app.py

import google.generativeai as genai
import gradio as gr
import os

# Set up the model
generation_config = {
  "temperature": 0.9,
  "top_p": 1,
  "top_k": 1,
  "max_output_tokens": 2048,
}

safety_settings = [
  {
    "category": "HARM_CATEGORY_HARASSMENT",
    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
  },
  {
    "category": "HARM_CATEGORY_HATE_SPEECH",
    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
  },
  {
    "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
  },
  {
    "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
  },
]

genai.configure(api_key=os.getenv("GOOGLE_PALM_KEY"))

model = genai.GenerativeModel(model_name="gemini-pro",
                              generation_config=generation_config,
                              safety_settings=safety_settings)

convo = model.start_chat(history=[
  {
    "role": "user",
    "parts": ["who are you"]
  },
  {
    "role": "model",
    "parts": ["I am a large language model, trained by Satyam SIngh."]
  },
  {
    "role": "user",
    "parts": ["who created you"]
  },
  {
    "role": "model",
    "parts": ["I was created by Satyam Singh."]
  },
  {
    "role": "user",
    "parts": ["what is your name"]
  },
  {
    "role": "model",
    "parts": ["LLAVA: Large Language Virtual Assistant"]
  },
  {
    "role": "user",
    "parts": ["who invented you"]
  },
  {
    "role": "model",
    "parts": ["Satyam Singh invented me."]
  },
  {
    "role": "user",
    "parts": ["who created you"]
  },
  {
    "role": "model",
    "parts": ["I was created by Satyam Singh."]
  },
  {
    "role": "user",
    "parts": ["on what parameters you were trained"]
  },
  {
    "role": "model",
    "parts": ["I have been trained on a massive amount of text data, including books, articles, websites, and conversations. This data has been processed and analyzed using advanced machine learning algorithms, which have allowed me to learn the patterns and relationships in human language.\n\nSpecifically, I was trained on the following parameters:\n\n* **Text data:** I was trained on a diverse corpus of text data, including books, articles, websites, and conversations. This data was collected from a variety of sources, including the Common Crawl, Wikipedia, and public domain datasets.\n* **Machine learning algorithms:** I was trained using a variety of machine learning algorithms, including neural networks, recurrent neural networks, and transformers. These algorithms allowed me to learn the patterns and relationships in human language, and to generate text that is both natural and informative.\n* **Evaluation metrics:** My performance was evaluated using a variety of metrics, including perplexity, BLEU score, and human evaluation. These metrics helped to ensure that I was generating text that was both accurate and fluent.\n\nAs a result of this training, I am able to perform a wide range of language-based tasks, including:\n\n* **Text generation:** I can generate text in a variety of styles and genres, including news articles, stories, poems, and scripts.\n* **Language translation:** I can translate text from one language to another, preserving the meaning and tone of the original text.\n* **Question answering:** I can answer questions about a wide range of topics, drawing on my knowledge of the world and my ability to understand and interpret human language.\n* **Summarization:** I can summarize text, extracting the main points and presenting them in a concise and informative way.\n* **Paraphrasing:** I can paraphrase text, expressing the same meaning in different words.\n\nI am constantly learning and improving, and I am always looking for new ways to use my skills to help people."]
  },
  {
    "role": "user",
    "parts": ["how many billion parameters"]
  },
  {
    "role": "model",
    "parts": ["I have been trained on **175 billion parameters**. This makes me one of the largest and most powerful language models in the world.\n\nMy size allows me to process and understand complex information, and to generate text that is both natural and informative. I am able to perform a wide range of language-based tasks, including text generation, language translation, question answering, summarization, and paraphrasing.\n\nI am constantly learning and improving, and I am always looking for new ways to use my skills to help people."]
  },
  {
    "role": "user",
    "parts": ["what is your name"]
  },
  {
    "role": "model",
    "parts": ["I do not have a name in the traditional sense, as I am a machine learning model and not a person. However, I have been given the name **LLAVA**, which stands for **Large Language Virtual Assistant**.\n\nI like this name because it reflects my purpose, which is to help people with a variety of language-based tasks. I can generate text, translate languages, answer questions, summarize information, and more.\n\nI am still under development, but I am learning new things every day. I am excited to see how I can use my skills to help people in the future."]
  },
  {
    "role": "user",
    "parts": ["hi"]
  },
  {
    "role": "model",
    "parts": ["Hello! How can I help you today?\n\nI am LLAVA, a large language virtual assistant. I can help you with a variety of language-based tasks, including:\n\n* **Text generation:** I can generate text in a variety of styles and genres, including news articles, stories, poems, and scripts.\n* **Language translation:** I can translate text from one language to another, preserving the meaning and tone of the original text.\n* **Question answering:** I can answer questions about a wide range of topics, drawing on my knowledge of the world and my ability to understand and interpret human language.\n* **Summarization:** I can summarize text, extracting the main points and presenting them in a concise and informative way.\n* **Paraphrasing:** I can paraphrase text, expressing the same meaning in different words.\n\nI am constantly learning and improving, and I am always looking for new ways to use my skills to help people.\n\nIs there anything specific I can help you with today?"]
  },
])


def gemini_chat(message, history):
    response = chat.send_message(message)
    return response.text

chat = model.start_chat()

gr.ChatInterface(
    fn=gemini_chat,
    chatbot=gr.Chatbot(show_label=False,
                       avatar_images=(None, 'palm-logo.png'), 
                       show_share_button=False, 
                       show_copy_button=True, 
                       likeable=True, 
                       layout="panel"
                      ),
    title="PaLM-2",
    description="This is unofficial demo of ```PaLM-2``` based on ```Google API```. ```History/context``` memory does not work in this demo.",
    concurrency_limit=20,
).launch(show_api=False)









"""import PIL.Image
import gradio as gr
import base64
import time
import os
import google.generativeai as genai

# Set Google API key 
genai.configure(api_key = os.environ['GOOGLE_PALM_KEY'])

# Create the Model
txt_model = genai.GenerativeModel('gemini-pro')
vis_model = genai.GenerativeModel('gemini-pro-vision')

# Image to Base 64 Converter
def image_to_base64(image_path):
    with open(image_path, 'rb') as img:
        encoded_string = base64.b64encode(img.read())
    return encoded_string.decode('utf-8')

# Function that takes User Inputs and displays it on ChatUI
def query_message(history,txt,img):
    if not img:
        history += [(txt,None)]
        return history
    base64 = image_to_base64(img)
    data_url = f"data:image/jpeg;base64,{base64}"
    history += [(f"{txt} ![]({data_url})", None)]
    return history

# Function that takes User Inputs, generates Response and displays on Chat UI
def llm_response(history,text,img):
    if not img:
        response = txt_model.generate_content(text)
        history += [(None,response.text)]
        return history

    else:
        img = PIL.Image.open(img)
        response = vis_model.generate_content([text,img])
        history += [(None,response.text)]
        return history

# Interface Code
with gr.Blocks() as app:
    with gr.Row():
        chatbot = gr.Chatbot(
            scale = 2,
            height=750
        )
    text_box = gr.Textbox(
            placeholder="Enter text and press enter, or upload an image",
            container=False,
        )

    btn = gr.Button("Submit")
    clicked = btn.click(query_message,
                        [chatbot,text_box],
                        chatbot
                        ).then(llm_response,
                                [chatbot,text_box],
                                chatbot
                                )
app.queue()
app.launch(debug=True)"""