Set default config in the constant module. Use from there to configure app

- Avoid having to pass the khoj_sample.yml data file into pip, native apps
- Packaging data files into python packages is annoying.
  - There's `MANIFEST.in`, `data_files` and `package_data` in setup.py
  - Bdist, wheel, generated source tarball use different set of these fields
    and put the data files in different locations
  - Rather just code the default config into a constant. Avoid
    pointless file reads as well this way

MANIFEST.in

@@ -1,5 +1,4 @@
 include Readme.md
-include config/khoj_sample.yml
 graft src/interface/*
 prune src/interface/web/images*
 prune docs*

src/interface/desktop/configure_screen.py

@@ -30,7 +30,7 @@ class ConfigureScreen(QtWidgets.QDialog):
         if resolve_absolute_path(self.config_file).exists():
             self.current_config = yaml_utils.load_config_from_file(self.config_file)
         else:
-            self.current_config = yaml_utils.load_config_from_file(constants.app_root_directory / 'config/khoj_sample.yml')
+            self.current_config = constants.default_config
         self.new_config = self.current_config
 
         # Initialize Configure Window
@@ -127,7 +127,7 @@ class ConfigureScreen(QtWidgets.QDialog):
 
     def get_default_config(self, search_type:SearchType=None, processor_type:ProcessorType=None):
         "Get default config"
-        config = yaml_utils.load_config_from_file(constants.app_root_directory / 'config/khoj_sample.yml')
+        config = constants.default_config
         if search_type:
             return config['content-type'][search_type]
         elif processor_type:

src/utils/constants.py

@@ -3,3 +3,62 @@ from pathlib import Path
 app_root_directory = Path(__file__).parent.parent.parent
 web_directory = app_root_directory / 'src/interface/web/'
 empty_escape_sequences = r'\n|\r\t '
+
+# default app config to use
+default_config = {
+    'content-type': {
+        'org': {
+            'input-files': None,
+            'input-filter': None,
+            'compressed-jsonl': '~/.khoj/content/org/org.jsonl.gz',
+            'embeddings-file': '~/.khoj/content/org/org_embeddings.pt'
+        },
+        'markdown': {
+            'input-files': None,
+            'input-filter': None,
+            'compressed-jsonl': '~/.khoj/content/markdown/markdown.jsonl.gz',
+            'embeddings-file': '~/.khoj/content/markdown/markdown_embeddings.pt'
+        },
+        'ledger': {
+            'input-files': None,
+            'input-filter': None,
+            'compressed-jsonl': '~/.khoj/content/ledger/ledger.jsonl.gz',
+            'embeddings-file': '~/.khoj/content/ledger/ledger_embeddings.pt'
+        },
+        'image': {
+            'input-directories': None,
+            'input-filter': None,
+            'embeddings-file': '~/.khoj/content/image/image_embeddings.pt',
+            'batch-size': 50,
+            'use-xmp-metadata': True
+        },
+        'music': {
+            'input-files': None,
+            'input-filter': None,
+            'compressed-jsonl': '~/.khoj/content/music/music.jsonl.gz',
+            'embeddings-file': '~/.khoj/content/music/music_embeddings.pt'
+        }
+    },
+    'search-type': {
+        'symmetric': {
+            'encoder': 'sentence-transformers/all-MiniLM-L6-v2',
+            'cross-encoder': 'cross-encoder/ms-marco-MiniLM-L-6-v2',
+            'model_directory': '~/.khoj/search/symmetric/'
+        },
+        'asymmetric': {
+            'encoder': 'sentence-transformers/multi-qa-MiniLM-L6-cos-v1',
+            'cross-encoder': 'cross-encoder/ms-marco-MiniLM-L-6-v2',
+            'model_directory': '~/.khoj/search/asymmetric/'
+        },
+        'image': {
+            'encoder': 'sentence-transformers/clip-ViT-B-32',
+            'model_directory': '~/.khoj/search/image/'
+        }
+    },
+    'processor': {
+        'conversation': {
+            'openai-api-key': None,
+            'conversation-logfile': '~/.khoj/processor/conversation/conversation_logs.json'
+        }
+   }
+}