Update app.py

app.py

@@ -2,43 +2,70 @@ import streamlit as st
 from streamlit_chat import message
 from streamlit_extras.colored_header import colored_header
 from streamlit_extras.add_vertical_space import add_vertical_space
-from hugchat import hugchat
 from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+st.set_page_config(page_title="Einfach.HugChat")
 
-tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/oasst-sft-6-llama-30b-xor")
-model = AutoModelForCausalLM.from_pretrained("OpenAssistant/oasst-sft-6-llama-30b-xor")
-
-
-st.set_page_config(page_title="EinfachChat")
+# List of models
+models = ["vicuna-13b", "koala-13b", "oasst-pythia-12b", "RWKV-4-Raven-14B", 
+          "alpaca-13b", "chatglm-6b", "llama-13b", "dolly-v2-12b", "stablelm-tuned-alpha-7b", 
+          "fastchat-t5-3b", "mpt-7b-chat"]
 
 # Sidebar contents
 with st.sidebar:
     st.title('EinfachChat')
-    max_length = st.slider('Max Length', min_value=10, max_value=100, value=30)
-    do_sample = st.checkbox('Do Sample', value=True)
-    temperature = st.slider('Temperature', min_value=0.1, max_value=1.0, value=0.4)
-    no_repeat_ngram_size = st.slider('No Repeat N-Gram Size', min_value=1, max_value=10, value=1)
-    top_k = st.slider('Top K', min_value=1, max_value=100, value=50)
-    top_p = st.slider('Top P', min_value=0.1, max_value=1.0, value=0.2)
-
-# Rest of your original Streamlit code ...
-
-def generate_text(prompt, max_length, do_sample, temperature, no_repeat_ngram_size, top_k, top_p):
-    formatted_prompt = "\n" + prompt
-    if not ',' in prompt:
-        formatted_prompt += ','
-    prompt = tokenizer(formatted_prompt, return_tensors='pt')
-    prompt = {key: value.to(device) for key, value in prompt.items()}
-    out = model.generate(**prompt, max_length=max_length, do_sample=do_sample, temperature=temperature,
-                          no_repeat_ngram_size=no_repeat_ngram_size, top_k=top_k, top_p=top_p)
-    output = tokenizer.decode(out[0])
-    clean_output = output.replace('\n', '\n')
-    return clean_output
-
-# Inside the conditional display part, replace
-# response = generate_response(user_input)
-# with
-response = generate_text(user_input, max_length, do_sample, temperature, no_repeat_ngram_size, top_k, top_p)
+    st.markdown('''
+    ## About
+    This app is a LLM-powered chatbot built using:
+    - [Streamlit](https://streamlit.io/)
+    - [OpenAssistant/oasst-sft-6-llama-30b-xor](https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor) LLM model
+    
+    💡 Note: No API key required!
+    ''')
+    model_name = st.selectbox('Choose a model', models)
+    add_vertical_space(5)
+    st.write('Made with ❤️ by EinfachAlex')
+
+# Generate empty lists for generated and past.
+## generated stores AI generated responses
+if 'generated' not in st.session_state:
+    st.session_state['generated'] = ["Hallo, wie kann ich dir helfen ?"]
+## past stores User's questions
+if 'past' not in st.session_state:
+    st.session_state['past'] = ['Hi!']
+
+# Layout of input/response containers
+input_container = st.container()
+colored_header(label='', description='', color_name='blue-30')
+response_container = st.container()
+
+# User input
+## Function for taking user provided prompt as input
+def get_text():
+    input_text = st.text_input("You: ", "", key="input")
+    return input_text
+## Applying the user input box
+with input_container:
+    user_input = get_text()
+
+# Response output
+## Function for taking user prompt as input followed by producing AI generated responses
+def generate_response(prompt, model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    inputs = tokenizer(prompt, return_tensors='pt')
+    outputs = model.generate(**inputs)
+    response = tokenizer.decode(outputs[0])
+    return response
+
+## Conditional display of AI generated responses as a function of user provided prompts
+with response_container:
+    if user_input:
+        response = generate_response(user_input, model_name)
+        st.session_state.past.append(user_input)
+        st.session_state.generated.append(response)
+        
+    if st.session_state['generated']:
+        for i in range(len(st.session_state['generated'])):
+            message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')
+            message(st.session_state["generated"][i], key=str(i))