app.py

import google.generativeai as genai
import gradio as gr
import os
from huggingface_hub import InferenceClient

client = InferenceClient("Satyam-Singh/LLaVa-Large-Language-Virtual-Assistant")

TITLE = """<h1 align="center">LLaVa Large Language Virtual Assistant</h1>"""

# Set up the model
generation_config = {
  "temperature": 0.9,
  "top_p": 1,
  "top_k": 1,
  "max_output_tokens": 4096,
}

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": ["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."]
  },
])

temperature_component = gr.Slider(
    minimum=0,
    maximum=1.0,
    value=0.4,
    step=0.05,
    label="Temperature",
    info=(
        "Temperature controls the degree of randomness in token selection. Lower "
        "temperatures are good for prompts that expect a true or correct response, "
        "while higher temperatures can lead to more diverse or unexpected results. "
    ))
max_output_tokens_component = gr.Slider(
    minimum=1,
    maximum=2048,
    value=1024,
    step=1,
    label="Token limit",
    info=(
        "Token limit determines the maximum amount of text output from one prompt. A "
        "token is approximately four characters. The default value is 2048."
    ))
stop_sequences_component = gr.Textbox(
    label="Add stop sequence",
    value="",
    type="text",
    placeholder="STOP, END",
    info=(
        "A stop sequence is a series of characters (including spaces) that stops "
        "response generation if the model encounters it. The sequence is not included "
        "as part of the response. You can add up to five stop sequences."
    ))
top_k_component = gr.Slider(
    minimum=1,
    maximum=40,
    value=32,
    step=1,
    label="Top-K",
    info=(
        "Top-k changes how the model selects tokens for output. A top-k of 1 means the "
        "selected token is the most probable among all tokens in the model’s "
        "vocabulary (also called greedy decoding), while a top-k of 3 means that the "
        "next token is selected from among the 3 most probable tokens (using "
        "temperature)."
    ))
top_p_component = gr.Slider(
    minimum=0,
    maximum=1,
    value=1,
    step=0.01,
    label="Top-P",
    info=(
        "Top-p changes how the model selects tokens for output. Tokens are selected "
        "from most probable to least until the sum of their probabilities equals the "
        "top-p value. For example, if tokens A, B, and C have a probability of .3, .2, "
        "and .1 and the top-p value is .5, then the model will select either A or B as "
        "the next token (using temperature). "
    ))

additional_inputs = [
    temperature_component,
    max_output_tokens_component,
    stop_sequences_component,
    top_k_component,
    top_p_component,
]

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



examples=[["I'm planning a vacation to India. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
          ["Can you write a short story about a time-traveling detective who solves historical mysteries?", None, None, None, None, None,],
          ["I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?", None, None, None, None, None,],
          ["I have paneer, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
          ["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
          ["What are some unique features of Python that make it stand out compared to other systems programming languages like C++,Java?", None, None, None, None, None,],
         ]

with gr.Blocks(css=css) as chat:
    gr.HTML(TITLE)
    gr.ChatInterface(
        fn=gemini_chat,
        chatbot=gr.Chatbot(show_label=False,
                           avatar_images=(None, 'llava-logo.svg'), 
                           show_share_button=False, 
                           show_copy_button=True, 
                           likeable=True, 
                           layout="panel",
                           bubble_full_width=True
                          ),
        title="LLAVA: Large Language Virtual Assistant",
        description="Official Demo Of ```LLAVA``` based on ```Large Language Virtual Assistant ```.",
        additional_inputs=additional_inputs,
        examples=examples,
        concurrency_limit=20,
    )
chat.launch(show_api=True)