Update app.py

app.py

@@ -639,16 +639,25 @@ Example: letter_queue = deque(random.sample(string.ascii_uppercase, 10))"""
     st.write('🔍Run 1 is Complete.')
 
 
-# ------------------------------- land call to new guy here! --------------------------------------
-
+# ------------------------------- Land call to new guy here! --------------------------------------
     # New guys laughs
-
-    
-
-    arxivmain(query)
-
+    #arxivmain(query)
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    result = client.predict(
+    		"What is Semantic and Episodic memory?",	# str  in 'Search' Textbox component
+    		4,	# float (numeric value between 4 and 10) in 'Top n results as context' Slider component
+    		"Semantic Search - up to 10 Mar 2024",	# Literal['Semantic Search - up to 10 Mar 2024', 'Arxiv Search - Latest - (EXPERIMENTAL)']  in 'Search Source' Dropdown component
+    		"mistralai/Mixtral-8x7B-Instruct-v0.1",	# Literal['mistralai/Mixtral-8x7B-Instruct-v0.1', 'mistralai/Mistral-7B-Instruct-v0.2', 'google/gemma-7b-it', 'None']  in 'LLM Model' Dropdown component
+    		api_name="/update_with_rag_md"
+    )
+    st.markdown(result)
+    SpeechSynthesis(result)
 # ------------------------------------------------------------------------------------Thx----------
 
+    # 🔍Run 1+N - plain query
+    response = chat_with_model45(result)        # experimental 45
+    all = query + '   ' + response
+    st.write('🔍Run 1+N is Complete.')
 
 
     
@@ -1114,6 +1123,38 @@ def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
     st.write(time.time() - start_time)
     return full_reply_content
 
+# 11.1 45
+@st.cache_resource
+#def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):    # gpt-4-0125-preview	gpt-3.5-turbo
+def chat_with_model45(prompt, document_section='', model_choice='gpt-4-0125-preview'):    # gpt-4-0125-preview	gpt-3.5-turbo
+    model = model_choice
+    conversation = [{'role': 'system', 'content': 'You are a coder, inventor, and writer of quotes on wisdom as a helpful expert in all fields of health, math, development and AI using python.'}]
+    conversation.append({'role': 'user', 'content': prompt})
+    if len(document_section)>0:
+        conversation.append({'role': 'assistant', 'content': document_section})
+    start_time = time.time()
+    report = []
+    res_box = st.empty()
+    collected_chunks = []
+    collected_messages = []
+    
+    for chunk in openai.ChatCompletion.create(model=model_choice, messages=conversation, temperature=0.5, stream=True): 
+        collected_chunks.append(chunk)  
+        chunk_message = chunk['choices'][0]['delta']  
+        collected_messages.append(chunk_message) 
+        content=chunk["choices"][0].get("delta",{}).get("content")
+        try:
+            report.append(content)
+            if len(content) > 0:
+                result = "".join(report).strip()
+                res_box.markdown(f'*{result}*') 
+        except:
+            st.write(' ')
+    full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
+    st.write("Elapsed time:")
+    st.write(time.time() - start_time)
+    return full_reply_content
+
 @st.cache_resource
 def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):  # gpt-4-0125-preview	gpt-3.5-turbo
 #def chat_with_file_contents(prompt, file_content, model_choice='gpt-4-0125-preview'):  # gpt-4-0125-preview	gpt-3.5-turbo