feat: adicionando app de ragas

ragas_api/admin.py

@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.

ragas_api/apps.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class RagasApiConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'ragas_api'

ragas_api/models.py

@@ -0,0 +1,3 @@
+from django.db import models
+
+# Create your models here.

ragas_api/serializer.py

@@ -0,0 +1,15 @@
+from rest_framework import serializers
+from resumos.serializer import ResumoCursorCompeltoSerializer
+
+
+class RagasSerializer(ResumoCursorCompeltoSerializer):
+    files = serializers.ListField(child=serializers.FileField(), required=True)
+    id_modelo_do_usuario = serializers.IntegerField(required=False)
+    hf_embedding = serializers.CharField(required=False, default="all-MiniLM-L6-v2")
+
+
+class RagasFromTextSerializer(ResumoCursorCompeltoSerializer):
+    files = None
+    id_modelo_do_usuario = serializers.IntegerField(required=False, default=9)
+    user_message = serializers.CharField(required=True)
+    context_provided = serializers.CharField(required=False)

ragas_api/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

ragas_api/views.py

@@ -0,0 +1,124 @@
+from rest_framework.views import APIView
+import tempfile, os
+from rest_framework.response import Response
+
+from _utils.resumo_completo_cursor import (
+    get_llm_summary_answer_by_cursor_complete,
+    test_ragas,
+)
+from .serializer import (
+    RagasFromTextSerializer,
+    RagasSerializer,
+)
+from rest_framework.parsers import MultiPartParser
+from drf_spectacular.utils import extend_schema
+
+
+class RagasView(APIView):
+    parser_classes = [MultiPartParser]
+
+    @extend_schema(
+        request=RagasSerializer,
+    )
+    def post(self, request):
+        serializer = RagasSerializer(data=request.data)
+        print("\n\n\n")
+        print("\n\n\n")
+        print("serializer.data: ", serializer)
+        listaPDFs = []
+        if serializer.is_valid(raise_exception=True):
+            for file in serializer.validated_data["files"]:
+                file.seek(0)
+                with tempfile.NamedTemporaryFile(
+                    delete=False, suffix=".pdf"
+                ) as temp_file:  # Create a temporary file to save the uploaded PDF
+                    for (
+                        chunk
+                    ) in (
+                        file.chunks()
+                    ):  # Write the uploaded file content to the temporary file
+                        temp_file.write(chunk)
+                    temp_file_path = (
+                        temp_file.name
+                    )  # Get the path of the temporary file
+                    listaPDFs.append(temp_file_path)
+
+            result = test_ragas(serializer, listaPDFs)
+
+            for file in listaPDFs:
+                os.remove(file)
+
+            return Response({"msg": result})
+
+
+class RagasFromTextView(APIView):
+    def post(self, request):
+        serializer = RagasFromTextSerializer(data=request.data)
+        if serializer.is_valid(raise_exception=True):
+            from datasets import Dataset
+            from ragas import evaluate
+            from ragas.metrics import (
+                faithfulness,
+                answer_relevancy,
+                answer_correctness,
+                context_precision,
+                context_recall,
+            )
+            import os
+            from datasets import load_dataset
+            import pandas as pd
+
+            os.environ.get("OPENAI_API_KEY")
+
+            df_pandas = pd.read_csv(
+                "D:/repositorios/projetos-pessoais/projeto-y-backend-hugginf-face-teste-01/vella-backend/_utils/files/ragas_testset.csv"
+            )
+            # print(df_pandas["position"])  # Print a specific column
+            data = {
+                "user_input": [
+                    "What is the capital of France?",
+                ],
+                "response": [],
+                "retrieved_contexts": [],
+            }
+
+            reference = [
+                "Paris is the capital of France. It is a major European city known for its culture."
+            ]
+
+            for x in df_pandas["user_input"]:
+                data["user_input"].append(x)
+
+            for x in df_pandas["reference"]:
+                reference.append(x)
+
+            print("data: ", reference)
+
+            for i in range(len(reference)):
+                serializer.validated_data["user_message"] = data["user_input"][i]
+                resposta_llm = get_llm_summary_answer_by_cursor_complete(
+                    serializer.validated_data, contexto=reference[i]
+                )
+                data["response"].append(resposta_llm["texto_completo"])
+                lista_reference_contexts = []
+                for x in resposta_llm["resultado"]:
+                    lista_reference_contexts.append(x["source"]["text"])
+                data["retrieved_contexts"].append(lista_reference_contexts)
+
+            # Convert the data to a Hugging Face Dataset
+            dataset = Dataset.from_dict(data)
+
+            # Define the metrics you want to evaluate
+            metrics = [
+                faithfulness,
+                # answer_relevancy,
+                # answer_correctness,
+                # context_precision,
+                # context_recall,
+            ]
+
+            # Evaluate the dataset using the selected metrics
+            results = evaluate(dataset, metrics)
+
+            # results.to_pandas().to_csv("./result.csv")
+            return Response({"resposta": results.to_pandas().to_string()})

setup/settings.py

@@ -26,7 +26,7 @@ BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 # See https://docs.djangoproject.com/en/4.2/howto/deployment/checklist/
 
 # SECURITY WARNING: keep the secret key used in production secret!
-SECRET_KEY = os.environ.get('SECRET_KEY')
+SECRET_KEY = os.environ.get("SECRET_KEY")
 
 # SECURITY WARNING: don't run with debug turned on in production!
 DEBUG = True
@@ -51,6 +51,7 @@ INSTALLED_APPS = [
     "drf_spectacular",
     "resumos",
     "modelos_usuarios",
+    "ragas_api",
 ]
 
 MIDDLEWARE = [
@@ -62,10 +63,10 @@ MIDDLEWARE = [
     "django.contrib.auth.middleware.AuthenticationMiddleware",
     "django.contrib.messages.middleware.MessageMiddleware",
     "django.middleware.clickjacking.XFrameOptionsMiddleware",
-    "whitenoise.middleware.WhiteNoiseMiddleware"
+    "whitenoise.middleware.WhiteNoiseMiddleware",
 ]
 
-STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'
+STATICFILES_STORAGE = "whitenoise.storage.CompressedManifestStaticFilesStorage"
 
 ROOT_URLCONF = "setup.urls"
 
@@ -92,16 +93,16 @@ WSGI_APPLICATION = "setup.wsgi.application"
 # https://docs.djangoproject.com/en/4.2/ref/settings/#databases
 
 DATABASES = {
-    'default': {
-        'ENGINE': 'django.db.backends.postgresql',
-        'NAME': "vella",
-        'USER': "vella_owner",
-        'PASSWORD': os.environ.get('DATABASE_PASSWORD'),
-        'HOST': "ep-black-tooth-a510h8oe.us-east-2.aws.neon.tech",
-        'PORT': 5432,
-        'OPTIONS': {
-            'sslmode': 'require',
-        }
+    "default": {
+        "ENGINE": "django.db.backends.postgresql",
+        "NAME": "vella",
+        "USER": "vella_owner",
+        "PASSWORD": os.environ.get("DATABASE_PASSWORD"),
+        "HOST": "ep-black-tooth-a510h8oe.us-east-2.aws.neon.tech",
+        "PORT": 5432,
+        "OPTIONS": {
+            "sslmode": "require",
+        },
     }
 }
 
@@ -149,7 +150,7 @@ USE_TZ = True
 # https://docs.djangoproject.com/en/4.2/howto/static-files/
 
 STATIC_URL = "static/"
-STATIC_ROOT = os.path.join(BASE_DIR, 'staticfiles')
+STATIC_ROOT = os.path.join(BASE_DIR, "staticfiles")
 
 # Default primary key field type
 # https://docs.djangoproject.com/en/4.2/ref/settings/#default-auto-field
@@ -159,21 +160,25 @@ DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
 CORS_ORIGIN_WHITELIST = [
     "http://localhost",
     "https://luanpoppe-projeto-y-teste-01.hf.space",
-    "https://*"
+    "https://*",
 ]
 
 REST_FRAMEWORK = {
-	'DEFAULT_PAGINATION_CLASS': 'rest_framework.pagination.PageNumberPagination',
-    'PAGE_SIZE': 10,
-    'DEFAULT_SCHEMA_CLASS': 'drf_spectacular.openapi.AutoSchema',
-    "DEFAULT_PARSER_CLASSES": ["rest_framework.parsers.JSONParser", "rest_framework.parsers.MultiPartParser", "rest_framework.parsers.FormParser"]
+    "DEFAULT_PAGINATION_CLASS": "rest_framework.pagination.PageNumberPagination",
+    "PAGE_SIZE": 10,
+    "DEFAULT_SCHEMA_CLASS": "drf_spectacular.openapi.AutoSchema",
+    "DEFAULT_PARSER_CLASSES": [
+        "rest_framework.parsers.JSONParser",
+        "rest_framework.parsers.MultiPartParser",
+        "rest_framework.parsers.FormParser",
+    ],
 }
 
 SPECTACULAR_SETTINGS = {
-    'TITLE': 'Your Project API',
-    'DESCRIPTION': 'Your project description',
-    'VERSION': '1.0.0',
-    'SERVE_INCLUDE_SCHEMA': False,
-    'COMPONENT_SPLIT_REQUEST': True
+    "TITLE": "Your Project API",
+    "DESCRIPTION": "Your project description",
+    "VERSION": "1.0.0",
+    "SERVE_INCLUDE_SCHEMA": False,
+    "COMPONENT_SPLIT_REQUEST": True,
     # OTHER SETTINGS
 }

setup/urls.py

@@ -6,13 +6,16 @@ from drf_spectacular.views import SpectacularSwaggerView, SpectacularAPIView
 
 from pdfs.views import getPDF
 from resumos.views import (
-    RagasFromTextView,
-    RagasView,
     ResumoView,
     ResumoSimplesCursorView,
     ResumoSimplesCursorCompletoView,
 )
-from modelos_usuarios.views import ListCreateModeloUsuarioView, CreateUpdateDeleteModeloUsuarioView, ListModelosPorUsuarioView
+from ragas_api.views import RagasFromTextView, RagasView
+from modelos_usuarios.views import (
+    ListCreateModeloUsuarioView,
+    CreateUpdateDeleteModeloUsuarioView,
+    ListModelosPorUsuarioView,
+)
 
 router = routers.DefaultRouter()
 # router.register("endpoint-teste", EndpointTesteViewSet, basename="Basename do endpoint-teste")