chore: Parse labels from CSV

lib/medical_transcription/transcriber.ex

@@ -1,9 +1,10 @@
 defmodule MedicalTranscription.Transcriber do
+  @input_filename "CMS32_DESC_LONG_SHORT_DX"
+
   def stream_transcription_and_search(live_view_pid, audio_file_path) do
     {model_info, tokenizer} = AudioTagger.Classifier.SemanticSearch.prepare_model()
-
-    labels_df = AudioTagger.SampleData.icd10_codes()
-    label_embeddings_path = Path.join(__DIR__, "../../icd10_vector_tensors.bin")
+    labels_df = read_labels_from_csv!()
+    label_embeddings_path = Path.join(__DIR__, "../../#{@input_filename}.bin")
 
     # TODO: We could explore storing these vectors within pgvector or Pinecone.io
     label_embeddings =
@@ -40,4 +41,18 @@ defmodule MedicalTranscription.Transcriber do
       send(live_view_pid, {:transcription_row, chunk_result})
     end
   end
+
+  defp read_labels_from_csv! do
+    __DIR__
+    |> Path.join("../../#{@input_filename}.csv")
+    |> Explorer.DataFrame.from_csv!(
+      dtypes: [
+        {"DIAGNOSIS CODE", :string},
+        {"LONG DESCRIPTION", :string},
+        {"SHORT DESCRIPTION", :string}
+      ]
+    )
+    |> Explorer.DataFrame.select([0, 1, 2])
+    |> Explorer.DataFrame.rename(["code", "long_description", "short_description"])
+  end
 end