Merge branch 'master' of github.com:debanjum/semantic-search into add-summarize-capability-to-chat-bot

- Fix openai_api_key being set in ConfigProcessorConfig
- Merge addition of config UI and config instantiation updates

src/utils/config.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass
 from pathlib import Path
 
 # Internal Packages
-from src.utils.helpers import get_from_dict
+from src.utils.rawconfig import ConversationProcessorConfig
 
 
 class SearchType(str, Enum):
@@ -42,80 +42,15 @@ class SearchModels():
     image_search: ImageSearchModel = None
 
 
-class TextSearchConfig():
-    def __init__(self, input_files, input_filter, compressed_jsonl, embeddings_file, verbose):
-        self.input_files = input_files
-        self.input_filter = input_filter
-        self.compressed_jsonl = Path(compressed_jsonl)
-        self.embeddings_file = Path(embeddings_file)
+class ConversationProcessorConfigModel():
+    def __init__(self, processor_config: ConversationProcessorConfig, verbose: bool):
+        self.openai_api_key = processor_config.openai_api_key
+        self.conversation_logfile = Path(processor_config.conversation_logfile)
+        self.chat_session = ''
+        self.meta_log = []
         self.verbose = verbose
 
 
-    def create_from_dictionary(config, key_tree, verbose):
-        text_config = get_from_dict(config, *key_tree)
-        search_enabled = text_config and ('input-files' in text_config or 'input-filter' in text_config)
-        if not search_enabled:
-            return None
-
-        return TextSearchConfig(
-            input_files = text_config['input-files'],
-            input_filter = text_config['input-filter'],
-            compressed_jsonl = Path(text_config['compressed-jsonl']),
-            embeddings_file = Path(text_config['embeddings-file']),
-            verbose = verbose)
-
-
-class ImageSearchConfig():
-    def __init__(self, input_directory, embeddings_file, batch_size, use_xmp_metadata, verbose):
-        self.input_directory = input_directory
-        self.embeddings_file = Path(embeddings_file)
-        self.batch_size = batch_size
-        self.use_xmp_metadata = use_xmp_metadata
-        self.verbose = verbose
-
-    def create_from_dictionary(config, key_tree, verbose):
-        image_config = get_from_dict(config, *key_tree)
-        search_enabled = image_config and 'input-directory' in image_config
-        if not search_enabled:
-            return None
-
-        return ImageSearchConfig(
-            input_directory = Path(image_config['input-directory']),
-            embeddings_file = Path(image_config['embeddings-file']),
-            batch_size = image_config['batch-size'],
-            use_xmp_metadata = {'yes': True, 'no': False}[image_config['use-xmp-metadata']],
-            verbose = verbose)
-
-
 @dataclass
-class SearchConfig():
-    notes: TextSearchConfig = None
-    ledger: TextSearchConfig = None
-    music: TextSearchConfig = None
-    image: ImageSearchConfig = None
-
-
-class ConversationProcessorConfig():
-    def __init__(self, conversation_logfile, chat_session, meta_log, openai_api_key, verbose):
-        self.openai_api_key = openai_api_key
-        self.conversation_logfile = conversation_logfile
-        self.chat_session = chat_session
-        self.meta_log = meta_log
-        self.verbose = verbose
-
-    def create_from_dictionary(config, key_tree, verbose):
-        conversation_config = get_from_dict(config, *key_tree)
-        if not conversation_config:
-            return None
-
-        return ConversationProcessorConfig(
-            openai_api_key = conversation_config['openai-api-key'],
-            chat_session = '',
-            meta_log = [],
-            conversation_logfile = Path(conversation_config['conversation-logfile']),
-            verbose = verbose)
-
-
-@dataclass
-class ProcessorConfig():
-    conversation: ConversationProcessorConfig = None
+class ProcessorConfigModel():
+    conversation: ConversationProcessorConfigModel = None