# import streamlit as st # from openai import OpenAI # 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 # ) # #Create supported models # model_links ={ # "Mistral-7b":"mistralai/Mistral-7B-Instruct-v0.2", # "Mistral-8x7b":"mistralai/Mixtral-8x7B-Instruct-v0.1" # # "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-7b": # {'description':"""The Mistral 7B 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'}, # "Mistral-8x7b": # {'description':"""The Mistral 8x7B 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-8x7b/) team as has based on MOE arch.** \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'}, # } # def reset_conversation(): # ''' # Resets 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 # # Create model description # 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']) # # 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"): # # 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}) # # 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}) # from huggingface_hub import InferenceClient # import gradio as gr # client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2") # def format_prompt(message, history): # prompt = "" # for user_prompt, bot_response in history: # prompt += f"[INST] {user_prompt} [/INST]" # prompt += f" {bot_response} " # prompt += f"[INST] {message} [/INST]" # return prompt # def generate( # prompt, history, temperature=0.2, max_new_tokens=3000, top_p=0.95, repetition_penalty=1.0, # ): # temperature = float(temperature) # if temperature < 1e-2: # temperature = 1e-2 # top_p = float(top_p) # generate_kwargs = dict( # temperature=temperature, # max_new_tokens=max_new_tokens, # top_p=top_p, # repetition_penalty=repetition_penalty, # do_sample=True, # seed=42, # ) # formatted_prompt = format_prompt(prompt, history) # stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False) # output = "" # for response in stream: # output += response.token.text # yield output # return output # mychatbot = gr.Chatbot( # avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,) # demo = gr.ChatInterface(fn=generate, # chatbot=mychatbot, # title="Mistral-Chat", # retry_btn=None, # undo_btn=None # ) # demo.queue().launch(show_api=False) import gradio as gr import boto3 import os from langchain.llms import Bedrock from langchain.chains import ConversationChain #from langchain.memory import ConversationBufferWindowMemory from langchain.prompts.prompt import PromptTemplate access_key_id = os.environ['aws_access_key_id'] secret_access_key = os.environ['aws_secret_access_key'] client = boto3.client(service_name='bedrock-runtime',region_name='us-east-1',aws_access_key_id=access_key_id,aws_secret_access_key=secret_access_key) prompt = """ <|begin_of_text|> {history} <|start_header_id|>user<|end_header_id|> {input} <|eot_id|> <|start_header_id|>assistant<|end_header_id|> """ prompt_temp = PromptTemplate(input_variables=["history", "input"], template=template) def generate( prompt_temp, temperature=0.2, max_gen_len=1024, top_p=0.95, ): temperature = float(temperature) if temperature < 1e-2: temperature = 1e-2 top_p = float(top_p) generate_kwargs = dict( temperature=temperature, max_gen_len=max_gen_len, top_p=top_p) llm = Bedrock(model_id="meta.llama3-8b-instruct-v1:0",model_kwargs=generate_kwargs,client=bedrock_runtime) conversation = ConversationChain( prompt=prompt_temp, llm=llm, verbose=True, memory= ConversationBufferMemory(ai_prefix="AI Assistant") ) chat_history = [] #result =conversation.predict(input="Hi there!") result = conversation({"input": message, "history":chat_history }) chat_history.append((message, result['response'])) return result['response'] demo=gr.ChatInterface(qa_fn) demo.queue().launch(show_api=False) # import gradio as gr # import boto3 # import json # from botocore.exceptions import ClientError # import os # access_key_id = os.environ['aws_access_key_id'] # secret_access_key = os.environ['aws_secret_access_key'] # bedrock = boto3.client(service_name='bedrock-runtime',region_name='us-east-1',aws_access_key_id=access_key_id,aws_secret_access_key=secret_access_key) # def invoke_llama3_8b(user_message): # try: # # Set the model ID, e.g., Llama 3 8B Instruct. # model_id = "meta.llama3-8b-instruct-v1:0" # # Embed the message in Llama 3's prompt format. # prompt = f""" # <|begin_of_text|> # <|start_header_id|>user<|end_header_id|> # {user_message} # <|eot_id|> # <|start_header_id|>assistant<|end_header_id|> # """ # # Format the request payload using the model's native structure. # request = { # "prompt": prompt, # # Optional inference parameters: # "max_gen_len": 1024, # "temperature": 0.6, # "top_p": 0.9, # } # # Encode and send the request. # response = bedrock.invoke_model(body=json.dumps(request), modelId=model_id) # # Decode the native response body. # model_response = json.loads(response["body"].read()) # # Extract and print the generated text. # response_text = model_response["generation"] # return response_text # except ClientError: # print("Couldn't invoke llama3 8B") # raise # mychatbot = gr.Chatbot( # avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,) # demo = gr.ChatInterface(fn=invoke_llama3_8b, # chatbot=mychatbot, # title="llama3-Chat", # retry_btn=None, # undo_btn=None # ) # demo.queue().launch(show_api=False)