import marimo

__generated_with = "0.18.0"
app = marimo.App(
    width="medium",
    layout_file="layouts/Architecture_Overview.slides.json",
)


@app.cell
def _():
    import marimo as mo
    return (mo,)


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    # Interview Analysis Pipeline Architecture

    **Project Goal:** Synthesize insights from 26 stakeholder interviews into a unified report.

    **Input:** 26 Interview Transcripts (`.srt`)
    **Output:** Comprehensive Qualitative Analysis Report
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## High-Level Workflow

    The analysis follows a structured **3-Stage Pipeline** to ensure consistency across all interviews while leveraging the reasoning capabilities of Large Language Models (LLMs).
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## Stage 1: Discovery (Theme Definition)

    **Goal:** Establish the "Rules of the Game" to ensure consistent analysis.

    1.  **Input:** A representative sample of 4-5 interviews.
    2.  **Process:**
        *   Exploratory analysis to identify recurring topics.
        *   Grouping topics into **Themes**.
        *   Defining the **"Other"** category for emerging insights that don't fit established themes.
    3.  **Output:** `master_codebook.json`
        *   Contains Theme Names, Definitions, and Color Codes.
        *   Serves as the strict instruction set for the AI in Stage 2.
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.mermaid("""
    graph TD
        A[Raw Transcripts] -->|Sample 4-5| B(Stage 1: Discovery)
        B -->|Generate| C[Master Codebook]
        C -->|Input| D(Stage 2: Theme Coding)
        A -->|All 26 Files| D
        D -->|Extract| E[Structured Dataset]
        E -->|Aggregate| F(Stage 3: Synthesis)
        F -->|Generate| G[Final Report]

    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## Stage 2: Structured Theme Coding (Extraction)

    **Goal:** Convert unstructured text into a structured dataset.

    This will be a dedicated notebook, and be run per transcript.

    1.  **Input:** Transcript + `master_codebook.json`.
    2.  **Process:**
        *   The LLM analyzes each transcript segment-by-segment.
        *   It extracts specific quotes that match a Theme Definition.
        *   **Multi-Theme Handling:** If a quote applies to multiple themes, it is tagged with *all* relevant themes. In the dataset, this creates multiple entries (one per theme) so the quote informs the synthesis of each relevant topic.
        *   **Granular Sentiment Analysis:** For each quote, the model identifies:
            *   **Subject:** The specific topic/object being discussed (e.g., "Login Flow", "Brand Tone").
            *   **Sentiment:** Positive / Neutral / Negative.
    3.  **Output:** `<transcript_name>_coded_segments.csv`
        *   Columns: `Source_File`, `Speaker`, `Theme`, `Quote`, `Subject`, `Sentiment`, `Context`.
        *   Each transcript produces its own CSV-file, which can be reviewed and adjusted before moving to the next stage
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## Stage 3: Synthesis & Reporting

    **Goal:** Derive conclusions from the aggregated data.

    1.  **Input:** `coded_segments.csv` (The consolidated dataset).
    2.  **Process:**
        *   **Theme Synthesis:** All quotes for "Theme A" are analyzed together to find patterns, contradictions, and consensus.
        *   **"Other" Review:** The "Other" category is manually or computationally reviewed to identify missed signals.
        *   **Global Synthesis:** Cross-theme analysis to build the final narrative.
    3.  **Output:** Final Report
        *   Executive Summary
        *   Theme-by-Theme Deep Dives (with supporting quotes)
        *   Strategic Recommendations
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## Technical Infrastructure

    | Component | Specification | Role |
    |-----------|---------------|------|
    | **Model** | `llama3.3:70b` | Primary reasoning engine (128k context) |
    | **Compute** | NVIDIA H100 (80GB) | High-performance inference |
    | **Orchestration** | Python + Marimo | Pipeline management and UI |
    | **Storage** | Local JSON/CSV | Data persistence |
    """)
    return


if __name__ == "__main__":
    app.run()