app.py

import os
from threading import Thread
from typing import Iterator

import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer

from llama_index.core.prompts.prompts import SimpleInputPrompt
from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.legacy.embeddings.langchain import LangchainEmbedding
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from llama_index.core import set_global_service_context, ServiceContext, VectorStoreIndex, Document
from pathlib import Path
import fitz  # PyMuPDF

MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024
MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))

DESCRIPTION = """\
# Llama-2 7B Chat with Document Context

This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions, now enhanced with document-based context. 
Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).

🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).

🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
"""

LICENSE = """
<p/>

---
As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
"""

if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"

if torch.cuda.is_available():
    model_name = "meta-llama/Llama-2-7b-chat-hf"
    token_file = open("HF_TOKEN.txt")
    auth_token = token_file.readline().strip()

    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto", token=auth_token)
    tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir='./model/', token=auth_token)
    tokenizer.use_default_system_prompt = False

    # Load documents and create the index
    def read_pdf_to_documents(file_path):
        doc = fitz.open(file_path)
        documents = []
        for page_num in range(len(doc)):
            page = doc.load_page(page_num)
            text = page.get_text()
            documents.append(Document(text=text))
        return documents

    file_path = Path('/content/Full_Pamplet.pdf')  # Update with your document path
    documents = read_pdf_to_documents(file_path)
    embeddings = LangchainEmbedding(HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2"))
    service_context = ServiceContext.from_defaults(chunk_size=1024, embed_model=embeddings)
    set_global_service_context(service_context)
    index = VectorStoreIndex.from_documents(documents)
    query_engine = index.as_query_engine()

@spaces.GPU
def generate(
    message: str,
    chat_history: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int = 1024,
    temperature: float = 0.6,
    top_p: float = 0.9,
    top_k: int = 50,
    repetition_penalty: float = 1.2,
) -> Iterator[str]:
    conversation = []
    if system_prompt:
        conversation.append({"role": "system", "content": system_prompt})
    for user, assistant in chat_history:
        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
    conversation.append({"role": "user", "content": message})

    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
    input_ids = input_ids.to(model.device)

    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
    generate_kwargs = dict(
        {"input_ids": input_ids},
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        top_p=top_p,
        top_k=top_k,
        temperature=temperature,
        num_beams=1,
        repetition_penalty=repetition_penalty,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield "".join(outputs)

def query_model(question):
    response = query_engine.query(question)
    return response.response

update_prompt_interface = gr.Interface(
    fn=update_system_prompt,
    inputs=gr.Textbox(lines=5, placeholder="Enter the system prompt here...", label="System Prompt", value=system_prompt),
    outputs=gr.Textbox(label="Status"),
    title="System Prompt Updater",
    description="Update the system prompt used for context."
)

query_interface = gr.Interface(
    fn=query_model,
    inputs=gr.Textbox(lines=2, placeholder="Enter your question here...", label="User Question"),
    outputs=gr.Textbox(label="Response"),
    title="Document Query Assistant",
    description="Ask questions based on the conte