"""
Generates "Vektoren in der Datenbank.pptx" — a LibreOffice-compatible presentation.
Run from the project root:  python3 make_presentation.py
"""

from pptx import Presentation
from pptx.util import Inches, Pt, Emu
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN
from pptx.oxml.ns import qn
from pptx.oxml import parse_xml
from lxml import etree
import os
import numpy as np
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches

_A_NS = "http://schemas.openxmlformats.org/drawingml/2006/main"

def OxmlElement(tag):
    local = tag.split(":")[1]
    return etree.fromstring(f'<a:{local} xmlns:a="{_A_NS}"/>')


# ── Diagram generation (matplotlib → PNG → embedded in slide) ────────────────

DIAG_BG   = "#1e1e2e"
DIAG_GRID = "#313244"
DIAG_AXIS = "#6c7086"

def _fig(w, h):
    fig, ax = plt.subplots(figsize=(w, h))
    fig.patch.set_facecolor(DIAG_BG)
    ax.set_facecolor(DIAG_BG)
    return fig, ax

def _save(fig, name):
    path = os.path.join("diagrams", name)
    fig.savefig(path, dpi=150, bbox_inches="tight", facecolor=DIAG_BG)
    plt.close(fig)
    return path


def diagram_s3_vectors():
    """Slide 3: 2-D vector space with Hund / Katze / Auto."""
    fig, ax = _fig(5, 5)
    ax.set_xlim(-1.3, 1.3)
    ax.set_ylim(-1.3, 1.3)
    ax.set_aspect("equal")
    ax.grid(True, color=DIAG_GRID, linewidth=0.5, alpha=0.6)
    ax.axhline(0, color=DIAG_AXIS, linewidth=1)
    ax.axvline(0, color=DIAG_AXIS, linewidth=1)
    ax.set_xticks([]); ax.set_yticks([])
    for sp in ax.spines.values(): sp.set_visible(False)
    ax.text(1.27,  0.05, "x₁", color=DIAG_AXIS, fontsize=12)
    ax.text( 0.05, 1.27, "x₂", color=DIAG_AXIS, fontsize=12)

    vecs = [
        ((0.91,  0.12), "#89b4fa", "Hund"),
        ((0.87,  0.18), "#74c7ec", "Katze"),
        ((-0.30,  0.90), "#f38ba8", "Auto"),
    ]
    for (vx, vy), color, label in vecs:
        ax.annotate("", xy=(vx, vy), xytext=(0, 0),
                    arrowprops=dict(arrowstyle="->", color=color, lw=2.5))
        ox, oy = 0.10, 0.07
        ax.text(vx + ox * np.sign(vx or 1),
                vy + oy * np.sign(vy or 1),
                label, color=color, fontsize=13, fontweight="bold")

    # Small arc: Hund ↔ Katze
    a1 = np.degrees(np.arctan2(0.12, 0.91))
    a2 = np.degrees(np.arctan2(0.18, 0.87))
    ax.add_patch(mpatches.Arc((0, 0), 0.32, 0.32, angle=0,
                               theta1=min(a1, a2), theta2=max(a1, a2),
                               color="#a6e3a1", lw=2))
    ax.text(0.22, -0.10, "klein", color="#a6e3a1", fontsize=10, ha="center")

    # Large arc: Hund ↔ Auto
    a3 = np.degrees(np.arctan2(0.90, -0.30))
    ax.add_patch(mpatches.Arc((0, 0), 0.52, 0.52, angle=0,
                               theta1=a1, theta2=a3,
                               color="#fab387", lw=2))
    ax.text(-0.35, 0.28, "groß", color="#fab387", fontsize=10)

    plt.tight_layout(pad=0.3)
    return _save(fig, "s3_vectors.png")


def diagram_s4_flow():
    """Slide 4: Semantic search pipeline as a flow diagram."""
    fig, ax = _fig(12, 1.9)        # flat figure — matches slide aspect ratio
    ax.set_xlim(0, 12); ax.set_ylim(0, 1.9)
    ax.axis("off")

    steps = [
        (1.2,  'Text-Anfrage\n"Bäume"',  "#89b4fa"),
        (3.6,  "CLIP-Modell",            "#cba6f7"),
        (6.0,  "Vektor  512 floats",     "#74c7ec"),
        (8.4,  "Datenbank k-NN",         "#f38ba8"),
        (10.8, "Ergebnisse\nnach Score", "#a6e3a1"),
    ]
    for x, label, color in steps:
        box = mpatches.FancyBboxPatch((x - 1.05, 0.22), 2.1, 1.4,
                                       boxstyle="round,pad=0.1",
                                       facecolor="#313244", edgecolor=color, linewidth=2)
        ax.add_patch(box)
        ax.text(x, 0.92, label, ha="center", va="center",
                color=color, fontsize=13, fontweight="bold", multialignment="center",
                fontfamily="sans-serif")

    for i in range(len(steps) - 1):
        x1 = steps[i][0]   + 1.05
        x2 = steps[i+1][0] - 1.05
        ax.annotate("", xy=(x2, 0.92), xytext=(x1, 0.92),
                    arrowprops=dict(arrowstyle="->", color=DIAG_AXIS, lw=2.5))

    plt.tight_layout(pad=0.15)
    return _save(fig, "s4_flow.png")


def diagram_s6_cosine():
    """Slide 6: Two vectors with the cosine angle between them."""
    fig, ax = _fig(5, 4.5)
    ax.set_xlim(-0.2, 1.35); ax.set_ylim(-0.15, 1.35)
    ax.set_aspect("equal")
    ax.axis("off")

    vA = np.array([1.1,  0.25])   # image vector
    vB = np.array([0.55, 1.0 ])   # text vector

    for v, color, label, lpos in [
        (vA, "#89b4fa", "Bild-Vektor",         (1.17,  0.08)),
        (vB, "#cba6f7", 'Text-Vektor\n"Bäume"', (0.56,  1.07)),
    ]:
        ax.annotate("", xy=v, xytext=(0, 0),
                    arrowprops=dict(arrowstyle="->", color=color, lw=3))
        ax.text(*lpos, label, color=color, fontsize=12,
                fontweight="bold", ha="center", multialignment="center")

    # Angle arc
    a1 = np.degrees(np.arctan2(vA[1], vA[0]))
    a2 = np.degrees(np.arctan2(vB[1], vB[0]))
    ax.add_patch(mpatches.Arc((0, 0), 0.45, 0.45, angle=0,
                               theta1=a1, theta2=a2,
                               color="#a6e3a1", lw=2.5))
    mid_angle = np.radians((a1 + a2) / 2)
    ax.text(0.28 * np.cos(mid_angle), 0.28 * np.sin(mid_angle),
            "θ", color="#a6e3a1", fontsize=16, fontweight="bold",
            ha="center", va="center")

    # Origin dot
    ax.plot(0, 0, "o", color=DIAG_AXIS, markersize=6)

    # Formula
    ax.text(0.58, -0.12,
            "Ähnlichkeit = 1 − cos(θ)",
            color="#cdd6f4", fontsize=11, ha="center",
            fontfamily="monospace")

    plt.tight_layout(pad=0.3)
    return _save(fig, "s6_cosine.png")


def diagram_architecture():
    """Architecture slide: 3 columns showing app server, database, and where CLIP runs."""
    CLIP_CLR = "#a6e3a1"
    # (x, db_name, color, port, clip_app, clip_db, db_tech, vec_embed_fn, foto_storage)
    COLS = [
        (2.3,  "PostgreSQL 18",              "#89b4fa", "Port 8000", True,  False, "pgvector 0.8.2\nHNSW (Disk)",  None,                "Fotos: Dateipfad (Filesystem)"),
        (6.65, "Oracle 26ai\nVECTORS_USER",  "#f38ba8", "Port 8001", True,  False, "HNSW (SGA)",                   None,                "Fotos: Dateipfad (Filesystem)"),
        (11.0, "Oracle 26ai\nVECTOR",        "#cba6f7", "Port 8002", False, True,  "HNSW (SGA)",                   "VECTOR_EMBEDDING()", "Fotos: BLOB (in Oracle)"),
    ]

    BOX_H  = 2.2   # all boxes same height
    DB_Y   = 0.15  # database box bottom
    GAP    = 0.60  # space between DB top and app server bottom
    APP_Y  = DB_Y + BOX_H + GAP   # = 2.95

    fig, ax = _fig(13.5, 6.5)
    ax.set_xlim(0, 13.5); ax.set_ylim(-0.8, 5.9)
    ax.axis("off")

    for x, db_name, color, port, clip_app, clip_db, db_tech, vec_fn, foto_storage in COLS:
        APP_TOP = APP_Y + BOX_H   # = 5.15
        DB_TOP  = DB_Y  + BOX_H   # = 2.35

        # ── Port label
        ax.text(x, APP_TOP + 0.28, port, ha="center", color=color,
                fontsize=13, fontweight="bold")

        # ── App server box
        ax.add_patch(mpatches.FancyBboxPatch(
            (x-1.7, APP_Y), 3.4, BOX_H,
            boxstyle="round,pad=0.1", facecolor="#28293d", edgecolor=color, lw=2))
        ax.text(x, APP_TOP - 0.22, "App-Server  (FastAPI)", ha="center",
                color=color, fontsize=11, fontweight="bold")

        if clip_app:
            ax.add_patch(mpatches.FancyBboxPatch(
                (x-1.2, APP_Y + 0.10), 2.4, 0.75,
                boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=CLIP_CLR, lw=2))
            ax.text(x, APP_Y + 0.475, "CLIP-Modell\n(sentence-transformers)",
                    ha="center", va="center", color=CLIP_CLR, fontsize=9.5, fontweight="bold",
                    multialignment="center")
            ax.add_patch(mpatches.FancyBboxPatch(
                (x-1.2, APP_Y + 0.95), 2.4, 0.42,
                boxstyle="round,pad=0.06", facecolor="#1e1e2e", edgecolor=DIAG_AXIS, lw=1,
                linestyle="dashed"))
            ax.text(x, APP_Y + 1.16, foto_storage,
                    ha="center", va="center", color=DIAG_AXIS, fontsize=9, style="italic")
        else:
            ax.add_patch(mpatches.FancyBboxPatch(
                (x-1.2, APP_Y + 0.10), 2.4, 0.75,
                boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=DIAG_AXIS, lw=1,
                linestyle="dashed"))
            ax.text(x, APP_Y + 0.475, "kein CLIP",
                    ha="center", va="center", color=DIAG_AXIS, fontsize=10, style="italic")

        # ── Arrow with comfortable gap
        ax.annotate("", xy=(x, DB_TOP + 0.05), xytext=(x, APP_Y - 0.05),
                    arrowprops=dict(arrowstyle="->", color=DIAG_AXIS, lw=2))
        arrow_lbl = "Vektor (512 floats)" if clip_app else "Text-String"
        ax.text(x + 0.2, (DB_TOP + APP_Y) / 2, arrow_lbl, ha="left", va="center",
                color=DIAG_AXIS, fontsize=9, style="italic")

        # ── Database box
        ax.add_patch(mpatches.FancyBboxPatch(
            (x-1.7, DB_Y), 3.4, BOX_H,
            boxstyle="round,pad=0.1", facecolor="#28293d", edgecolor=color, lw=2))

        if clip_db:
            ax.add_patch(mpatches.FancyBboxPatch(
                (x-1.2, DB_Y + 0.10), 2.4, 0.72,
                boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=CLIP_CLR, lw=2))
            ax.text(x, DB_Y + 0.46, "CLIP-Modell\n(ONNX, in Oracle)",
                    ha="center", va="center", color=CLIP_CLR, fontsize=9.5, fontweight="bold",
                    multialignment="center")
            ax.add_patch(mpatches.FancyBboxPatch(
                (x-1.2, DB_Y + 0.92), 2.4, 0.40,
                boxstyle="round,pad=0.06", facecolor="#1e1e2e", edgecolor=DIAG_AXIS, lw=1,
                linestyle="dashed"))
            ax.text(x, DB_Y + 1.12, foto_storage,
                    ha="center", va="center", color=DIAG_AXIS, fontsize=9, style="italic")
            ax.text(x, DB_Y + 1.50, vec_fn,
                    ha="center", color="#fab387", fontsize=10, fontweight="bold",
                    fontfamily="monospace")
            ax.text(x, DB_Y + 1.72, "Oracle 26ai", ha="center", color=color,
                    fontsize=11, fontweight="bold")
            ax.text(x, DB_Y + 1.92, "Schema: VECTOR", ha="center", color=color,
                    fontsize=9)
            ax.text(x, DB_Y + 2.10, db_tech, ha="center", color=DIAG_AXIS,
                    fontsize=9)
        else:
            # Split db_name → ["PostgreSQL 18"] or ["Oracle 26ai", "VECTORS_USER"]
            # Split db_tech → ["pgvector 0.8.2", "HNSW (Disk)"] or ["HNSW (SGA)"]
            name_parts = db_name.split("\n")
            tech_parts = db_tech.split("\n")
            hnsw       = tech_parts[-1]          # always last
            tech_extra = tech_parts[:-1]         # e.g. ["pgvector 0.8.2"]

            # HNSW — same height across all three DB boxes
            ax.text(x, DB_Y + 2.10, hnsw, ha="center", color=DIAG_AXIS, fontsize=9)

            # Middle line: schema name or version info (matches "Schema: VECTOR" in col 3)
            if len(name_parts) > 1:
                mid_label = "Schema: " + name_parts[1]
            elif tech_extra:
                mid_label = tech_extra[0]
            else:
                mid_label = ""
            if mid_label:
                ax.text(x, DB_Y + 1.92, mid_label, ha="center", color=color, fontsize=9)

            # Main DB name (matches "Oracle 26ai" in col 3)
            ax.text(x, DB_Y + 1.72, name_parts[0], ha="center", color=color,
                    fontsize=11, fontweight="bold")

    # ── Vertical separators
    for xsep in [4.5, 8.85]:
        ax.plot([xsep, xsep], [0.05, 5.55], color=DIAG_GRID, lw=1, linestyle="--")

    # ── Caption — separated from boxes, applies to all three columns
    ax.plot([0.3, 13.2], [-0.18, -0.18], color=DIAG_GRID, lw=1)
    ax.text(6.75, -0.5, "116 Street Fotos  ·  CLIP ViT-B/32  ·  512-dimensionale Vektoren",
            ha="center", va="center", color="#cdd6f4", fontsize=13, style="italic")

    plt.tight_layout(pad=0.2)
    return _save(fig, "architecture.png")

# Generate diagrams up front
os.makedirs("diagrams", exist_ok=True)
DIAG_S3   = diagram_s3_vectors()
DIAG_S4   = diagram_s4_flow()
DIAG_S6   = diagram_s6_cosine()
DIAG_ARCH = diagram_architecture()

import copy

# ── Colour palette (dark theme) ──────────────────────────────────────────────
BG          = RGBColor(0x1e, 0x1e, 0x2e)   # slide background
TITLE_CLR   = RGBColor(0xcb, 0xd3, 0xff)   # slide titles
BODY_CLR    = RGBColor(0xcd, 0xd6, 0xf4)   # body text
DIM_CLR     = RGBColor(0x6c, 0x70, 0x86)   # dimmed / captions
ACCENT_PG   = RGBColor(0x89, 0xb4, 0xfa)   # pgvector blue
ACCENT_ORA  = RGBColor(0xf3, 0x8b, 0xa8)   # Oracle red/pink
ACCENT_IDB  = RGBColor(0xcb, 0xa6, 0xf7)   # in-DB purple
ACCENT_GRN  = RGBColor(0xa6, 0xe3, 0xa1)   # green for highlights
CODE_BG     = RGBColor(0x31, 0x32, 0x44)   # code block background
CODE_CLR    = RGBColor(0xa6, 0xe3, 0xa1)   # code text

W = Inches(13.33)   # widescreen 16:9
H = Inches(7.5)

FONT = "Roboto"

prs = Presentation()
prs.slide_width  = W
prs.slide_height = H

blank_layout = prs.slide_layouts[6]   # completely blank

LOGO_PATH   = "/home/dierk/Bilder/Logo/Logo DLC Final.png"
CONFERENCE  = "Quest Data Minds Konferenz"
EVENT_DATE  = "28. Mai 2026"
EVENT_CITY  = "Köln"

_slide_num = [0]   # mutable counter so nested calls can increment it


def add_slide(logo=True, footer=True):
    slide = prs.slides.add_slide(blank_layout)
    bg = slide.background
    fill = bg.fill
    fill.solid()
    fill.fore_color.rgb = BG
    if logo:
        slide.shapes.add_picture(LOGO_PATH,
            Inches(11.6), Inches(7.0), Inches(1.6), Inches(0.42))
    if footer:
        _slide_num[0] += 1
        # thin separator line
        sep = slide.shapes.add_shape(1, Inches(0.3), Inches(6.95), Inches(11.1), Pt(1))
        sep.fill.solid()
        sep.fill.fore_color.rgb = DIM_CLR
        sep.line.fill.background()
        # left: conference info
        txb(slide, f"{CONFERENCE}  ·  {EVENT_CITY}, {EVENT_DATE}",
            Inches(0.3), Inches(7.02), Inches(9.5), Inches(0.35),
            size=11, color=DIM_CLR)
        # right: page number (before logo)
        txb(slide, str(_slide_num[0]),
            Inches(10.9), Inches(7.02), Inches(0.6), Inches(0.35),
            size=11, color=DIM_CLR, align=PP_ALIGN.RIGHT)
    return slide


def txb(slide, text, x, y, w, h,
        size=24, bold=False, color=BODY_CLR,
        align=PP_ALIGN.LEFT, italic=False):
    box = slide.shapes.add_textbox(x, y, w, h)
    tf  = box.text_frame
    tf.word_wrap = True
    p = tf.paragraphs[0]
    p.alignment = align
    run = p.add_run()
    run.text = text
    run.font.size   = Pt(size)
    run.font.bold   = bold
    run.font.italic = italic
    run.font.color.rgb = color
    run.font.name   = FONT
    return box


def title_slide_layout(slide, title, subtitle=None):
    txb(slide, title,
        Inches(1), Inches(2.8), Inches(11.33), Inches(1.2),
        size=48, bold=True, color=TITLE_CLR, align=PP_ALIGN.CENTER)
    if subtitle:
        txb(slide, subtitle,
            Inches(1), Inches(4.1), Inches(11.33), Inches(0.8),
            size=24, color=DIM_CLR, align=PP_ALIGN.CENTER)


def section_header(slide, title, accent=ACCENT_PG):
    """Full-width coloured bar at top, then title."""
    bar = slide.shapes.add_shape(
        1,  # MSO_SHAPE_TYPE.RECTANGLE
        Inches(0), Inches(0), W, Inches(0.12)
    )
    bar.fill.solid()
    bar.fill.fore_color.rgb = accent
    bar.line.fill.background()

    txb(slide, title,
        Inches(0.5), Inches(0.2), Inches(12.33), Inches(0.8),
        size=32, bold=True, color=TITLE_CLR)


def bullet_box(slide, items, x, y, w, h, size=20, color=BODY_CLR, indent=False):
    box = slide.shapes.add_textbox(x, y, w, h)
    tf  = box.text_frame
    tf.word_wrap = True
    first = True
    for item in items:
        if first:
            p = tf.paragraphs[0]
            first = False
        else:
            p = tf.add_paragraph()
        p.space_before = Pt(4)
        run = p.add_run()
        run.text = ("    " if indent else "") + item
        run.font.size  = Pt(size)
        run.font.color.rgb = color
        run.font.name  = FONT


def code_box(slide, code, x, y, w, h, size=13):
    # Background rectangle (no text)
    bg = slide.shapes.add_shape(1, x, y, w, h)
    bg.fill.solid()
    bg.fill.fore_color.rgb = CODE_BG
    bg.line.color.rgb = RGBColor(0x58, 0x5b, 0x70)
    bg.text_frame.text = ""

    # Text box on top — textboxes have predictable left-aligned defaults
    pad = Pt(7)
    tb = slide.shapes.add_textbox(x + pad, y + pad, w - pad * 2, h - pad * 2)
    tf = tb.text_frame
    tf.word_wrap = False
    tf.margin_left   = Pt(0)
    tf.margin_right  = Pt(0)
    tf.margin_top    = Pt(0)
    tf.margin_bottom = Pt(0)

    first = True
    for line in code.strip().split("\n"):
        if first:
            p = tf.paragraphs[0]
            first = False
        else:
            p = tf.add_paragraph()
        p.alignment    = PP_ALIGN.LEFT
        p.space_before = Pt(0)
        p.space_after  = Pt(0)
        # Explicitly zero out left margin, hanging indent, and remove any bullet
        pPr = p._p.get_or_add_pPr()
        pPr.set("marL", "0")
        pPr.set("indent", "0")
        for tag in ("a:buClr","a:buClrTx","a:buFont","a:buFontTx","a:buChar","a:buAutoNum","a:buNone"):
            for el in pPr.findall(qn(tag)):
                pPr.remove(el)
        pPr.append(OxmlElement("a:buNone"))
        run = p.add_run()
        run.text = line
        run.font.size  = Pt(size)
        run.font.color.rgb = CODE_CLR
        run.font.name  = "Courier New"


def divider(slide, y, color=DIM_CLR):
    line = slide.shapes.add_shape(1, Inches(0.5), y, Inches(12.33), Pt(1))
    line.fill.solid()
    line.fill.fore_color.rgb = color
    line.line.fill.background()


# ════════════════════════════════════════════════════════════════════════════
# Slide 1 — Titelfolie
# ════════════════════════════════════════════════════════════════════════════
s = add_slide(logo=False, footer=False)  # title slide: custom layout
title_slide_layout(s,
    "Vektoren in der Datenbank",
    "Der VECTOR-Datentyp in Oracle 26ai und PostgreSQL")
# Conference details
txb(s, CONFERENCE,
    Inches(1), Inches(5.0), Inches(11.33), Inches(0.5),
    size=20, bold=True, color=ACCENT_PG, align=PP_ALIGN.CENTER)
txb(s, f"{EVENT_DATE}  ·  {EVENT_CITY}",
    Inches(1), Inches(5.5), Inches(11.33), Inches(0.45),
    size=18, color=DIM_CLR, align=PP_ALIGN.CENTER)
# Larger centred logo
s.shapes.add_picture(LOGO_PATH, Inches(4.67), Inches(6.1), Inches(4.0), Inches(1.06))

# ════════════════════════════════════════════════════════════════════════════
# Slide 2 — Motivation: Der VECTOR-Datentyp
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Der VECTOR-Datentyp", ACCENT_PG)
bullet_box(s, [
    "▸  VECTOR ist ein neuer nativer Datentyp in Oracle AI Database 26ai und PostgreSQL (pgvector)",
    "▸  Ermöglicht das Speichern hochdimensionaler Vektoren direkt in der Datenbank",
    "▸  Bringt optimierte Suchoperatoren und Indizes für Ähnlichkeitssuche (k-NN) mit",
    "▸  Macht KI-Embeddings zu einem First-Class-Citizen in relationalen Datenbanken",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(2.2), size=22)

divider(s, Inches(3.7))

txb(s, "Ziel dieses Vortrags", Inches(0.8), Inches(3.85), Inches(11.5), Inches(0.5),
    size=22, bold=True, color=ACCENT_PG)
bullet_box(s, [
    "▸  Den VECTOR-Datentyp erklären — was er ist, wie er funktioniert",
    "▸  Gemeinsamkeiten und Unterschiede zwischen Oracle 26ai und PostgreSQL/pgvector zeigen",
    "▸  Eine konkrete Demo: semantische Bildsuche mit 116 Street-Fotos",
    "▸  Drei Ansätze vergleichen: pgvector, Oracle (Python-Embedding), Oracle (In-Database-Embedding)",
], Inches(0.8), Inches(4.4), Inches(11.5), Inches(2.3), size=20)

# ════════════════════════════════════════════════════════════════════════════
# Slide 3 — Agenda
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Agenda", ACCENT_PG)
bullet_box(s, [
    "01  Was ist ein Vektor?",
    "02  Semantische Suche — jenseits von Schlüsselwörtern",
    "03  Das CLIP-Modell",
    "04  Ähnlichkeit messen: Cosinus-Distanz",
    "05  PostgreSQL + pgvector",
    "06  Oracle 26ai — nativer Vektor-Support",
    "07  Oracle 26ai — Embedding in der Datenbank",
    "08  Architektur der Demo",
    "09  Demo",
    "10  Vergleich & Fazit",
], Inches(1.5), Inches(1.3), Inches(10), Inches(5.5), size=20)

# ════════════════════════════════════════════════════════════════════════════
# Slide 3 — Was ist ein Vektor?
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Was ist ein Vektor?", ACCENT_PG)
bullet_box(s, [
    "▸  Ein Vektor ist eine geordnete Liste von Zahlen: [0.12, -0.87, 0.44, …]",
    "▸  Jede Zahl beschreibt eine Dimension im semantischen Raum",
    "▸  Moderne KI-Modelle erzeugen Vektoren mit 512 bis 1536 Dimensionen",
    "▸  Ähnliche Inhalte → ähnliche Vektoren → kleiner Abstand im Raum",
    "▸  Texte, Bilder, Audio — alles lässt sich in denselben Vektorraum einbetten",
], Inches(0.8), Inches(1.3), Inches(7.2), Inches(4), size=20)

# 2-D vector diagram on the right
s.shapes.add_picture(DIAG_S3, Inches(7.8), Inches(1.1), Inches(5.3), Inches(5.3))

txb(s, "Vektoren machen Ähnlichkeit berechenbar.",
    Inches(0.3), Inches(5.75), Inches(7.4), Inches(0.8),
    size=26, bold=True, color=ACCENT_GRN)

# ════════════════════════════════════════════════════════════════════════════
# Slide 4 — Semantische Suche
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Semantische Suche — jenseits von Schlüsselwörtern", ACCENT_PG)
bullet_box(s, [
    "Klassische Suche:    \"trees\" findet nur Dokumente mit dem Wort \"trees\"",
    "",
    "Semantische Suche:  \"trees\" findet Bilder von Wäldern, Parks, Natur —",
    "                             ohne dass das Wort irgendwo steht",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(2.2), size=20)

divider(s, Inches(3.7))

bullet_box(s, [
    "▸  Text-Anfrage wird in denselben Vektorraum eingebettet wie die Bilder",
    "▸  Datenbankabfrage: finde die k nächsten Nachbarn (k-NN)",
    "▸  Ergebnis: Bilder nach semantischer Ähnlichkeit gerankt",
    "▸  Kein manuelles Tagging, keine Metadaten nötig",
], Inches(0.8), Inches(3.9), Inches(11.5), Inches(1.1), size=20)

# Flow diagram
s.shapes.add_picture(DIAG_S4, Inches(0.5), Inches(5.1), Inches(12.3), Inches(1.75))

# ════════════════════════════════════════════════════════════════════════════
# Slide 5 — CLIP-Modell
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Das CLIP-Modell (OpenAI)", ACCENT_IDB)
bullet_box(s, [
    "CLIP = Contrastive Language–Image Pretraining",
    "▸  Trainiert auf hunderten Millionen Bild-Text-Paaren",
    "▸  Bildet sowohl Bilder als auch Text in denselben 512-dimensionalen Raum ab",
    "▸  Modell: clip-ViT-B-32  (Vision Transformer, Patch-Größe 32×32)",
    "▸  Quell-Gewichte: Hugging Face Hub (sentence-transformers/clip-ViT-B-32)",
], Inches(0.8), Inches(1.3), Inches(7.5), Inches(3.2), size=20)

code_box(s,
    'from sentence_transformers import (\n    SentenceTransformer)\n\nmodel = SentenceTransformer(\n    "clip-ViT-B-32")\n\n# Bild einbetten\nvec = model.encode(image)\n# → 512 floats\n\n# Text einbetten\nvec = model.encode("Bäume")\n# → 512 floats, gleicher Raum!',
    Inches(8.8), Inches(1.3), Inches(4.3), Inches(3.8), size=11)

txb(s, "Bild-Vektor und Text-Vektor zeigen in dieselbe Richtung,\nwenn Bild und Text inhaltlich übereinstimmen.",
    Inches(0.8), Inches(5.0), Inches(11.5), Inches(1.0),
    size=18, italic=True, color=ACCENT_IDB)

# ════════════════════════════════════════════════════════════════════════════
# Slide 6 — Cosinus-Distanz
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Ähnlichkeit messen: Cosinus-Distanz", ACCENT_PG)
bullet_box(s, [
    "▸  CLIP-Vektoren haben unterschiedliche Beträge — daher kein euklidischer Abstand",
    "▸  Cosinus-Distanz misst nur den Winkel zwischen zwei Vektoren",
    "▸  Cosinus-Distanz = 0   →  identisch",
    "▸  Cosinus-Distanz = 1   →  völlig unähnlich",
    "▸  Ähnlichkeitswert = 1 − Distanz  →  1.0 = perfekte Übereinstimmung",
], Inches(0.8), Inches(1.3), Inches(7.5), Inches(3.5), size=20)

# Cosine diagram on the right
s.shapes.add_picture(DIAG_S6, Inches(8.0), Inches(1.1), Inches(5.1), Inches(3.7))

code_box(s,
    "-- PostgreSQL\n1 - (embedding <=> query_vec)\n\n-- Oracle 26ai\n1 - VECTOR_DISTANCE(embedding, query_vec, COSINE)",
    Inches(0.8), Inches(5.0), Inches(6.0), Inches(1.85), size=13)

txb(s, "In der Demo:\nScore 28 % = schwach\nScore 75 % = stark",
    Inches(7.0), Inches(5.0), Inches(5.0), Inches(1.85),
    size=18, color=ACCENT_GRN)

# ════════════════════════════════════════════════════════════════════════════
# Slide 7 — PostgreSQL + pgvector: Voraussetzungen
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "PostgreSQL + pgvector", ACCENT_PG)

txb(s, "Was wird benötigt?", Inches(0.8), Inches(1.3), Inches(11), Inches(0.5),
    size=22, bold=True, color=ACCENT_PG)
bullet_box(s, [
    "▸  PostgreSQL (ab Version 13)",
    "▸  pgvector-Extension  —  docker image: pgvector/pgvector:pg18",
    "▸  Extension aktivieren:  CREATE EXTENSION vector;",
    "▸  Python-Paket:  psycopg2-binary",
    "▸  KI-Bibliothek:  sentence-transformers  (auf dem Anwendungsserver)",
], Inches(0.8), Inches(1.9), Inches(11.5), Inches(2.5), size=20)

divider(s, Inches(4.6))

txb(s, "Schema & Index", Inches(0.8), Inches(4.5), Inches(11), Inches(0.5),
    size=22, bold=True, color=ACCENT_PG)
code_box(s,
    "CREATE TABLE images (\n    id        SERIAL PRIMARY KEY,\n    filename  TEXT NOT NULL UNIQUE,\n    embedding vector(512)          -- pgvector-Typ\n);\n\nCREATE INDEX ON images USING hnsw (embedding vector_cosine_ops);",
    Inches(0.8), Inches(5.0), Inches(7.5), Inches(1.85), size=13)

bullet_box(s, [
    "HNSW = Hierarchical Navigable Small World",
    "Approximativer k-NN Index",
    "Sehr schnell bei der Suche",
], Inches(8.8), Inches(5.0), Inches(4.3), Inches(1.85), size=18, color=DIM_CLR)

# ════════════════════════════════════════════════════════════════════════════
# Slide 8 — PostgreSQL: Suchanfrage
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "PostgreSQL: Suchanfrage", ACCENT_PG)

bullet_box(s, [
    "1.  Text-Anfrage mit CLIP in Python in einen Vektor umwandeln",
    "2.  Vektor an die SQL-Abfrage übergeben",
    "3.  PostgreSQL findet die ähnlichsten Bilder via HNSW-Index",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(1.5), size=20)

code_box(s,
    "# Python\nvec = model.encode(\"Bäume\")       # → 512 floats\n\n# SQL\nSELECT filename,\n       1 - (embedding <=> %s::vector) AS score\nFROM   images\nORDER  BY embedding <=> %s::vector\nLIMIT  12;",
    Inches(0.8), Inches(3.0), Inches(7.5), Inches(3.5), size=16)

bullet_box(s, [
    "<=>  Cosinus-Distanz-Operator",
    "(pgvector-spezifisch)",
    "",
    "$1::vector  expliziter Cast",
    "erforderlich",
    "",
    "LIMIT statt FETCH FIRST",
], Inches(9.0), Inches(3.0), Inches(4.0), Inches(3.5), size=18, color=DIM_CLR)

# ════════════════════════════════════════════════════════════════════════════
# Slide 9 — Oracle 26ai: Nativer Support
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Oracle 26ai — nativer Vektor-Support", ACCENT_ORA)

txb(s, "Was wird benötigt?", Inches(0.8), Inches(1.3), Inches(11), Inches(0.5),
    size=22, bold=True, color=ACCENT_ORA)
bullet_box(s, [
    "▸  Oracle AI Database 26ai Free (oder Enterprise)",
    "▸  Keine Extension nötig — Vektoren sind eingebaut",
    "▸  Vector Memory Area im SGA konfigurieren (für HNSW-Index)",
    "▸  Python-Paket: oracledb  (Thin Mode — kein Oracle Client nötig)",
    "▸  KI-Bibliothek: sentence-transformers  (auf dem Anwendungsserver)",
], Inches(0.8), Inches(1.9), Inches(11.5), Inches(2.2), size=20)

divider(s, Inches(4.2))

txb(s, "Schema & Index", Inches(0.8), Inches(4.3), Inches(11), Inches(0.45),
    size=20, bold=True, color=ACCENT_ORA)
code_box(s,
    "CREATE TABLE images (\n    id        NUMBER GENERATED ALWAYS AS IDENTITY PRIMARY KEY,\n    filename  VARCHAR2(255) NOT NULL UNIQUE,\n    embedding VECTOR(512, FLOAT32)     -- Typ + Dimension\n);\nCREATE VECTOR INDEX images_idx ON images(embedding)\n    ORGANIZATION INMEMORY NEIGHBOR GRAPH\n    WITH DISTANCE COSINE WITH TARGET ACCURACY 95;",
    Inches(0.8), Inches(4.8), Inches(8.5), Inches(2.0), size=11)

bullet_box(s, [
    "HNSW im SGA",
    "(Vector Memory Area)",
    "512 MB konfiguriert",
], Inches(9.8), Inches(4.8), Inches(3.3), Inches(2.0), size=17, color=DIM_CLR)

# ════════════════════════════════════════════════════════════════════════════
# Slide 10 — Oracle: Unterschiede zu pgvector
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Oracle vs. pgvector — Schema-Unterschiede", ACCENT_ORA)

rows = [
    ("Extension",       "CREATE EXTENSION vector",        "Eingebaut, keine Extension"),
    ("Vektor-Spalte",   "vector(512)  — nur Dimension",   "VECTOR(512, FLOAT32)  — Dim + Typ"),
    ("Primary Key",     "SERIAL",                          "NUMBER GENERATED ALWAYS AS IDENTITY"),
    ("Text-Spalte",     "TEXT  (unbegrenzt)",              "VARCHAR2(n)  — Länge erforderlich"),
    ("HNSW-Syntax",     "USING hnsw (...ops)",             "ORGANIZATION INMEMORY NEIGHBOR GRAPH"),
    ("Genauigkeit",     "Implizit via Index-Parameter",   "WITH TARGET ACCURACY 95  (explizit)"),
    ("Speicher",        "Kein Sonder-Speicher nötig",     "vector_memory_size im SGA"),
    ("Abstand-Op",      "<=>  (Operator)",                 "VECTOR_DISTANCE(col, vec, COSINE)"),
    ("Top-N",           "LIMIT n",                         "FETCH FIRST n ROWS ONLY"),
]

# Column header row
y = Inches(1.3)
hdr_bg = s.shapes.add_shape(1, Inches(0.3), y, Inches(12.7), Inches(0.55))
hdr_bg.fill.solid()
hdr_bg.fill.fore_color.rgb = RGBColor(0x18, 0x18, 0x28)
hdr_bg.line.fill.background()
txb(s, "Aspekt",               Inches(0.4), y + Pt(6), Inches(2.2), Inches(0.5), size=14, bold=True, color=BODY_CLR)
txb(s, "PostgreSQL + pgvector",Inches(2.7), y + Pt(6), Inches(4.8), Inches(0.5), size=14, bold=True, color=ACCENT_PG)
txb(s, "Oracle 26ai",          Inches(7.6), y + Pt(6), Inches(5.4), Inches(0.5), size=14, bold=True, color=ACCENT_ORA)
y += Inches(0.56)

for i, (aspect, pg, ora) in enumerate(rows):
    bg_color = RGBColor(0x28, 0x29, 0x3d) if i % 2 == 0 else RGBColor(0x24, 0x25, 0x38)
    row_bg = s.shapes.add_shape(1, Inches(0.3), y, Inches(12.7), Inches(0.52))
    row_bg.fill.solid()
    row_bg.fill.fore_color.rgb = bg_color
    row_bg.line.fill.background()

    txb(s, aspect, Inches(0.4), y + Pt(5), Inches(2.2), Inches(0.48), size=13, bold=True, color=DIM_CLR)
    txb(s, pg,     Inches(2.7), y + Pt(5), Inches(4.8), Inches(0.48), size=13, color=ACCENT_PG)
    txb(s, ora,    Inches(7.6), y + Pt(5), Inches(5.4), Inches(0.48), size=13, color=ACCENT_ORA)
    y += Inches(0.53)

# ════════════════════════════════════════════════════════════════════════════
# Slide 11 — Oracle In-Database Embedding
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Oracle 26ai — Embedding in der Datenbank", ACCENT_IDB)

bullet_box(s, [
    "▸  Oracle kann ONNX-Modelle direkt in die Datenbank laden",
    "     (ONNX = Open Neural Network Exchange)",
    "▸  VECTOR_EMBEDDING() ruft das Modell innerhalb einer SQL-Abfrage auf",
    "▸  Kein Python, keine KI-Bibliothek auf dem Anwendungsserver zur Laufzeit",
    "▸  Der Text-String ist der einzige Parameter aus Python",
    "▸  Schema: VECTOR  —  Tabelle: FOTO_VEKTOR  —  Bilder als BLOB gespeichert",
    "▸  HNSW-Index auf FOTO_VEKTOR (wie in Schema VECTORS_USER)",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(2.4), size=16)

code_box(s,
    "-- Gesamte Logik in einem SQL-Statement\nSELECT filename,\n       1 - VECTOR_DISTANCE(\n               foto_vek,\n               VECTOR_EMBEDDING(CLIP_TXT USING :q AS data),\n               COSINE\n           ) AS score\nFROM   VECTOR.FOTO_VEKTOR\nORDER  BY VECTOR_DISTANCE(\n             foto_vek,\n             VECTOR_EMBEDDING(CLIP_TXT USING :q AS data), COSINE)\nFETCH  FIRST 12 ROWS ONLY;",
    Inches(0.8), Inches(3.8), Inches(7.5), Inches(3.0), size=11)

bullet_box(s, [
    ":q  = reiner Text aus Python",
    "",
    "Oracle übernimmt:",
    "  • Tokenisierung",
    "  • ONNX-Inferenz",
    "  • Vektorsuche",
    "",
    "→ Architektur vereinfacht sich",
], Inches(9.0), Inches(3.8), Inches(4.0), Inches(3.0), size=16, color=DIM_CLR)

# ════════════════════════════════════════════════════════════════════════════
# Slide 12 — ONNX in Oracle: Besonderheit
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "ONNX in Oracle: Was zu beachten ist", ACCENT_IDB)

bullet_box(s, [
    "Oracle's ONNX-Validator stellt strenge Anforderungen an das Modell-Graph:",
    "",
    "▸  input_ids darf nur in einem einzigen Gather-Knoten verwendet werden",
    "▸  Standard-CLIP-Export verwendet input_ids auch in ArgMax  →  wird abgelehnt",
    "",
    "Lösung: CLIP_TXT mit CLS-Token-Pooling (Position 0) statt EOS-Token-Pooling",
    "▸  Einfacherer ONNX-Graph, den Oracle akzeptiert",
    "▸  Cosinus-Ähnlichkeit zwischen EOS- und CLS-Variante: ~0,70",
    "▸  Modell muss beim Export entsprechend angepasst werden",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(3.8), size=19)

code_box(s,
    "-- Modell laden (einmalig durch Administrator)\nEXEC DBMS_VECTOR.LOAD_ONNX_MODEL(\n    'VEC_DUMP', 'clip_txt.onnx', 'CLIP_TXT',\n    JSON('{\"function\":\"embedding\",\"embeddingOutput\":\"output\",\n          \"input\":{\"input\":[\"DATA\"]}}'));",
    Inches(0.8), Inches(5.2), Inches(11.5), Inches(1.6), size=13)

# ════════════════════════════════════════════════════════════════════════════
# Slide 13 — Architektur: Wo wird CLIP berechnet?
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Architektur der Demo", ACCENT_GRN)
s.shapes.add_picture(DIAG_ARCH, Inches(0.3), Inches(1.1), Inches(12.73), Inches(5.7))

# Slide 15 — Demo-Hinweis
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Demo", ACCENT_GRN)

for url, label, color, y in [
    ("http://localhost:8000/ui/", "pgvector (blau)",    ACCENT_PG,  Inches(2.2)),
    ("http://localhost:8001/ui/", "Oracle 26ai (rot)",  ACCENT_ORA, Inches(3.5)),
    ("http://localhost:8002/ui/", "Oracle In-DB (lila)",ACCENT_IDB, Inches(4.8)),
]:
    txb(s, url,   Inches(1.5), y,               Inches(6),    Inches(0.5), size=22, bold=True, color=color)
    txb(s, label, Inches(7.8), y + Inches(0.05), Inches(4.5), Inches(0.5), size=20, color=DIM_CLR)

txb(s, "Suchbegriffe zum Ausprobieren:",
    Inches(1.5), Inches(5.9), Inches(10), Inches(0.5), size=18, color=BODY_CLR)
txb(s, "Bäume  ·  Wasser  ·  Menschen  ·  Gebäude  ·  Himmel  ·  Nacht  ·  Autos",
    Inches(1.5), Inches(6.3), Inches(10), Inches(0.6), size=20, bold=True, color=ACCENT_GRN)

# ════════════════════════════════════════════════════════════════════════════
# Slide 15 — Vergleich
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Vergleich", ACCENT_PG)

rows = [
    ("Merkmal",                "PostgreSQL + pgvector",       "Oracle · VECTORS_USER",      "Oracle · VECTOR"),
    ("Fotos indiziert",        "116",                          "116",                         "116"),
    ("Indizierungszeit",       "Ø 12,1 Sek.  (3 Läufe)",      "Ø 12,1 Sek.  (3 Läufe)",     "Ø 13,6 Sek.  (3 Läufe)"),
    ("Index-Typ",              "HNSW (auf Disk)",              "HNSW (im Speicher)",          "HNSW (im Speicher)"),
    ("RAM-Bedarf",             "Keiner",                       "512 MB SGA",                  "512 MB SGA"),
    ("CLIP zur Laufzeit",      "Ja (Python)",                  "Ja (Python)",                 "Nein"),
    ("Embedding-Ort",          "Python-Prozess",               "Python-Prozess",              "In der Datenbank"),
    ("VECTOR_EMBEDDING()",     "—",                            "—",                           "Ja"),
    ("Extension nötig",        "CREATE EXTENSION vector",      "Nein",                        "Nein"),
]

y = Inches(1.3)
header = True
for row in rows:
    bg_color = RGBColor(0x18, 0x18, 0x28) if header else (RGBColor(0x28, 0x29, 0x3d) if rows.index(row) % 2 == 0 else RGBColor(0x24, 0x25, 0x38))
    row_bg = s.shapes.add_shape(1, Inches(0.3), y, Inches(12.7), Inches(0.52))
    row_bg.fill.solid()
    row_bg.fill.fore_color.rgb = bg_color
    row_bg.line.fill.background()

    colors = [DIM_CLR, ACCENT_PG, ACCENT_ORA, ACCENT_IDB] if header else [BODY_CLR, ACCENT_PG, ACCENT_ORA, ACCENT_IDB]
    widths = [2.5, 3.0, 3.1, 3.1]
    xs = [0.4, 2.9, 6.0, 9.15]
    for j, (cell, col, w, x) in enumerate(zip(row, colors, widths, xs)):
        txb(s, cell, Inches(x), y + Pt(4), Inches(w), Inches(0.48),
            size=13, bold=header, color=col)
    y += Inches(0.53)
    header = False

# ════════════════════════════════════════════════════════════════════════════
# Slide 16 — Fazit
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Fazit", ACCENT_GRN)

bullet_box(s, [
    "▸  Beide Datenbanken unterstützen Vektorsuche produktionsreif",
    "▸  pgvector: einfach, leichtgewichtig, kein zusätzlicher Speicher nötig",
    "▸  Oracle 26ai: vollständig integriert, kein Extension-Management",
    "▸  Oracle In-DB Embedding: Architektur ohne ML-Laufzeit im App-Server",
    "▸  CLIP ermöglicht Bildersuche per Freitext — ohne Tagging oder Metadaten",
    "▸  HNSW liefert schnelle approximative k-NN-Suche in beiden Datenbanken",
    "▸  VECTOR ist eine sehr willkommene Erweiterung — relationale Datenbanken",
    "     nutzen damit KI-Embeddings als First-Class-Citizen",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(4.2), size=21)

divider(s, Inches(5.1))

txb(s, "Quellcode & Dokumentation",
    Inches(0.8), Inches(5.2), Inches(11), Inches(0.5),
    size=20, bold=True, color=BODY_CLR)
txb(s, "https://gitea.dl-cons.de/dierk/vector-search-demo",
    Inches(0.8), Inches(5.7), Inches(11), Inches(0.5),
    size=20, color=ACCENT_PG)

txb(s, "Programmierung und Folien unterstützt durch Claude (Anthropic)",
    Inches(0.8), Inches(6.55), Inches(11.33), Inches(0.35),
    size=13, italic=True, color=DIM_CLR, align=PP_ALIGN.CENTER)


# ════════════════════════════════════════════════════════════════════════════
# Save
# ════════════════════════════════════════════════════════════════════════════
OUT = "Vektoren in der Datenbank.pptx"
prs.save(OUT)
print(f"Saved: {OUT}  ({prs.slides.__len__()} slides)")