Update app.py

app.py

@@ -7,16 +7,16 @@ import gradio as gr
 from utilities.setup import get_files
 
 from connections.pinecone import PineconeConnector
-#from connections.model import InferencePipeline
+from connections.model import InferencePipeline
 
 from services.embed_service.embed import EmbeddingService
-#from services.qa_service.qna import QAService
-from server import QAService
+from services.qa_service.qna import QAService
+#from server import QAService
 
-#import spaces
+import spaces
 
 #################### Functions ####################
-#@spaces.GPU
+@spaces.GPU
 def process_transcripts(files, context):
     
     print(files)
@@ -26,13 +26,17 @@ def process_transcripts(files, context):
     # some way to wait or a progress bar?
     return "Completed Loading Data"
 
-#@spaces.GPU
+@spaces.GPU
 def retrieve_answer(question, goals):
     #with QAService(conf) as q:
     #    q.infer(question)
 
-    #with QAService(conf, pinecone=pinecones, model_pipeline=pipeline, question=question, goals=goals) as q:
-        #q.run()
+    with QAService(conf, 
+                   pinecone=pinecones, 
+                   model_pipeline=pipeline, 
+                   question=question, 
+                   goals=goals) as q:
+        q.run()
 
     return question + goals
 
@@ -92,14 +96,10 @@ if __name__ == "__main__":
     pinecones = pc_connector.run()
 
     # initialize model connector
-    #pipeline = InferencePipeline()
+    pipeline = InferencePipeline()
 
-    #pipeline = InferencePipeline(conf,
-    #                             api_key=keys["huggingface"]
-    #                             )
-#
-#pipeline.infer(prompt)
-
-    
+    pipeline = InferencePipeline(conf,
+                                 api_key=keys["huggingface"]
+                                 )
     # run main
     main(conf)