import streamlit as st

# Initialize the slide groups in session state on first run.
if "slide_groups" not in st.session_state:
    st.session_state.slide_groups = [
        {
            "group": "Slide 1: Introduction",
            "content": r"""
**Title:** AI Toolbox: 20 Papers in 5 Minutes  
**Goal:** Show how these topics (Torch, Ollama, Deepseek, SFT, knowledge distillation, crowdsourcing, etc.) tie together into an end-to-end AI pipeline.  
**Media:** Quick intro audio & a short video clip highlighting AI breakthroughs.
            """
        },
        {
            "group": "Slides 2–3: Torch (PyTorch Foundations)",
            "content": r"""
**Paper 1**  
*Reference:* Paszke, A. et al. “PyTorch: An Imperative Style, High-Performance Deep Learning Library.” arXiv:1912.01703 (2019)  
*Key Points:*  
- Dynamic computation graphs for rapid prototyping.  
- Strong GPU acceleration and broad community support.  
*Presentation Element:* Brief code snippet in Python + a Mermaid flowchart showing how forward/backprop flows in PyTorch.

**Paper 2**  
*Reference:* Paszke, A. et al. “Automatic Differentiation in PyTorch.” arXiv:1707.?? (Hypothetical reference)  
*Key Points:*  
- Core mechanism behind autograd.  
- How tensor operations are tracked and reversed for gradients.  
*Presentation Element:* Minimal slides highlighting computational graph merges with HPC concepts.
            """
        },
        {
            "group": "Slides 4–5: Ollama & LLaMA-Based Models",
            "content": r"""
**Paper 3**  
*Reference:* Touvron, H. et al. “LLaMA: Open and Efficient Foundation Language Models.” arXiv:2302.13971 (2023)  
*Key Points:*  
- Architecture, training efficiency, and open-source benefits.  
- Relevance to Ollama (lightweight local LLaMA inference).  
*Presentation Element:* Short video demo of an Ollama prompt or model reply.

**Paper 4**  
*Reference:* Zhang, M. et al. “Exploring LLaMA Derivatives for Local Inference.” arXiv:2303.???? (Hypothetical)  
*Key Points:*  
- Techniques for running large models on consumer-grade hardware.  
- Model quantization, CPU/GPU scheduling.  
*Presentation Element:* Mermaid sequence diagram comparing server-based vs. local inference pipelines.
            """
        },
        {
            "group": "Slides 6–7: Deepseek MoE + Chain of Thought (CoT)",
            "content": r"""
**Paper 5**  
*Reference:* Fedus, W., Zoph, B., Shazeer, N. “Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity.” arXiv:2101.03961 (2021)  
*Key Points:*  
- Mixture-of-Experts (MoE) approach to scale large models.  
- Efficiency gains via sparse routing.  
*Presentation Element:* Visual MoE block diagram with color-coded experts.

**Paper 6**  
*Reference:* Wei, J. et al. “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.” arXiv:2201.11903 (2022)  
*Key Points:*  
- Step-by-step reasoning prompts improve logical consistency.  
- Potential synergy with MoE for specialized “reasoning experts.”  
*Presentation Element:* Mermaid mind map illustrating short CoT vs. detailed CoT.
            """
        },
        {
            "group": "Slides 8–9: Hugging Face SFT Trainer",
            "content": r"""
**Paper 7**  
*Reference:* Wolf, T. et al. “Transformers: State-of-the-Art Natural Language Processing.” arXiv:1910.03771 (2020)  
*Key Points:*  
- Core library behind Hugging Face’s ecosystem.  
- Transformer architecture fundamentals.  
*Presentation Element:* Show how SFTTrainer (hypothetical name) builds on Trainer for supervised finetuning.

**Paper 8**  
*Reference:* Houlsby, N. et al. “Parameter-Efficient Transfer Learning for NLP.” arXiv:1902.00751 (2019)  
*Key Points:*  
- Techniques like adapters, LoRA, or selective layer freezing.  
- Impact on training efficiency and model size.  
*Presentation Element:* A side-by-side bar chart showing reduction in GPU hours with parameter-efficient methods.
            """
        },
        {
            "group": "Slides 10–11: Knowledge Distillation & Mermaid Graphs",
            "content": r"""
**Paper 9**  
*Reference:* Hinton, G., Vinyals, O., Dean, J. “Distilling the Knowledge in a Neural Network.” arXiv:1503.02531 (2015)  
*Key Points:*  
- Transfer knowledge from large “teacher” models to small “student” models.  
- Temperature scaling and teacher-student training.  
*Presentation Element:* Mermaid flowchart detailing teacher–student relationships.

**Paper 10**  
*Reference:* Chen, X. et al. “Graph-Based Knowledge Distillation for Neural Networks.” arXiv:2105.???? (Hypothetical)  
*Key Points:*  
- Represent model layers and hidden states as nodes & edges.  
- Synergy with SFT and domain adaptation.  
*Presentation Element:* Mermaid graph diagram linking teacher network nodes to student network nodes.
            """
        },
        {
            "group": "Slides 12–13: Crowdsourcing & Agents for Evaluation",
            "content": r"""
**Paper 11**  
*Reference:* Callison-Burch, C. “Fast, Cheap, and Creative: Evaluating Translation Quality Using Amazon’s Mechanical Turk.” arXiv:0907.5225 (2009)  
*Key Points:*  
- Crowdsourcing pipeline for large-scale text evaluation.  
- Reliability strategies: gold standards, inter-annotator agreement.  
*Presentation Element:* Timeline comparing tasks for crowdworkers vs. automated agents.

**Paper 12**  
*Reference:* Nie, Y. et al. “Adversarial NLI: A New Benchmark for Natural Language Understanding.” arXiv:1910.14599 (2019)  
*Key Points:*  
- Human-and-model-in-the-loop adversarial examples.  
- Incremental data curation to improve robustness.  
*Presentation Element:* Short audio explanation of adversarial example refinement.
            """
        },
        {
            "group": "Slides 14–15: Python + Gradio/Streamlit",
            "content": r"""
**Paper 13**  
*Reference:* Abid, A. et al. “Gradio: A User Interface for Interactive Machine Learning.” arXiv:2101.???? (Hypothetical)  
*Key Points:*  
- Build quick demos and capture user feedback.  
- Invaluable for crowdsourced data collection and real-time model updates.  
*Presentation Element:* 10-second video demo of a Gradio UI (e.g. a chatbot or image classifier).

**Paper 14**  
*Reference:* [Streamlit Team], “Streamlit: Democratizing Data App Creation.” arXiv:2004.???? (Hypothetical)  
*Key Points:*  
- Turning Python scripts into web apps effortlessly.  
- Useful for HPC dashboards and debugging distributed training.  
*Presentation Element:* Animated slides showing how to add interactive widgets with minimal code.
            """
        },
        {
            "group": "Slides 16–17: HPC for Python-Based AI",
            "content": r"""
**Paper 15**  
*Reference:* Shoeybi, M. et al. “Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.” arXiv:1909.08053 (2019)  
*Key Points:*  
- Scaling large models via model parallelism on HPC clusters.  
- Integration with NVIDIA libraries (e.g. NCCL).  
*Presentation Element:* Mermaid architecture diagram illustrating parallel pipelines.

**Paper 16**  
*Reference:* Huang, Y. et al. “GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism.” arXiv:1811.06965 (2019)  
*Key Points:*  
- Overlap of communication and computation for HPC efficiency.  
- Synergy with MoE or large LLaMA models.  
*Presentation Element:* Throughput vs. latency charts and an HPC cluster image.
            """
        },
        {
            "group": "Slides 18–19: Semantic & Episodic Memory + RLHF",
            "content": r"""
**Paper 17**  
*Reference:* Ouyang, X. et al. “Integrating Episodic and Semantic Memory for Task-Oriented Dialogue.” arXiv:2105.???? (Hypothetical)  
*Key Points:*  
- Differentiate short-term episodic from long-term semantic context.  
- Improves consistency and factual correctness in dialogue.  
*Presentation Element:* Mermaid diagram contrasting ephemeral vs. persistent memory flows.

**Paper 18**  
*Reference:* Ouyang, X. et al. “Training Language Models to Follow Instructions with Human Feedback.” arXiv:2203.02155 (2022)  
*Key Points:*  
- Reinforcement Learning from Human Feedback (RLHF).  
- Align model outputs with user preferences and ethical guidelines.  
*Presentation Element:* RLHF pseudo-code snippet and a timeline of preference collection.
            """
        },
        {
            "group": "Slides 20–21: Transfer Learning & “Learning for Good”",
            "content": r"""
**Paper 19**  
*Reference:* Ruder, S. “A Survey on Transfer Learning for NLP.” arXiv:1910.?? (2019)  
*Key Points:*  
- Overview of transfer learning strategies (fine-tuning, adapters, multitask learning).  
- Quickly customize large pre-trained models.  
*Presentation Element:* Graph of performance gains vs. training time.

**Paper 20**  
*Reference:* Zhang, Y., Yang, Q. “A Survey on Multi-Task Learning.” arXiv:1707.08114 (2017)  
*Key Points:*  
- Train one model on multiple tasks to share representations.  
- Synergy with “Learning for Good” scenarios (e.g., medical, climate).  
*Presentation Element:* Mermaid multi-task diagram showing convergence in shared layers.
            """
        },
        {
            "group": "Slide 22: Closing & Next Steps",
            "content": r"""
**Key Takeaways:**  
- **Integration:** Every paper contributes to an end-to-end AI pipeline—from HPC scaling to crowdsourced evaluation.  
- **Modular Approach:** Combining PyTorch, Hugging Face SFT, and knowledge distillation leads to efficient model development.  
- **Interactive Demonstrations:** Leveraging Gradio/Streamlit and RLHF creates user-friendly, human-centric AI experiences.  
- **Future Work:** Explore deeper synergies among MoE, HPC, and memory-based architectures.

**Media:**  
- Concluding audio clip.  
- (Optionally) a final Mermaid diagram linking all stages: data ingestion → HPC training → crowdsourcing → RLHF → model deployment.
            """
        }
    ]
    st.session_state.current_index = 0  # Initialize the current slide index


# Set up the page configuration
st.set_page_config(page_title="AI Presentation Outline", layout="wide")
st.title("AI Toolbox Presentation Outline")

# Sidebar: Navigation and slide group addition
st.sidebar.header("Navigation")

# --- Option to add a new slide group ---
with st.sidebar.expander("Add New Slide Group"):
    with st.form("new_slide_form"):
        new_group = st.text_input("Slide Group Title")
        new_content = st.text_area("Slide Group Content (Markdown)", height=200)
        submitted = st.form_submit_button("Add Slide Group")
        if submitted:
            if new_group.strip() and new_content.strip():
                st.session_state.slide_groups.append({
                    "group": new_group.strip(),
                    "content": new_content.strip()
                })
                st.success(f"Added slide group: {new_group}")
            else:
                st.error("Please provide both a title and content.")

# --- Slide group selector ---
slide_titles = [slide["group"] for slide in st.session_state.slide_groups]
# Use a selectbox whose index is synced with session_state.current_index
selected_index = st.sidebar.selectbox(
    "Select Slide Group",
    range(len(slide_titles)),
    index=st.session_state.current_index,
    format_func=lambda i: slide_titles[i]
)
st.session_state.current_index = selected_index

# --- Navigation buttons ---
cols = st.sidebar.columns(2)
if cols[0].button("⟨ Previous"):
    st.session_state.current_index = max(st.session_state.current_index - 1, 0)
if cols[1].button("Next ⟩"):
    st.session_state.current_index = min(st.session_state.current_index + 1, len(slide_titles) - 1)

# Main: Display the selected slide group's details
current_slide = st.session_state.slide_groups[st.session_state.current_index]
st.header(current_slide["group"])
st.markdown(current_slide["content"], unsafe_allow_html=True)