data_after_response())
loop = asyncio.get_running_loop()
loop.run_in_executor(
None, lambda: asyncio.run(proccess_data_after_response())
)
return Response(
{"resposta": "Requisição está sendo processada em segundo plano"}
)
class GerarDocumentoComPDFProprioView(AsyncAPIView):
parser_classes = [MultiPartParser]
serializer = {}
axiom_instance = Axiom()
@extend_schema(
request=GerarDocumentoComPDFProprioSerializer,
)
async def post(self, request):
self.axiom_instance.generate_new_uuid()
print(f"\n\nDATA E HORA DA REQUISIÇÃO: {datetime.now()}")
self.axiom_instance.send_axiom("COMEÇOU NOVA REQUISIÇÃO")
self.axiom_instance.send_axiom(f"request.data: {request.data}")
serializer = GerarDocumentoComPDFProprioSerializer(data=request.data)
if serializer.is_valid(raise_exception=True):
data = cast(Dict[str, Any], serializer.validated_data)
obj = serializer.get_obj() # type: ignore
self.serializer = data
listaPDFs = handle_pdf_files_from_serializer(
data["files"], self.axiom_instance
)
resposta_llm = await gerar_documento(obj, listaPDFs, self.axiom_instance)
self.axiom_instance.send_axiom(f"resposta_llm: {resposta_llm}")
remove_pdf_temp_files(listaPDFs)
self.axiom_instance.send_axiom(
"PRÓXIMA LINHA ENVIA A RESPOSTA A QUEM FEZ A REQUISIÇÃO"
)
return Response({"resposta": resposta_llm})
class GerarEmentaView(AsyncAPIView):
serializer = {}
@extend_schema(
request=GerarDocumentoSerializer,
)
async def post(self, request):
print(f"\n\nDATA E HORA DA REQUISIÇÃO: {datetime.now()}")
print("request.data: ", request.data)
serializer = GerarEmentaSerializer(data=request.data)
if serializer.is_valid(raise_exception=True):
if not serializer.validated_data:
raise ValueError("Erro no validated_data")
async def proccess_data_after_response():
data = cast(Dict[str, Any], serializer.validated_data)
self.serializer = data
listaPDFs = [l["link_arquivo"] for l in data["files"]]
print("\n\nlistaPDFs: ", listaPDFs)
all_PDFs_chunks, full_text_as_array = (
await get_full_text_and_all_PDFs_chunks(
listaPDFs,
Splitter(data["chunk_size"], data["chunk_overlap"]),
False,
True,
)
)
full_text = "".join(full_text_as_array)
llm = LLM()
prompt_template = PromptTemplate(
input_variables=["context"], template=full_text
)
response = await llm.google_gemini().ainvoke(
prompt_template.format(context=full_text)
)
print("\n\nresposta_llm: ", response.content)
# asyncio.create_task(proccess_data_after_response())
loop = asyncio.get_running_loop()
loop.run_in_executor(
None, lambda: asyncio.run(proccess_data_after_response())
)
return Response(
{"resposta": "Requisição está sendo processada em segundo plano"}
)
class GerarEmentaComPDFProprioView(AsyncAPIView):
parser_classes = [MultiPartParser]
serializer = {}
@extend_schema(
request=GerarDocumentoComPDFProprioSerializer,
)
async def post(self, request):
print(f"\n\nDATA E HORA DA REQUISIÇÃO: {datetime.now()}")
serializer = GerarDocumentoComPDFProprioSerializer(data=request.data)
if serializer.is_valid(raise_exception=True):
data = cast(Dict[str, Any], serializer.validated_data)
print("\n\ndata: ", data)
self.serializer = data
data = cast(Dict[str, Any], serializer.validated_data)
self.serializer = data
listaPDFs = [l["link_arquivo"] for l in data["files"]]
print("\n\nlistaPDFs: ", listaPDFs)
all_PDFs_chunks, full_text_as_array = (
await get_full_text_and_all_PDFs_chunks(
listaPDFs,
Splitter(data["chunk_size"], data["chunk_overlap"]),
False,
True,
)
)
full_text = "".join(full_text_as_array)
llm = LLM()
prompt_template = PromptTemplate(
input_variables=["context"], template=full_text
)
response = await llm.google_gemini().ainvoke(
prompt_template.format(context=full_text)
)
print("\n\nresposta_llm: ", response.content)
remove_pdf_temp_files(listaPDFs)
print("PRÓXIMA LINHA ENVIA A RESPOSTA A QUEM FEZ A REQUISIÇÃO")
return Response({"resposta": response.content})
|