Update app.py

app.py

@@ -1,70 +1,10 @@
-""" Simple Chatbot
-@author: Nigel Gebodh
-@email: nigel.gebodh@gmail.com
-
-"""
-
 import streamlit as st
-from openai import OpenAI
+import requests
+import json
 import os
-import sys
-from dotenv import load_dotenv, dotenv_values
-load_dotenv()
-
-
-
-
-
-# initialize the client
-client = OpenAI(
-  base_url="https://api-inference.huggingface.co/v1",
-  api_key=os.environ.get('HUGGINGFACEHUB_API_TOKEN')#"hf_xxx" # Replace with your token
-) 
-
-
-
+from dotenv import load_dotenv
 
-#Create supported models
-model_links ={
-    "Mistral":"mistralai/Mistral-7B-Instruct-v0.2",
-    "Gemma-7B":"google/gemma-7b-it",
-    "Gemma-2B":"google/gemma-2b-it",
-    "Zephyr-7B-β":"HuggingFaceH4/zephyr-7b-beta",
-
-}
-
-#Pull info about the model to display
-model_info ={
-    "Mistral":
-        {'description':"""The Mistral model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
-            \nIt was created by the [**Mistral AI**](https://mistral.ai/news/announcing-mistral-7b/) team as has over  **7 billion parameters.** \n""",
-        'logo':'https://mistral.ai/images/logo_hubc88c4ece131b91c7cb753f40e9e1cc5_2589_256x0_resize_q97_h2_lanczos_3.webp'},
-    "Gemma-7B":        
-        {'description':"""The Gemma model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
-            \nIt was created by the [**Google's AI Team**](https://blog.google/technology/developers/gemma-open-models/) team as has over  **7 billion parameters.** \n""",
-        'logo':'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'},
-    "Gemma-2B":        
-    {'description':"""The Gemma model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
-        \nIt was created by the [**Google's AI Team**](https://blog.google/technology/developers/gemma-open-models/) team as has over  **2 billion parameters.** \n""",
-    'logo':'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'},
-    "Zephyr-7B":        
-    {'description':"""The Zephyr model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
-        \nFrom Huggingface: \n\
-        Zephyr is a series of language models that are trained to act as helpful assistants. \
-        [Zephyr 7B Gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)\
-        is the third model in the series, and is a fine-tuned version of google/gemma-7b \
-        that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO)\n""",
-    'logo':'https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1/resolve/main/thumbnail.png'},
-    "Zephyr-7B-β":        
-    {'description':"""The Zephyr model is a **Large Language Model (LLM)** that's able to have question and answer interactions.\n \
-        \nFrom Huggingface: \n\
-        Zephyr is a series of language models that are trained to act as helpful assistants. \
-        [Zephyr-7B-β](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)\
-        is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 \
-        that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO)\n""",
-    'logo':'https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png'},
-
-}
+load_dotenv()
 
 def reset_conversation():
     '''
@@ -73,25 +13,112 @@ def reset_conversation():
     st.session_state.conversation = []
     st.session_state.messages = []
     return None
-    
-
-
-
-# Define the available models
-models =[key for key in model_links.keys()]
-
-# Create the sidebar with the dropdown for model selection
-selected_model = st.sidebar.selectbox("Select Model", models)
 
-#Create a temperature slider
-temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, (0.5))
-
-
-#Add reset button to clear conversation
-st.sidebar.button('Reset Chat', on_click=reset_conversation) #Reset button
+# Define model links for Hugging Face models
+model_links = {
+    "Mistral": "mistralai/Mistral-7B-Instruct-v0.2",
+    "Gemma-7B": "google/gemma-7b-it",
+    "Gemma-2B": "google/gemma-2b-it",
+    "Zephyr-7B-β": "HuggingFaceH4/zephyr-7b-beta",
+    "Nous-Hermes-2-Yi-34B": "NousResearch/Nous-Hermes-2-Yi-34B"
+}
 
+# Define model info for all models
+model_info = {
+    "Mistral": {
+        'description': "The Mistral model is a Large Language Model (LLM) developed by Mistral AI.",
+        'logo': 'https://mistral.ai/images/logo_hubc88c4ece131b91c7cb753f40e9e1cc5_2589_256x0_resize_q97_h2_lanczos_3.webp'
+    },
+    "Gemma-7B": {
+        'description': "The Gemma-7B model is a Large Language Model (LLM) developed by Google with 7 billion parameters.",
+        'logo': 'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'
+    },
+    "Gemma-2B": {
+        'description': "The Gemma-2B model is a Large Language Model (LLM) developed by Google with 2 billion parameters.",
+        'logo': 'https://pbs.twimg.com/media/GG3sJg7X0AEaNIq.jpg'
+    },
+    "Zephyr-7B-β": {
+        'description': "The Zephyr-7B-β model is a Large Language Model (LLM) developed by HuggingFace.",
+        'logo': 'https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png'
+    },
+    "Nous-Hermes-2-Yi-34B": {
+        'description': "The Nous Hermes model is a Large Language Model (LLM) developed by Nous Research with 34 billion parameters.",
+        'logo': 'https://example.com/nous_hermes_logo.png'
+    }
+}
 
-# Create model description
+# Function to interact with Hugging Face models
+def interact_with_huggingface_model(messages, model):
+    # Add your code here to interact with the Hugging Face model
+    pass
+
+# Function to interact with the Together API model
+def interact_with_together_api(messages):
+    all_messages = []
+
+    if not messages:  # If history is empty
+        all_messages.append({"role": "user", "content": ""})
+        history = [("", "")]  # Add dummy values to prevent unpacking error
+
+    for human, assistant in messages:
+        all_messages.append({"role": "user", "content": human})
+        all_messages.append({"role": "assistant", "content": assistant})
+
+    all_messages.append({"role": "user", "content": messages[-1][1]})
+
+    url = "https://api.together.xyz/v1/chat/completions"
+    payload = {
+        "model": "NousResearch/Nous-Hermes-2-Yi-34B",
+        "temperature": 1.05,
+        "top_p": 0.9,
+        "top_k": 50,
+        "repetition_penalty": 1,
+        "n": 1,
+        "messages": all_messages,
+        "stream_tokens": True,
+    }
+
+    TOGETHER_API_KEY = os.getenv('TOGETHER_API_KEY')
+    headers = {
+        "accept": "application/json",
+        "content-type": "application/json",
+        "Authorization": f"Bearer {TOGETHER_API_KEY}",
+    }
+
+    response = requests.post(url, json=payload, headers=headers, stream=True)
+    response.raise_for_status()  # Ensure HTTP request was successful
+
+    for line in response.iter_lines():
+        if line:
+            decoded_line = line.decode('utf-8')
+
+            # Check for the completion signal
+            if decoded_line == "data: [DONE]":
+                yield entire_assistant_response  # Yield the entire response at the end
+                break
+
+            try:
+                # Decode and strip any SSE format specific prefix ("data: ")
+                if decoded_line.startswith("data: "):
+                    decoded_line = decoded_line.replace("data: ", "")
+                    chunk_data = json.loads(decoded_line)
+                    content = chunk_data['choices'][0]['delta']['content']
+                    entire_assistant_response += content  # Aggregate content
+                    yield entire_assistant_response
+
+            except json.JSONDecodeError:
+                print(f"Invalid JSON received: {decoded_line}")
+                continue
+            except KeyError as e:
+                print(f"KeyError encountered: {e}")
+                continue
+
+# Create sidebar with model selection dropdown and temperature slider
+selected_model = st.sidebar.selectbox("Select Model", list(model_links.keys()))
+temperature = st.sidebar.slider('Select Temperature', 0.0, 1.0, 0.5)
+st.sidebar.button('Reset Chat', on_click=reset_conversation)
+
+# Display model description and logo
 st.sidebar.write(f"You're now chatting with **{selected_model}**")
 st.sidebar.markdown(model_info[selected_model]['description'])
 st.sidebar.image(model_info[selected_model]['logo'])
@@ -99,65 +126,33 @@ st.sidebar.markdown("*Generated content may be inaccurate or false.*")
 st.sidebar.markdown("\nLearn how to build this chatbot [here](https://ngebodh.github.io/projects/2024-03-05/).")
 st.sidebar.markdown("\nRun into issues? Try the [back-up](https://huggingface.co/spaces/ngebodh/SimpleChatbot-Backup).")
 
-
-
-
-if "prev_option" not in st.session_state:
-    st.session_state.prev_option = selected_model
-
-if st.session_state.prev_option != selected_model:
-    st.session_state.messages = []
-    # st.write(f"Changed to {selected_model}")
-    st.session_state.prev_option = selected_model
-    reset_conversation()
-
-
-
-#Pull in the model we want to use
-repo_id = model_links[selected_model]
-
-
-st.subheader(f'AI - {selected_model}')
-# st.title(f'ChatBot Using {selected_model}')
-
-# Set a default model
-if selected_model not in st.session_state:
-    st.session_state[selected_model] = model_links[selected_model] 
-
 # Initialize chat history
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-
 # Display chat messages from history on app rerun
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-
-
 # Accept user input
-if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
-
+if prompt := st.chat_input(f"Hi, I'm {selected_model}, ask me a question"):
     # Display user message in chat message container
     with st.chat_message("user"):
         st.markdown(prompt)
     # Add user message to chat history
-    st.session_state.messages.append({"role": "user", "content": prompt})
+    st.session_state.messages.append(("user", prompt))
 
+    # Interact with selected model
+    if selected_model == "Nous-Hermes-2-Yi-34B":
+        stream = interact_with_together_api(st.session_state.messages)
+    else:
+        interact_with_huggingface_model(st.session_state.messages, model_links[selected_model])
 
     # Display assistant response in chat message container
     with st.chat_message("assistant"):
-        stream = client.chat.completions.create(
-            model=model_links[selected_model],
-            messages=[
-                {"role": m["role"], "content": m["content"]}
-                for m in st.session_state.messages
-            ],
-            temperature=temp_values,#0.5,
-            stream=True,
-            max_tokens=3000,
-        )
-
-        response = st.write_stream(stream)
-    st.session_state.messages.append({"role": "assistant", "content": response})
+        response = ""
+        for chunk in stream:
+            response = chunk
+            st.markdown(response)
+    st.session_state.messages.append(("assistant", response))