Update chain_app.py

chain_app.py

@@ -1955,655 +1955,652 @@ async def on_chat_start():
 @cl.on_message  
 async def main(message: cl.Message):
     chat_profile = cl.user_session.get("chat_profile")
-        if chat_profile == 'neural-brain-AI':
-            completion = openai_client.chat.completions.create(
-                model="ft:gpt-3.5-turbo-1106:nb:aria1:9UWDrLJK",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-    
-        elif chat_profile == "Dorna-AI":
-            result = hf_text_client.predict(
-                message=message.content,
-                request=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-                param_3=512,
-                param_4=0.7,
-                param_5=0.95,
-                api_name="/chat"
-            )
-            model_response = result.strip("</s>") 
-            await cl.Message(
-                content=model_response
-            ).send()
-        elif chat_profile == "gpt4-o-mini":
-            completion = openai_client.chat.completions.create(
-                model="gpt-4o-mini",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-      #   elif chat_profile == 'Image-Generation':
-      #       result = hf_image_client.predict(
-    		# prompt=message.content,
-    		# negative_prompt="",
-    		# seed=0,
-    		# randomize_seed=True,
-    		# width=512,
-    		# height=512,
-    		# guidance_scale=0,
-    		# num_inference_steps=2,
-    		# api_name="/infer"
-      #       )
-      #       image = cl.Image(path=result, name="result", display="inline")
-      #       await cl.Message(
-      #           content="This message has an image!",
-      #           elements=[image],
-      #       ).send()
-        elif chat_profile == 'GPT-4':
-            completion = openai_client.chat.completions.create(
-                model="gpt-4",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-    
-        elif chat_profile == 'gpt-3.5-turbo':
-            completion = openai_client.chat.completions.create(
-                model="gpt-3.5-turbo",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-        elif chat_profile == 'GPT-3.5-turbo-0125':
-            completion = openai_client.chat.completions.create(
-                model="GPT-3.5-turbo-0125",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-        elif chat_profile == 'gpt-3.5-turbo-1106':
-            completion = openai_client.chat.completions.create(
-                model="gpt-3.5-turbo-1106",
-                messages=[
-                    {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
-                    {"role": "user", "content": message.content}
-                ]
-            )
-            model_response = completion.choices[0].message.content
-            await cl.Message(
-                content=model_response
-            ).send()
-        # elif chat_profile == 'davinci-002':
-        #     completion = openai_client.chat.completions.create(
-        #         model="davinci-002",
-        #         messages=[
-        #             {"role": "system", "content": "You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust"},
-        #             {"role": "user", "content": message.content}
-        #         ]
-        #     )
-        #     model_response = completion.choices[0].message.content
-        #     await cl.Message(
-        #         content=model_response
-        #     ).send()
-    
-        elif chat_profile == 'TTS':
-            response = openai_client.audio.speech.create(
-                model="tts-1",
-                voice="alloy",
-                input=message.content,
-            )
-    
-            response.stream_to_file("output.mp3")
-    
-            elements = [
-                cl.Audio(name="output.mp3", path="./output.mp3", display="inline"),
-            ]
-            await cl.Message(
-                content="Here it is the response!",
-                elements=elements,
-            ).send()
-    
-        elif chat_profile == 'Qwen2-57B':
-            client = Client("Qwen/Qwen2-57b-a14b-instruct-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-            ).send()
-            
-        elif chat_profile == 'Qwen2-7B':
-            client = Client("Qwen/Qwen2-7b-instruct-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        elif chat_profile == 'Qwen2-1.5B':
-            client = Client("Qwen/Qwen2-1.5b-instruct-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        elif chat_profile == 'Qwen2-0.5B':
-            client = Client("Qwen/Qwen2-0.5B-Instruct", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
     
-            ).send()
-        elif chat_profile == 'Qwen1.5-110B':
-            client = Client("Qwen/Qwen1.5-110B-Chat-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        elif chat_profile == 'Qwen1.5-32B':
-            client = Client("Qwen/Qwen1.5-32B-Chat-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        elif chat_profile == 'Qwen1.5-2.7B':
-            client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
-            result = client.predict(
-        		query=message.content,
-        		system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-        		api_name="/model_chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        # elif chat_profile == 'Qwen-14B':
-        #     client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
-        #     result = client.predict(
-        # 		query=message.content,
-        # 		system="You are a helpful AI chatbot made by two iranian boys named Artin Daneshvar and Sadra Noadoust",
-        # 		api_name="/model_chat"
-        #     )
-        #     await cl.Message(
-        #         content=result[1][0][1]
-    
-        #     ).send()
-    
-        # elif chat_profile == 'Qwen-7B':
-        #     client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
-        #     result = client.predict(
-        # 		query=message.content,
-        # 		system="You are a helpful AI chatbot made by two iranian boys named Artin Daneshvar and Sadra Noadoust",
-        # 		api_name="/model_chat"
-        #     )
-        #     await cl.Message(
-        #         content=result[1][0][1]
-    
-        #     ).send()
-            
-        elif chat_profile == 'Llama-3.1-405B':        
-            completion = groq_client.chat.completions.create(
-                model="llama-3.1-405b-reasoning",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
-        
-            complete_content = ""
-        
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
-        
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-    
-        
-        elif chat_profile == 'Llama-3.1-70B':
-            completion = groq_client.chat.completions.create(
-                model="llama-3.1-70b-versatile",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
-        
-            complete_content = ""
-        
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
-        
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Llama-3.1-8B':
-            completion = groq_client.chat.completions.create(
-                model="llama-3.1-8b-instant",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
-        
-            complete_content = ""
+    if chat_profile == 'neural-brain-AI':
+        completion = openai_client.chat.completions.create(
+            model="ft:gpt-3.5-turbo-1106:nb:aria1:9UWDrLJK",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+
+    elif chat_profile == "Dorna-AI":
+        result = hf_text_client.predict(
+            message=message.content,
+            request=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            param_3=512,
+            param_4=0.7,
+            param_5=0.95,
+            api_name="/chat"
+        )
+        model_response = result.strip("</s>") 
+        await cl.Message(
+            content=model_response
+        ).send()
+    elif chat_profile == "gpt4-o-mini":
+        completion = openai_client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+  #   elif chat_profile == 'Image-Generation':
+  #       result = hf_image_client.predict(
+        # prompt=message.content,
+        # negative_prompt="",
+        # seed=0,
+        # randomize_seed=True,
+        # width=512,
+        # height=512,
+        # guidance_scale=0,
+        # num_inference_steps=2,
+        # api_name="/infer"
+  #       )
+  #       image = cl.Image(path=result, name="result", display="inline")
+  #       await cl.Message(
+  #           content="This message has an image!",
+  #           elements=[image],
+  #       ).send()
+    elif chat_profile == 'GPT-4':
+        completion = openai_client.chat.completions.create(
+            model="gpt-4",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+
+    elif chat_profile == 'gpt-3.5-turbo':
+        completion = openai_client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+    elif chat_profile == 'GPT-3.5-turbo-0125':
+        completion = openai_client.chat.completions.create(
+            model="GPT-3.5-turbo-0125",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+    elif chat_profile == 'gpt-3.5-turbo-1106':
+        completion = openai_client.chat.completions.create(
+            model="gpt-3.5-turbo-1106",
+            messages=[
+                {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
+                {"role": "user", "content": message.content}
+            ]
+        )
+        model_response = completion.choices[0].message.content
+        await cl.Message(
+            content=model_response
+        ).send()
+    # elif chat_profile == 'davinci-002':
+    #     completion = openai_client.chat.completions.create(
+    #         model="davinci-002",
+    #         messages=[
+    #             {"role": "system", "content": "You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust"},
+    #             {"role": "user", "content": message.content}
+    #         ]
+    #     )
+    #     model_response = completion.choices[0].message.content
+    #     await cl.Message(
+    #         content=model_response
+    #     ).send()
+
+    elif chat_profile == 'TTS':
+        response = openai_client.audio.speech.create(
+            model="tts-1",
+            voice="alloy",
+            input=message.content,
+        )
+
+        response.stream_to_file("output.mp3")
+
+        elements = [
+            cl.Audio(name="output.mp3", path="./output.mp3", display="inline"),
+        ]
+        await cl.Message(
+            content="Here it is the response!",
+            elements=elements,
+        ).send()
+
+    elif chat_profile == 'Qwen2-57B':
+        client = Client("Qwen/Qwen2-57b-a14b-instruct-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+        ).send()
         
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
+    elif chat_profile == 'Qwen2-7B':
+        client = Client("Qwen/Qwen2-7b-instruct-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+
+    elif chat_profile == 'Qwen2-1.5B':
+        client = Client("Qwen/Qwen2-1.5b-instruct-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+
+    elif chat_profile == 'Qwen2-0.5B':
+        client = Client("Qwen/Qwen2-0.5B-Instruct", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+    elif chat_profile == 'Qwen1.5-110B':
+        client = Client("Qwen/Qwen1.5-110B-Chat-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+
+    elif chat_profile == 'Qwen1.5-32B':
+        client = Client("Qwen/Qwen1.5-32B-Chat-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+
+    elif chat_profile == 'Qwen1.5-2.7B':
+        client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
+        result = client.predict(
+            query=message.content,
+            system=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            api_name="/model_chat"
+        )
+        await cl.Message(
+            content=result[1][0][1]
+
+        ).send()
+
+    # elif chat_profile == 'Qwen-14B':
+    #     client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
+    #     result = client.predict(
+    # 		query=message.content,
+    # 		system="You are a helpful AI chatbot made by two iranian boys named Artin Daneshvar and Sadra Noadoust",
+    # 		api_name="/model_chat"
+    #     )
+    #     await cl.Message(
+    #         content=result[1][0][1]
+
+    #     ).send()
+
+    # elif chat_profile == 'Qwen-7B':
+    #     client = Client("Qwen/qwen1.5-MoE-A2.7B-Chat-demo", hf_token=hf_token)
+    #     result = client.predict(
+    # 		query=message.content,
+    # 		system="You are a helpful AI chatbot made by two iranian boys named Artin Daneshvar and Sadra Noadoust",
+    # 		api_name="/model_chat"
+    #     )
+    #     await cl.Message(
+    #         content=result[1][0][1]
+
+    #     ).send()
         
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Llama-3-70B':
-            completion = groq_client.chat.completions.create(
-                model="llama3-70b-8192",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
+    elif chat_profile == 'Llama-3.1-405B':        
+        completion = groq_client.chat.completions.create(
+            model="llama-3.1-405b-reasoning",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
     
-            complete_content = ""
+        complete_content = ""
     
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
-    
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Llama-3-8B':
-            completion = groq_client.chat.completions.create(
-                model="llama3-8b-8192",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
-    
-            complete_content = ""
-    
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
-    
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-
-        elif chat_profile == 'gemma2-27B':
-            client = Client("gokaygokay/Gemma-2-llamacpp")
-            result = client.predict(
-            		message=message.content,
-            		model="gemma-2-27b-it-Q5_K_M.gguf",
-            		system_message=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-            		max_tokens=2048,
-            		temperature=0.7,
-            		top_p=0.95,
-            		top_k=40,
-            		repeat_penalty=1.1,
-            		api_name="/chat"
-            )
-            await cl.Message(
-                content=result
-            ).send()
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
     
-        elif chat_profile == 'gemma2-9B':
-            completion = groq_client.chat.completions.create(
-                model="gemma2-9b-it",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
     
-            complete_content = ""
+    elif chat_profile == 'Llama-3.1-70B':
+        completion = groq_client.chat.completions.create(
+            model="llama-3.1-70b-versatile",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
     
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
+        complete_content = ""
     
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
     
-        elif chat_profile == 'gemma-7B':
-            completion = groq_client.chat.completions.create(
-                model="gemma-7b-it",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Llama-3.1-8B':
+        completion = groq_client.chat.completions.create(
+            model="llama-3.1-8b-instant",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
     
-            complete_content = ""
+        complete_content = ""
     
-            # Iterate over each chunk
-            for chunk in completion:
-                # Retrieve the content from the current chunk
-                content = chunk.choices[0].delta.content
-                
-                # Check if the content is not None before concatenating it
-                if content is not None:
-                    complete_content += content
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
     
-            # Send the concatenated content as a message
-            await cl.Message(content=complete_content).send()
-        
-        elif chat_profile == "zephyr-7B":
-            result = hf_text_client.predict(
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Llama-3-70B':
+        completion = groq_client.chat.completions.create(
+            model="llama3-70b-8192",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        complete_content = ""
+
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
+
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Llama-3-8B':
+        completion = groq_client.chat.completions.create(
+            model="llama3-8b-8192",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        complete_content = ""
+
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
+
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'gemma2-27B':
+        client = Client("gokaygokay/Gemma-2-llamacpp")
+        result = client.predict(
                 message=message.content,
-                request=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
-                param_3=512,
-                param_4=0.7,
-                param_5=0.95,
+                model="gemma-2-27b-it-Q5_K_M.gguf",
+                system_message=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+                max_tokens=2048,
+                temperature=0.7,
+                top_p=0.95,
+                top_k=40,
+                repeat_penalty=1.1,
                 api_name="/chat"
-            )
-            model_response = result.strip("</s>") 
-            await cl.Message(
-                content=model_response
-            ).send()
-    
-        elif chat_profile == 'mixtral-8x7B':
-            completion = groq_client.chat.completions.create(
-                model="mixtral-8x7b-32768",
-                messages=[
-                    {
-                        "role": "user",
-                        "content": message.content
-                    }
-                ],
-                temperature=1,
-                max_tokens=1024,
-                top_p=1,
-                stream=True,
-                stop=None,
-            )
-    
-            complete_content = ""
-    
-            for chunk in completion:
-                content = chunk.choices[0].delta.content
-                
-                if content is not None:
-                    complete_content += content
-    
-            await cl.Message(content=complete_content).send() 
-    
-        elif chat_profile == 'mistral-nemo-12B':
-            client = Client("0x7o/Mistral-Nemo-Instruct", hf_token=hf_token)
-            result = client.predict(
-            		message=message.content,
-            		max_new_tokens=512,
-            		temperature=0.7,
-            		top_p=0.95,
-            		api_name="/chat"
-            )
-            await cl.Message(
-                content=result[1][0][1]
-    
-            ).send()
-    
-        # elif chat_profile == 'Toka-353M':
-        #     output = query({
-        #     "inputs": message.content,
-        # })
-        #     await cl.Message(
-        #         content=output[0]['sequence']
-        #     ).send()
-    
-        elif chat_profile == 'Aya-23B':
-            stream = co.chat_stream( 
-            model='c4ai-aya-23',
-            message=message.content,
-            temperature=0.3,
-            # chat_history=[{"role": "User", "message": "Hello"}, {"role": "Chatbot", "message": "Hello! How can I help you today?"}, {"role": "User", "message": "Hi"}, {"role": "User", "message": "hello"}],
-            prompt_truncation='OFF',
-            connectors=[],
-            ) 
-    
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
+        )
+        await cl.Message(
+            content=result
+        ).send()
+
+    elif chat_profile == 'gemma2-9B':
+        completion = groq_client.chat.completions.create(
+            model="gemma2-9b-it",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        complete_content = ""
+
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
+
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'gemma-7B':
+        completion = groq_client.chat.completions.create(
+            model="gemma-7b-it",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        complete_content = ""
+
+        # Iterate over each chunk
+        for chunk in completion:
+            # Retrieve the content from the current chunk
+            content = chunk.choices[0].delta.content
+            
+            # Check if the content is not None before concatenating it
+            if content is not None:
+                complete_content += content
+
+        # Send the concatenated content as a message
+        await cl.Message(content=complete_content).send()
     
-        elif chat_profile == 'Aya-35B':
-            stream = co.chat_stream( 
-            model='c4ai-aya-23',
+    elif chat_profile == "zephyr-7B":
+        result = hf_text_client.predict(
             message=message.content,
-            temperature=0.3,
-            # chat_history=[{"role": "User", "message": "Hello"}, {"role": "Chatbot", "message": "Hello! How can I help you today?"}, {"role": "User", "message": "Hi"}, {"role": "User", "message": "hello"}],
-            prompt_truncation='OFF',
-            connectors=[],
-            ) 
-    
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Command-R-Plus':
-            stream = co.chat_stream( 
-              model='command-r-plus',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Command-R':
-            stream = co.chat_stream( 
-              model='command-r',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Command':
-            stream = co.chat_stream( 
-              model='command',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
+            request=f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people",
+            param_3=512,
+            param_4=0.7,
+            param_5=0.95,
+            api_name="/chat"
+        )
+        model_response = result.strip("</s>") 
+        await cl.Message(
+            content=model_response
+        ).send()
+
+    elif chat_profile == 'mixtral-8x7B':
+        completion = groq_client.chat.completions.create(
+            model="mixtral-8x7b-32768",
+            messages=[
+                {
+                    "role": "user",
+                    "content": message.content
+                }
+            ],
+            temperature=1,
+            max_tokens=1024,
+            top_p=1,
+            stream=True,
+            stop=None,
+        )
+
+        complete_content = ""
+
+        for chunk in completion:
+            content = chunk.choices[0].delta.content
             
-        elif chat_profile == 'Command-Light':
-            stream = co.chat_stream( 
-              model='command-light',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Command-Light-Nightly':
-            stream = co.chat_stream( 
-              model='command-light-nightly',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    
-        elif chat_profile == 'Command-Nightly':
-            stream = co.chat_stream( 
-              model='command-light-nightly',
-              message=message.content,
-              temperature=0.3,
-              chat_history=[],
-              prompt_truncation='AUTO',
-            ) 
-            complete_content = ''
-            for event in stream:
-                if event.event_type == 'text-generation':
-                    complete_content += event.text
-            await cl.Message(content=complete_content).send()
-    else:
+            if content is not None:
+                complete_content += content
+
+        await cl.Message(content=complete_content).send() 
+
+    elif chat_profile == 'mistral-nemo-12B':
+        client = Client("0x7o/Mistral-Nemo-Instruct", hf_token=hf_token)
+        result = client.predict(
+                message=message.content,
+                max_new_tokens=512,
+                temperature=0.7,
+                top_p=0.95,
+                api_name="/chat"
+        )
         await cl.Message(
-            content="Try Sending your message again. or edit it.",
+            content=result[1][0][1]
+
         ).send()
+
+    # elif chat_profile == 'Toka-353M':
+    #     output = query({
+    #     "inputs": message.content,
+    # })
+    #     await cl.Message(
+    #         content=output[0]['sequence']
+    #     ).send()
+
+    elif chat_profile == 'Aya-23B':
+        stream = co.chat_stream( 
+        model='c4ai-aya-23',
+        message=message.content,
+        temperature=0.3,
+        # chat_history=[{"role": "User", "message": "Hello"}, {"role": "Chatbot", "message": "Hello! How can I help you today?"}, {"role": "User", "message": "Hi"}, {"role": "User", "message": "hello"}],
+        prompt_truncation='OFF',
+        connectors=[],
+        ) 
+
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Aya-35B':
+        stream = co.chat_stream( 
+        model='c4ai-aya-23',
+        message=message.content,
+        temperature=0.3,
+        # chat_history=[{"role": "User", "message": "Hello"}, {"role": "Chatbot", "message": "Hello! How can I help you today?"}, {"role": "User", "message": "Hi"}, {"role": "User", "message": "hello"}],
+        prompt_truncation='OFF',
+        connectors=[],
+        ) 
+
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Command-R-Plus':
+        stream = co.chat_stream( 
+          model='command-r-plus',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Command-R':
+        stream = co.chat_stream( 
+          model='command-r',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Command':
+        stream = co.chat_stream( 
+          model='command',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+        
+    elif chat_profile == 'Command-Light':
+        stream = co.chat_stream( 
+          model='command-light',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Command-Light-Nightly':
+        stream = co.chat_stream( 
+          model='command-light-nightly',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
+
+    elif chat_profile == 'Command-Nightly':
+        stream = co.chat_stream( 
+          model='command-light-nightly',
+          message=message.content,
+          temperature=0.3,
+          chat_history=[],
+          prompt_truncation='AUTO',
+        ) 
+        complete_content = ''
+        for event in stream:
+            if event.event_type == 'text-generation':
+                complete_content += event.text
+        await cl.Message(content=complete_content).send()
         
 
 @cl.on_settings_update