Update app.py

app.py

@@ -210,62 +210,33 @@ def search_glossary(query):
         all_results = ""
         st.markdown(f"- {query}")
 
-        
+        # 🔍 ArXiv RAG researcher expert ~-<>-~ Paper Summary & Ask LLM
         #database_choice Literal['Semantic Search', 'Arxiv Search - Latest - (EXPERIMENTAL)'] Default: "Semantic Search"
         #llm_model_picked Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None'] Default: "mistralai/Mistral-7B-Instruct-v0.2"
-    
-        # 🔍 Run 1 - ArXiv RAG researcher expert ~-<>-~ Paper Summary & Ask LLM
+        
         client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
         response2 = client.predict(
             message=query,	# str  in 'parameter_13' Textbox component
-            llm_results_use=5,
+            llm_results_use=10,
     		database_choice="Semantic Search",
     		llm_model_picked="mistralai/Mistral-7B-Instruct-v0.2",
             api_name="/update_with_rag_md"
         )
-        st.code(response2, language="python", line_numbers=True)
+        st.markdown(response2)
+        st.code(response2, language="python", line_numbers=True, wrap_lines=True)
 
-        
         #llm_model_picked Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None'] Default: "mistralai/Mistral-7B-Instruct-v0.2"
-
+                
+        # 🔍 ArXiv RAG researcher expert ~-<>-~ Paper Summary & Ask LLM
         result = client.predict(
     		prompt=query,
     		llm_model_picked="mistralai/Mistral-7B-Instruct-v0.2",
     		stream_outputs=True,
     		api_name="/ask_llm"
         )
+        st.markdown(result)
         st.code(result, language="python", line_numbers=True)
-
-        response1 = client.predict(
-            query,	
-            10,	
-            "Semantic Search - up to 10 Mar 2024",	# Search Source Dropdown component
-            "mistralai/Mixtral-8x7B-Instruct-v0.1",	# LLM Model Dropdown component
-            api_name="/update_with_rag_md"
-        )
-        st.code(response1[0], language="python", line_numbers=True, wrap_lines=False)
-
-        
-        # ArXiv searcher - Paper Summary & Ask LLM
-        # client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
         
-        response1 = client.predict(
-            message=query,
-            llm_results_use=5,
-            database_choice=database_choice,
-            llm_model_picked=model_choice,
-            api_name="/update_with_rag_md"
-        )
-        st.code(response1, language="python", line_numbers=True, wrap_lines=False)
-
-        response2 = client.predict(
-            prompt=query,
-            llm_model_picked=model_choice,
-            stream_outputs=True,
-            api_name="/ask_llm"
-        )
-        st.code(response2, language="python", line_numbers=True, wrap_lines=False)
-
         # Aggregate hyperlinks and show with emojis
         hyperlinks = extract_hyperlinks([response1, response2])
         st.markdown("### 🔗 Aggregated Hyperlinks")
@@ -277,60 +248,10 @@ def search_glossary(query):
         st.code(f"Response 1: \n{format_with_line_numbers(response1)}\n\nResponse 2: \n{format_with_line_numbers(response2)}", language="json")
 
         # Save both responses to Cosmos DB
-        save_to_cosmos_db(query, response1, response2)
+        save_to_cosmos_db(query, response2, result)
 
 
         
-    
-
-# 🔍 Search Glossary function
-def search_glossaryv1(query):
-    # 🕵️‍♂️ Searching the glossary for: query
-    all_results = ""
-    st.markdown(f"- {query}")
-
-    #database_choice Literal['Semantic Search', 'Arxiv Search - Latest - (EXPERIMENTAL)'] Default: "Semantic Search"
-    #llm_model_picked Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None'] Default: "mistralai/Mistral-7B-Instruct-v0.2"
-
-    # 🔍 Run 1 - ArXiv RAG researcher expert ~-<>-~ Paper Summary & Ask LLM
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    response2 = client.predict(
-        message=query,	# str  in 'parameter_13' Textbox component
-        llm_results_use=5,
-		database_choice="Semantic Search",
-		llm_model_picked="mistralai/Mistral-7B-Instruct-v0.2",
-        api_name="/update_with_rag_md"
-    )
-
-    #llm_model_picked Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None'] Default: "mistralai/Mistral-7B-Instruct-v0.2"
-
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    result = client.predict(
-		prompt=query,
-		llm_model_picked="mistralai/Mistral-7B-Instruct-v0.2",
-		stream_outputs=True,
-		api_name="/ask_llm"
-    )
-    st.write('🔍 Run of Multi-Agent System Paper Summary Spec is Complete')
-    st.markdown(response2)
-    
-    # ArXiv searcher ~-<>-~ Paper References - Update with RAG
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    response1 = client.predict(
-        query,	
-        10,	
-        "Semantic Search - up to 10 Mar 2024",	# Search Source Dropdown component
-        "mistralai/Mixtral-8x7B-Instruct-v0.1",	# LLM Model Dropdown component
-        api_name="/update_with_rag_md"
-    )
-
-
-    
-    #st.write('🔍 Run of Multi-Agent System Paper References is Complete')
-    #responseall = response2 + response1[0] + response1[1]
-    #st.markdown(responseall)
-    return responseall
-
 # 📝 Function to process text input
 def process_text(text_input):
     if text_input: