[Multi-User Part 3]: Separate chat sesssions based on authenticated users (#511)

- Add a data model which allows us to store Conversations with users. This does a minimal lift over the current setup, where the underlying data is stored in a JSON file. This maintains parity with that configuration.
- There does _seem_ to be some regression in chat quality, which is most likely attributable to search results.

This will help us with #275. It should become much easier to maintain multiple Conversations in a given table in the backend now. We will have to do some thinking on the UI.

tests/helpers.py

@@ -0,0 +1,51 @@
+import factory
+import os
+
+from database.models import (
+    KhojUser,
+    ConversationProcessorConfig,
+    OfflineChatProcessorConversationConfig,
+    OpenAIProcessorConversationConfig,
+    Conversation,
+)
+
+
+class UserFactory(factory.django.DjangoModelFactory):
+    class Meta:
+        model = KhojUser
+
+    username = factory.Faker("name")
+    email = factory.Faker("email")
+    password = factory.Faker("password")
+    uuid = factory.Faker("uuid4")
+
+
+class ConversationProcessorConfigFactory(factory.django.DjangoModelFactory):
+    class Meta:
+        model = ConversationProcessorConfig
+
+    max_prompt_size = 2000
+    tokenizer = None
+
+
+class OfflineChatProcessorConversationConfigFactory(factory.django.DjangoModelFactory):
+    class Meta:
+        model = OfflineChatProcessorConversationConfig
+
+    enable_offline_chat = True
+    chat_model = "llama-2-7b-chat.ggmlv3.q4_0.bin"
+
+
+class OpenAIProcessorConversationConfigFactory(factory.django.DjangoModelFactory):
+    class Meta:
+        model = OpenAIProcessorConversationConfig
+
+    api_key = os.getenv("OPENAI_API_KEY")
+    chat_model = "gpt-3.5-turbo"
+
+
+class ConversationFactory(factory.django.DjangoModelFactory):
+    class Meta:
+        model = Conversation
+
+    user = factory.SubFactory(UserFactory)