Merge branch 'dev' into Rahul-540

.github/workflows/linters.yml

@@ -5,13 +5,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v1
-      - name: Set up Python 3.7
+      - name: Set up Python 3.9.20
         uses: actions/setup-python@v1
         with:
-          python-version: 3.7
+          python-version: 3.9.20
       - name: Debug Message - Check Github branch
         run: echo "Current Git branch is ${GITHUB_REF##*/}" 
       - name: Install Black
-        run: pip install black
+        run: pip install black==23.1.0
       - name: Run black --check . to check for code formatting.
-        run: black --check .
+        run: black --check .

backend/anudesh_backend/logger.py

@@ -1,6 +1,7 @@
 """
 Defines the logging format for the console logger
 """
+
 import logging
 from django.utils.termcolors import colorize
 

backend/dataset/migrations/0055_auto_20241029_0902.py

@@ -0,0 +1,140 @@
+# Generated by Django 3.2.14 on 2024-10-29 09:02
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("tasks", "0050_alter_annotation_unique_together"),
+        ("dataset", "0054_auto_20241016_0456"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="conversation",
+            name="datasetbase_ptr",
+        ),
+        migrations.RemoveField(
+            model_name="ocrdocument",
+            name="datasetbase_ptr",
+        ),
+        migrations.RemoveField(
+            model_name="sentencetext",
+            name="datasetbase_ptr",
+        ),
+        migrations.RemoveField(
+            model_name="speechconversation",
+            name="datasetbase_ptr",
+        ),
+        migrations.RemoveField(
+            model_name="translationpair",
+            name="datasetbase_ptr",
+        ),
+        migrations.AlterField(
+            model_name="datasetinstance",
+            name="dataset_type",
+            field=models.CharField(
+                choices=[
+                    ("PromptBase", "PromptBase"),
+                    ("PromptAnswer", "PromptAnswer"),
+                    ("PromptAnswerEvaluation", "PromptAnswerEvaluation"),
+                    ("Interaction", "Interaction"),
+                    ("Instruction", "Instruction"),
+                    ("MultiModelInteraction", "MultiModelInteraction"),
+                ],
+                help_text="Dataset Type which is specific for each annotation task",
+                max_length=100,
+                verbose_name="dataset_type",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="promptanswer",
+            name="language",
+            field=models.CharField(
+                choices=[
+                    ("English", "English"),
+                    ("Assamese", "Assamese"),
+                    ("Bengali", "Bengali"),
+                    ("Bodo", "Bodo"),
+                    ("Dogri", "Dogri"),
+                    ("Filipino", "Filipino"),
+                    ("Gujarati", "Gujarati"),
+                    ("Hindi", "Hindi"),
+                    ("Kannada", "Kannada"),
+                    ("Kashmiri", "Kashmiri"),
+                    ("Konkani", "Konkani"),
+                    ("Maithili", "Maithili"),
+                    ("Malayalam", "Malayalam"),
+                    ("Manipuri", "Manipuri"),
+                    ("Marathi", "Marathi"),
+                    ("Nepali", "Nepali"),
+                    ("Odia", "Odia"),
+                    ("Punjabi", "Punjabi"),
+                    ("Sanskrit", "Sanskrit"),
+                    ("Santali", "Santali"),
+                    ("Sindhi", "Sindhi"),
+                    ("Sinhala", "Sinhala"),
+                    ("Tamil", "Tamil"),
+                    ("Telugu", "Telugu"),
+                    ("Thai", "Thai"),
+                    ("Urdu", "Urdu"),
+                ],
+                max_length=15,
+                verbose_name="language",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="promptbase",
+            name="language",
+            field=models.CharField(
+                choices=[
+                    ("English", "English"),
+                    ("Assamese", "Assamese"),
+                    ("Bengali", "Bengali"),
+                    ("Bodo", "Bodo"),
+                    ("Dogri", "Dogri"),
+                    ("Filipino", "Filipino"),
+                    ("Gujarati", "Gujarati"),
+                    ("Hindi", "Hindi"),
+                    ("Kannada", "Kannada"),
+                    ("Kashmiri", "Kashmiri"),
+                    ("Konkani", "Konkani"),
+                    ("Maithili", "Maithili"),
+                    ("Malayalam", "Malayalam"),
+                    ("Manipuri", "Manipuri"),
+                    ("Marathi", "Marathi"),
+                    ("Nepali", "Nepali"),
+                    ("Odia", "Odia"),
+                    ("Punjabi", "Punjabi"),
+                    ("Sanskrit", "Sanskrit"),
+                    ("Santali", "Santali"),
+                    ("Sindhi", "Sindhi"),
+                    ("Sinhala", "Sinhala"),
+                    ("Tamil", "Tamil"),
+                    ("Telugu", "Telugu"),
+                    ("Thai", "Thai"),
+                    ("Urdu", "Urdu"),
+                ],
+                max_length=15,
+                verbose_name="language",
+            ),
+        ),
+        migrations.DeleteModel(
+            name="BlockText",
+        ),
+        migrations.DeleteModel(
+            name="Conversation",
+        ),
+        migrations.DeleteModel(
+            name="OCRDocument",
+        ),
+        migrations.DeleteModel(
+            name="SentenceText",
+        ),
+        migrations.DeleteModel(
+            name="SpeechConversation",
+        ),
+        migrations.DeleteModel(
+            name="TranslationPair",
+        ),
+    ]

backend/dataset/models.py

@@ -1,6 +1,7 @@
 """
 Model definitions for Dataset Management
 """
+
 from django.db import models
 from users.models import User, LANG_CHOICES
 from organizations.models import Organization
@@ -89,6 +90,7 @@
     ("English", "English"),
     ("Assamese", "Assamese"),
     ("Bengali", "Bengali"),
+    ("Burmese", "Burmese"),
     ("Bodo", "Bodo"),
     ("Dogri", "Dogri"),
     ("Gujarati", "Gujarati"),
@@ -109,6 +111,7 @@
     ("Sinhala", "Sinhala"),
     ("Tamil", "Tamil"),
     ("Telugu", "Telugu"),
+    ("Thai", "Thai"),
     ("Urdu", "Urdu"),
 ]
 

backend/dataset/resources.py

@@ -1,6 +1,7 @@
 """
 Module to store Import-Export resource classes
 """
+
 from import_export.resources import ModelResource
 from .models import *
 from .mixins import ResourceMixin

backend/dataset/serializers.py

@@ -1,6 +1,7 @@
 """
 Module to store Django REST Framework Serializers for dataset related models
 """
+
 from django_celery_results.models import TaskResult
 from rest_framework import serializers
 

backend/dataset/views.py

@@ -31,7 +31,7 @@
     convert_seconds_to_hours,
     get_audio_project_types,
     get_audio_transcription_duration,
-    calculate_word_error_rate_between_two_audio_transcription_annotation,
+    calculate_word_error_rate_between_two_llm_prompts,
     ocr_word_count,
 )
 
@@ -1020,7 +1020,7 @@ def project_analytics(self, request, pk=None):
                                 )
                             )
                             total_word_error_rate_ar_list.append(
-                                calculate_word_error_rate_between_two_audio_transcription_annotation(
+                                calculate_word_error_rate_between_two_llm_prompts(
                                     review_annotation.result,
                                     review_annotation.parent_annotation.result,
                                 )
@@ -1049,7 +1049,7 @@ def project_analytics(self, request, pk=None):
                                 )
                             )
                             total_word_error_rate_rs_list.append(
-                                calculate_word_error_rate_between_two_audio_transcription_annotation(
+                                calculate_word_error_rate_between_two_llm_prompts(
                                     supercheck_annotation.result,
                                     supercheck_annotation.parent_annotation.result,
                                 )