Add speech to text model configuration to Database

src/khoj/database/adapters/__init__.py

@@ -28,6 +28,7 @@ from khoj.database.models import (
     Conversation,
     ChatModelOptions,
     SearchModelConfig,
+    SpeechToTextModelOptions,
     Subscription,
     UserConversationConfig,
     OpenAIProcessorConversationConfig,
@@ -339,6 +340,10 @@ class ConversationAdapters:
     async def get_openai_chat_config():
         return await OpenAIProcessorConversationConfig.objects.filter().afirst()
 
+    @staticmethod
+    async def get_speech_to_text_config():
+        return await SpeechToTextModelOptions.objects.filter().afirst()
+
 
 class EntryAdapters:
     word_filer = WordFilter()

src/khoj/database/admin.py

@@ -9,12 +9,14 @@ from khoj.database.models import (
     OpenAIProcessorConversationConfig,
     OfflineChatProcessorConversationConfig,
     SearchModelConfig,
+    SpeechToTextModelOptions,
     Subscription,
 )
 
 admin.site.register(KhojUser, UserAdmin)
 
 admin.site.register(ChatModelOptions)
+admin.site.register(SpeechToTextModelOptions)
 admin.site.register(OpenAIProcessorConversationConfig)
 admin.site.register(OfflineChatProcessorConversationConfig)
 admin.site.register(SearchModelConfig)

src/khoj/database/migrations/0020_speechtotextmodeloptions_and_more.py

@@ -0,0 +1,35 @@
+# Generated by Django 4.2.7 on 2023-11-22 08:51
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("database", "0019_alter_googleuser_family_name_and_more"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="SpeechToTextModelOptions",
+            fields=[
+                ("id", models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name="ID")),
+                ("created_at", models.DateTimeField(auto_now_add=True)),
+                ("updated_at", models.DateTimeField(auto_now=True)),
+                ("model_name", models.CharField(default="whisper-1", max_length=200)),
+                (
+                    "model_type",
+                    models.CharField(
+                        choices=[("openai", "Openai"), ("offline", "Offline")], default="openai", max_length=200
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AlterField(
+            model_name="chatmodeloptions",
+            name="chat_model",
+            field=models.CharField(default="gpt-4", max_length=200),
+        ),
+    ]

src/khoj/database/models/__init__.py

@@ -120,6 +120,15 @@ class OfflineChatProcessorConversationConfig(BaseModel):
     enabled = models.BooleanField(default=False)
 
 
+class SpeechToTextModelOptions(BaseModel):
+    class ModelType(models.TextChoices):
+        OPENAI = "openai"
+        OFFLINE = "offline"
+
+    model_name = models.CharField(max_length=200, default="whisper-1")
+    model_type = models.CharField(max_length=200, choices=ModelType.choices, default=ModelType.OPENAI)
+
+
 class ChatModelOptions(BaseModel):
     class ModelType(models.TextChoices):
         OPENAI = "openai"
@@ -127,7 +136,7 @@ class ChatModelOptions(BaseModel):
 
     max_prompt_size = models.IntegerField(default=None, null=True, blank=True)
     tokenizer = models.CharField(max_length=200, default=None, null=True, blank=True)
-    chat_model = models.CharField(max_length=200, default=None, null=True, blank=True)
+    chat_model = models.CharField(max_length=200, default="gpt-4")
     model_type = models.CharField(max_length=200, choices=ModelType.choices, default=ModelType.OPENAI)
 
 

src/khoj/utils/initialization.py

@@ -6,6 +6,7 @@ from khoj.database.models import (
     OfflineChatProcessorConversationConfig,
     OpenAIProcessorConversationConfig,
     ChatModelOptions,
+    SpeechToTextModelOptions,
 )
 
 from khoj.utils.constants import default_offline_chat_model, default_online_chat_model
@@ -94,6 +95,15 @@ def initialization():
                 chat_model=openai_chat_model, model_type=ChatModelOptions.ModelType.OPENAI, max_prompt_size=max_tokens
             )
 
+            default_speech2text_model = "whisper-1"
+            openai_speech2text_model = input(
+                f"Enter the OpenAI speech to text model you want to use (default: {default_speech2text_model}): "
+            )
+            openai_speech2text_model = openai_speech2text_model or default_speech2text_model
+            SpeechToTextModelOptions.objects.create(
+                model_name=openai_speech2text_model, model_type=SpeechToTextModelOptions.ModelType.OPENAI
+            )
+
         logger.info("🗣️  Chat model configuration complete")
 
     admin_user = KhojUser.objects.filter(is_staff=True).first()