from diffusers import StableDiffusionPipeline
import torch
from langchain.chains import LLMChain
from langchain.llms import HuggingFaceHub
from langchain.prompts import PromptTemplate
import streamlit as st
import json

# Load existing ideas from a file
def load_ideas():
    try:
        with open("ideas.json", "r") as file:
            ideas = json.load(file)
    except FileNotFoundError:
        ideas = []
    return ideas

# Save ideas to a file
def save_ideas(ideas):
    with open("ideas.json", "w") as file:
        json.dump(ideas, file)

# Create the pipeline and langchain model 
def load_models():
  with torch.no_grad():
    model_id = "CompVis/stable-diffusion-v1-4"
    device = "cuda"
    pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
    pipe = pipe.to(device)
    hub_llm = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta")
    prompt = PromptTemplate(
        input_variables=['keyword'],
        template="""
        Write a comprehensive article about {keyword} covering the following aspects:
        Introduction, History and Background, Key Concepts and Terminology, Use Cases and Applications, Benefits and Drawbacks, Future Outlook, Conclusion
        Ensure that the article is well-structured, informative, and at least 1500 words long. Use SEO best practices for content optimization.
        """
    )
    hub_chain = LLMChain(prompt=prompt, llm=hub_llm, verbose=True)
    return hub_chain,pipe

# Wait for the models to be created
with st.spinner("Creating generation pipelines. Please Wait:)..."):
  hub_chain,pipe = load_models()


# Function to generate content
@torch.no_grad()
def generate_content(topic):
    content = hub_chain.run(topic)

    subheadings = [
        "Introduction",
        "History and Background",
        "Key Concepts and Terminology",
        "Use Cases and Applications",
        "Benefits and Drawbacks",
        "Future Outlook",
        "Conclusion",
    ]

    for subheading in subheadings:
        if (subheading + ":") in content:
            content = content.replace(subheading + ":", "## " + subheading + "\n")
        elif subheading in content:
            content = content.replace(subheading, "## " + subheading + "\n")

    return content



# generate image
@torch.no_grad()
def generate_image(topic):
    prompt = f"blog banner about {topic}"
    image = pipe(prompt).images[0]
    return image


# Streamlit app
st.title("Blog Generator")

# Input and button
topic = st.text_input("Enter Title for the blog")
button_clicked = st.button("Create blog!")
st.subheader(topic)
# Load existing ideas
existing_ideas = load_ideas()
st.sidebar.header("Previous Ideas:")

# Display existing ideas in the sidebar
keys = list(set([key for idea in existing_ideas for key in idea.keys()]))
if topic in keys:
    index = keys.index(topic)
    selected_idea = st.sidebar.selectbox("Select Idea", keys, key=f"selectbox{topic}", index=index)
    # Display content and image for the selected idea
    selected_idea_from_list = next((idea for idea in existing_ideas if selected_idea in idea), None)
    st.markdown(selected_idea_from_list[selected_idea]["content"])
    st.image(selected_idea_from_list[selected_idea]["image_path"])
else:
    index = 0
# Handle button click
if button_clicked:
    # Generate content and update existing ideas
    content, image_path = generate_content(topic),generate_image(topic)
    existing_ideas.append({topic: {"content": content, "image_path": image_path}})
    save_ideas(existing_ideas)
    # Update keys and selected idea in the sidebar
    keys = list(set([key for idea in existing_ideas for key in idea.keys()]))
    selected_idea = st.sidebar.selectbox("Select Idea", keys, key=f"selectbox{topic}", index=keys.index(topic))
    st.markdown(content)
    st.image(image_path)