dierk/vector-search-demo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add in-DB indexing script, benchmark results, schema names in presentation

Browse Source 
- index_images_indb.py: new script indexing via VECTOR_EMBEDDING(CLIP_IMG)
  using a two-step INSERT+UPDATE to work around ORA-24816
- index_images_oracle.py / index_images.py: add timing output
- Presentation: schema names VECTORS_USER/VECTOR in diagram and comparison,
  ONNX expansion, HNSW index note on slide 11,
  indexing times updated from 3-run benchmark (avg: PG 12.1s, Ora 12.1s, InDB 13.6s)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Dierk
2026-05-20 10:42:13 +02:00
parent e70d422c69
commit 3ef43019be
5 changed files with 324 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
make_presentation.py
+267 -48
View File
@@ -10,6 +10,12 @@ 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"
@@ -17,6 +23,242 @@ 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(-0.10, 0.34, "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", (1.12, 0.18)),
(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)
COLS = [
(2.3, "PostgreSQL 18", "#89b4fa", "Port 8000", True, False, "pgvector 0.8.2\nHNSW (Disk)", None),
(6.65, "Oracle 26ai\nVECTORS_USER", "#f38ba8", "Port 8001", True, False, "HNSW (SGA)", None),
(11.0, "Oracle 26ai\nVECTOR", "#cba6f7", "Port 8002", False, True, "HNSW (SGA)", "VECTOR_EMBEDDING()"),
]
fig, ax = _fig(13.5, 6.5)
ax.set_xlim(0, 13.5); ax.set_ylim(-0.8, 6.0)
ax.axis("off")
for x, db_name, color, port, clip_app, clip_db, db_tech, vec_fn in COLS:
# ── Column title + port
ax.text(x, 5.78, port, ha="center", color=color, fontsize=13, fontweight="bold")
# ── App server box
ax.add_patch(mpatches.FancyBboxPatch(
(x-1.7, 3.7), 3.4, 1.85,
boxstyle="round,pad=0.1", facecolor="#28293d", edgecolor=color, lw=2))
ax.text(x, 5.38, "App-Server (FastAPI)", ha="center",
color=color, fontsize=11, fontweight="bold")
if clip_app:
ax.add_patch(mpatches.FancyBboxPatch(
(x-1.2, 3.78), 2.4, 0.82,
boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=CLIP_CLR, lw=2))
ax.text(x, 4.19, "CLIP-Modell\n(sentence-transformers)",
ha="center", va="center", color=CLIP_CLR, fontsize=9.5, fontweight="bold",
multialignment="center")
else:
ax.add_patch(mpatches.FancyBboxPatch(
(x-1.2, 3.78), 2.4, 0.82,
boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=DIAG_AXIS, lw=1,
linestyle="dashed"))
ax.text(x, 4.19, "kein CLIP",
ha="center", va="center", color=DIAG_AXIS, fontsize=10, style="italic")
# ── Arrow + what is sent
ax.annotate("", xy=(x, 3.05), xytext=(x, 3.65),
arrowprops=dict(arrowstyle="->", color=DIAG_AXIS, lw=2))
arrow_lbl = "Vektor (512 floats)" if clip_app else "Text-String"
ax.text(x, 3.35, arrow_lbl, ha="center", va="center",
color=DIAG_AXIS, fontsize=9, style="italic")
# ── Database box
db_h = 2.8 if clip_db else 1.9
ax.add_patch(mpatches.FancyBboxPatch(
(x-1.7, 0.15), 3.4, db_h,
boxstyle="round,pad=0.1", facecolor="#28293d", edgecolor=color, lw=2))
if clip_db:
# CLIP ONNX box inside DB
ax.add_patch(mpatches.FancyBboxPatch(
(x-1.2, 0.25), 2.4, 0.82,
boxstyle="round,pad=0.08", facecolor="#1e1e2e", edgecolor=CLIP_CLR, lw=2))
ax.text(x, 0.66, "CLIP-Modell\n(ONNX, in Oracle)",
ha="center", va="center", color=CLIP_CLR, fontsize=9.5, fontweight="bold",
multialignment="center")
# VECTOR_EMBEDDING() label
ax.text(x, 1.22, vec_fn,
ha="center", color="#fab387", fontsize=10, fontweight="bold",
fontfamily="monospace")
# DB name
ax.text(x, 1.65, db_name, ha="center", color=color,
fontsize=11, fontweight="bold")
ax.text(x, 2.35, db_tech, ha="center", color=DIAG_AXIS,
fontsize=9, multialignment="center")
else:
ax.text(x, 1.5, db_name, ha="center", color=color,
fontsize=11, fontweight="bold")
ax.text(x, 0.72, db_tech, ha="center", color=DIAG_AXIS,
fontsize=9, multialignment="center")
# ── Vertical separators
for xsep in [4.5, 8.85]:
ax.plot([xsep, xsep], [0.05, 5.9], 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) ──────────────────────────────────────────────
@@ -235,13 +477,13 @@ bullet_box(s, [
"▸ 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(7.5), Inches(4), size=20)
], Inches(0.8), Inches(1.3), Inches(7.2), Inches(4), size=20)
code_box(s, '# 4-dimensionaler Beispielvektor\nvec_hund = [0.91, 0.12, -0.44, 0.72]\nvec_katze = [0.87, 0.18, -0.39, 0.68]\n# ähnlich! Abstand ≈ 0.04\nvec_auto = [-0.3, -0.82, 0.91, -0.11]\n# weit entfernt',
Inches(8.8), Inches(1.5), Inches(4.3), Inches(2.6), size=12)
# 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(0.8), Inches(5.8), Inches(11), Inches(0.7),
Inches(0.8), Inches(5.8), Inches(6.8), Inches(0.7),
size=22, bold=True, color=ACCENT_GRN)
# ════════════════════════════════════════════════════════════════════════════
@@ -263,7 +505,10 @@ bullet_box(s, [
"▸ 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(2.8), size=20)
], 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
@@ -297,14 +542,17 @@ bullet_box(s, [
"▸ Cosinus-Distanz = 0 → identisch",
"▸ Cosinus-Distanz = 1 → völlig unähnlich",
"▸ Ähnlichkeitswert = 1 − Distanz → 1.0 = perfekte Übereinstimmung",
], Inches(0.8), Inches(1.3), Inches(8.5), Inches(3.5), size=20)
], 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(1.9), size=13)
Inches(0.8), Inches(5.0), Inches(6.0), Inches(1.85), size=13)
txb(s, "In der Demo:\nScore 28 % = schwache Übereinstimmung\nScore 75 % = starke Übereinstimmung",
Inches(7.5), Inches(5.0), Inches(5.0), Inches(2.0),
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)
# ════════════════════════════════════════════════════════════════════════════
@@ -442,10 +690,13 @@ 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",
], Inches(0.8), Inches(1.3), Inches(11.5), Inches(2.2), size=20)
"▸ 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(3.0), size=19)
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;",
@@ -485,45 +736,13 @@ code_box(s,
Inches(0.8), Inches(5.2), Inches(11.5), Inches(1.6), size=13)
# ════════════════════════════════════════════════════════════════════════════
# Slide 13 — Architektur der Demo
# 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))
# Three columns
for i, (label, port, color) in enumerate([
("pgvector", "Port 8000", ACCENT_PG),
("Oracle 26ai\n(Python)", "Port 8001", ACCENT_ORA),
("Oracle 26ai\n(In-DB)", "Port 8002", ACCENT_IDB),
]):
x = Inches(0.5 + i * 4.27)
# Box
box = s.shapes.add_shape(1, x, Inches(1.3), Inches(3.8), Inches(4.8))
box.fill.solid()
box.fill.fore_color.rgb = RGBColor(0x28, 0x29, 0x3d)
box.line.color.rgb = color
txb(s, label, x + Inches(0.1), Inches(1.4), Inches(3.6), Inches(0.8),
size=22, bold=True, color=color, align=PP_ALIGN.CENTER)
txb(s, port, x + Inches(0.1), Inches(2.1), Inches(3.6), Inches(0.4),
size=16, color=DIM_CLR, align=PP_ALIGN.CENTER)
items = {
"pgvector": ["Browser /ui/", "FastAPI", "CLIP (Python)", "PostgreSQL 18", "pgvector 0.8.2"],
"Oracle 26ai\n(Python)": ["Browser /ui/", "FastAPI", "CLIP (Python)", "Oracle 26ai", "HNSW (SGA)"],
"Oracle 26ai\n(In-DB)": ["Browser /ui/", "FastAPI", "(kein CLIP)", "Oracle 26ai", "VECTOR_EMBEDDING()"],
}[label]
for j, item in enumerate(items):
txb(s, "▸ " + item, x + Inches(0.2), Inches(2.65 + j * 0.52), Inches(3.5), Inches(0.48),
size=16, color=BODY_CLR)
txb(s, "116 Street Fotos · CLIP ViT-B/32 · 512-dimensionale Vektoren",
Inches(0.5), Inches(6.6), Inches(12.33), Inches(0.3),
size=16, color=DIM_CLR, align=PP_ALIGN.CENTER)
# ════════════════════════════════════════════════════════════════════════════
# Slide 14 — Demo-Hinweis
# Slide 15 — Demo-Hinweis
# ════════════════════════════════════════════════════════════════════════════
s = add_slide()
section_header(s, "Demo", ACCENT_GRN)
@@ -548,10 +767,10 @@ s = add_slide()
section_header(s, "Vergleich", ACCENT_PG)
rows = [
("Merkmal", "PostgreSQL + pgvector", "Oracle 26ai (Python)", "Oracle 26ai (In-DB)"),
("Merkmal", "PostgreSQL + pgvector", "Oracle · VECTORS_USER", "Oracle · VECTOR"),
("Fotos indiziert", "116", "116", "116"),
("Indizierungszeit", "~26 Sek. (CPU)", "~16 Sek. (CPU)", "— (separat)"),
("Index-Typ", "HNSW (auf Disk)", "HNSW (im Speicher)", "Full Table Scan"),
("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"),