Update app.py

app.py

@@ -340,7 +340,7 @@ vectorstore,search_type="similarity",k=4,score_threshold=None
 base_retriever_HF = Vectorstore_backed_retriever(vector_store_HF,"similarity",k=10)
 
 
-
+'''
 def create_compression_retriever(embeddings, base_retriever, chunk_size=500, k=16, similarity_threshold=None):
     """Build a ContextualCompressionRetriever.
     We wrap the the base_retriever (a vectorstore-backed retriever) into a ContextualCompressionRetriever.
@@ -382,7 +382,10 @@ def create_compression_retriever(embeddings, base_retriever, chunk_size=500, k=1
     )
     print("compression retriever done")
     return compression_retriever
+'''
+
 
+'''
 def CohereRerank_retriever(  
     base_retriever, 
     cohere_api_key,cohere_model="rerank-multilingual-v2.0", top_n=8
@@ -407,10 +410,10 @@ def CohereRerank_retriever(
     )
     print("cohere rerank done")
     return retriever_Cohere
+'''
 
 
-
-
+'''
 def retrieval_blocks(
     create_vectorstore=True,# if True a Chroma vectorstore is created, else the Chroma vectorstore will be loaded
     LLM_service="HuggingFace",
@@ -514,7 +517,7 @@ and has {vector_store._collection.count()} chunks.")
         return retriever
     except Exception as e:
         print(e)
-
+'''
 
 
 
@@ -903,7 +906,7 @@ with gr.Blocks(css=css) as demo:
                 btn_clear_conversation = gr.Button("Start New Conversation")
 
 
-            with gr.Columnv(visible=False):
+            with gr.Column(visible=False):
                 prompt_template = gr.Dropdown(label="Choose an Expert:", choices=list(prompt_templates.keys()))
                 prompt_template_preview = gr.Markdown(elem_id="prompt_template_preview")
                 with gr.Accordion("Advanced parameters", open=False):