Make search model configurable on server

- Expose ability to modify search model via Django admin interface
- Previously the bi_encoder and cross_encoder models to use were set
  in code
- Now it's user configurable but with a default config generated by
  default

src/database/adapters/__init__.py

@@ -1,8 +1,8 @@
 import math
-from typing import Optional, Type, TypeVar, List
-from datetime import date, datetime, timedelta
+from typing import Optional, Type, List
+from datetime import date, datetime
 import secrets
-from typing import Type, TypeVar, List
+from typing import Type, List
 from datetime import date, timezone
 
 from django.db import models
@@ -31,6 +31,7 @@ from database.models import (
     GithubRepoConfig,
     Conversation,
     ChatModelOptions,
+    SearchModel,
     Subscription,
     UserConversationConfig,
     OpenAIProcessorConversationConfig,
@@ -41,15 +42,6 @@ from khoj.search_filter.word_filter import WordFilter
 from khoj.search_filter.file_filter import FileFilter
 from khoj.search_filter.date_filter import DateFilter
 
-ModelType = TypeVar("ModelType", bound=models.Model)
-
-
-async def retrieve_object(model_class: Type[ModelType], id: int) -> ModelType:
-    instance = await model_class.objects.filter(id=id).afirst()
-    if not instance:
-        raise HTTPException(status_code=404, detail=f"{model_class.__name__} not found")
-    return instance
-
 
 async def set_notion_config(token: str, user: KhojUser):
     notion_config = await NotionConfig.objects.filter(user=user).afirst()
@@ -220,6 +212,10 @@ async def set_user_github_config(user: KhojUser, pat_token: str, repos: list):
     return config
 
 
+def get_or_create_search_model():
+    return SearchModel.objects.filter().get_or_create()[0]
+
+
 class ConversationAdapters:
     @staticmethod
     def get_conversation_by_user(user: KhojUser):

src/database/admin.py

@@ -8,6 +8,7 @@ from database.models import (
     ChatModelOptions,
     OpenAIProcessorConversationConfig,
     OfflineChatProcessorConversationConfig,
+    SearchModel,
     Subscription,
 )
 
@@ -16,4 +17,5 @@ admin.site.register(KhojUser, UserAdmin)
 admin.site.register(ChatModelOptions)
 admin.site.register(OpenAIProcessorConversationConfig)
 admin.site.register(OfflineChatProcessorConversationConfig)
+admin.site.register(SearchModel)
 admin.site.register(Subscription)

src/database/migrations/0017_searchmodel.py

@@ -0,0 +1,32 @@
+# Generated by Django 4.2.5 on 2023-11-14 23:25
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("database", "0016_alter_subscription_renewal_date"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="SearchModel",
+            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)),
+                ("name", models.CharField(default="default", max_length=200)),
+                ("model_type", models.CharField(choices=[("text", "Text")], default="text", max_length=200)),
+                ("bi_encoder", models.CharField(default="thenlper/gte-small", max_length=200)),
+                (
+                    "cross_encoder",
+                    models.CharField(
+                        blank=True, default="cross-encoder/ms-marco-MiniLM-L-6-v2", max_length=200, null=True
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

src/database/models/__init__.py

@@ -102,6 +102,18 @@ class LocalPlaintextConfig(BaseModel):
     user = models.ForeignKey(KhojUser, on_delete=models.CASCADE)
 
 
+class SearchModel(BaseModel):
+    class ModelType(models.TextChoices):
+        TEXT = "text"
+
+    name = models.CharField(max_length=200, default="default")
+    model_type = models.CharField(max_length=200, choices=ModelType.choices, default=ModelType.TEXT)
+    bi_encoder = models.CharField(max_length=200, default="thenlper/gte-small")
+    cross_encoder = models.CharField(
+        max_length=200, default="cross-encoder/ms-marco-MiniLM-L-6-v2", null=True, blank=True
+    )
+
+
 class OpenAIProcessorConversationConfig(BaseModel):
     api_key = models.CharField(max_length=200)