Make type of encoder to use for embeddings configurable via khoj.yml

- Previously `model_type' was set in the setup of each `search_type'
  - All encoders were of type `SentenceTransformer'
  - All cross_encoders were of type `CrossEncoder'

- Now `encoder-type' can be configured via the new `encoder_type' field
  in `TextSearchConfig' under `search-type` in `khoj.yml`.

- All the specified `encoder-type' class needs is an `encode' method
  that takes entries and returns embedding vectors

src/search_type/image_search.py

@@ -36,7 +36,7 @@ def initialize_model(search_config: ImageSearchConfig):
     encoder = load_model(
         model_dir  = search_config.model_directory,
         model_name = search_config.encoder,
-        model_type = SentenceTransformer)
+        model_type = search_config.encoder_type or SentenceTransformer)
 
     return encoder
 

src/search_type/text_search.py

@@ -37,7 +37,7 @@ def initialize_model(search_config: TextSearchConfig):
     bi_encoder = load_model(
         model_dir  = search_config.model_directory,
         model_name = search_config.encoder,
-        model_type = SentenceTransformer,
+        model_type = search_config.encoder_type or SentenceTransformer,
         device=f'{state.device}')
 
     # The cross-encoder re-ranks the results to improve quality