Initial commit: Hermes Agent Skills collection
This commit is contained in:
Debian
@@ -0,0 +1,165 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Batch visual QA of rendered document pages/slides via direct vLLM API calls.
|
||||
|
||||
Bypasses the vision_analyze tool — useful when:
|
||||
- vision_analyze fails due to config caching / model resolution issues
|
||||
- You need to QA many images efficiently in one pass
|
||||
- The active chat model is text-only but a multimodal model is on the same endpoint
|
||||
|
||||
Usage:
|
||||
python batch_vision_qa.py /path/to/images/ <num_images> [options]
|
||||
|
||||
Environment variables:
|
||||
NORIS_API_KEY - API key for the vLLM endpoint (required)
|
||||
VISION_BASE_URL - Full chat completions URL (default: https://ai.noris.de/v1/chat/completions)
|
||||
VISION_MODEL - Model name (default: vllm/release/gemma-4-31b-it)
|
||||
|
||||
Example:
|
||||
NORIS_API_KEY=sk-bf-xxx python batch_vision_qa.py /home/debian/ai101/qa/ 17
|
||||
|
||||
Expects files named slide-01.jpg, slide-02.jpg, ..., slide-NN.jpg.
|
||||
Outputs per-slide status and a summary of any issues found.
|
||||
|
||||
Before using: verify the model accepts images (see references/model-capabilities.md).
|
||||
"""
|
||||
|
||||
import sys
|
||||
import os
|
||||
import base64
|
||||
import json
|
||||
import time
|
||||
import urllib.request
|
||||
|
||||
API_KEY = os.environ.get("NORIS_API_KEY", "")
|
||||
BASE_URL = os.environ.get(
|
||||
"VISION_BASE_URL", "https://ai.noris.de/v1/chat/completions"
|
||||
)
|
||||
MODEL = os.environ.get("VISION_MODEL", "vllm/release/gemma-4-31b-it")
|
||||
|
||||
# Expanded 6-category prompt: overlap, overflow, contrast, layout, content, symbols
|
||||
QA_PROMPT_TEMPLATE = """You are a visual QA reviewer for a professional presentation slide.
|
||||
Analyze this slide carefully for ALL of these issues:
|
||||
1. TEXT OVERLAP: Any text overlapping other text or graphics?
|
||||
2. TEXT OVERFLOW: Any text extending beyond edges or getting cut off?
|
||||
3. CONTRAST: Any low contrast between text and background making text hard to read?
|
||||
4. LAYOUT: Misalignment, elements too close, insufficient margins, awkward spacing?
|
||||
5. CONTENT: Unclear messaging, missing information, placeholder text, spelling errors, logical inconsistencies?
|
||||
6. SYMBOLS: Any broken/missing Unicode characters showing as boxes or empty circles?
|
||||
|
||||
Respond in this exact JSON format:
|
||||
{{"slide": {slide_num}, "overlap": "none|<description>", "overflow": "none|<description>", "contrast": "ok|<description>", "layout": "ok|<description>", "content": "ok|<description>", "symbols": "ok|<description>", "overall": "clean|issues found"}}
|
||||
|
||||
Be precise and thorough. If no issues, say "clean". If issues exist, describe them specifically."""
|
||||
|
||||
|
||||
def qa_single_image(image_path: str, slide_num: int) -> dict:
|
||||
"""Send one image to the vision model and return parsed QA result."""
|
||||
with open(image_path, "rb") as f:
|
||||
img_b64 = base64.b64encode(f.read()).decode()
|
||||
|
||||
payload = {
|
||||
"model": MODEL,
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": QA_PROMPT_TEMPLATE.format(slide_num=slide_num),
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": f"data:image/jpeg;base64,{img_b64}"
|
||||
},
|
||||
},
|
||||
],
|
||||
}
|
||||
],
|
||||
"max_tokens": 500,
|
||||
}
|
||||
|
||||
req = urllib.request.Request(
|
||||
BASE_URL,
|
||||
data=json.dumps(payload).encode(),
|
||||
headers={
|
||||
"Authorization": f"Bearer {API_KEY}",
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
)
|
||||
|
||||
resp = urllib.request.urlopen(req, timeout=60)
|
||||
data = json.loads(resp.read())
|
||||
content = data["choices"][0]["message"].get("content", "")
|
||||
|
||||
# Strip markdown code fences if present
|
||||
content = content.strip()
|
||||
if content.startswith("```"):
|
||||
content = content.split("\n", 1)[-1].rsplit("```", 1)[0].strip()
|
||||
|
||||
try:
|
||||
return json.loads(content)
|
||||
except json.JSONDecodeError:
|
||||
return {
|
||||
"slide": slide_num,
|
||||
"overlap": "parse error",
|
||||
"overflow": "parse error",
|
||||
"contrast": "parse error",
|
||||
"layout": "parse error",
|
||||
"content": "parse error",
|
||||
"symbols": "parse error",
|
||||
"overall": content[:200],
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) < 3:
|
||||
print(f"Usage: {sys.argv[0]} <images_dir> <num_images>")
|
||||
print(f"Example: {sys.argv[0]} /home/debian/ai101/qa/ 17")
|
||||
sys.exit(1)
|
||||
|
||||
images_dir = sys.argv[1]
|
||||
num_slides = int(sys.argv[2])
|
||||
|
||||
if not API_KEY:
|
||||
print("ERROR: Set NORIS_API_KEY environment variable.")
|
||||
sys.exit(1)
|
||||
|
||||
results = []
|
||||
issues_found = []
|
||||
|
||||
for i in range(1, num_slides + 1):
|
||||
slide_path = os.path.join(images_dir, f"slide-{i:02d}.jpg")
|
||||
if not os.path.exists(slide_path):
|
||||
print(f"Slide {i}: file not found — {slide_path}")
|
||||
continue
|
||||
|
||||
try:
|
||||
result = qa_single_image(slide_path, i)
|
||||
results.append(result)
|
||||
status = result.get("overall", "?")
|
||||
marker = "⚠️" if "issue" in status.lower() else "✅"
|
||||
print(f"Slide {i}/{num_slides} {marker} {status}")
|
||||
if "issue" in status.lower():
|
||||
issues_found.append(result)
|
||||
except Exception as e:
|
||||
print(f"Slide {i} FAILED: {e}")
|
||||
results.append({"slide": i, "error": str(e)})
|
||||
|
||||
time.sleep(0.5)
|
||||
|
||||
print("\n" + "=" * 60)
|
||||
if issues_found:
|
||||
print(f"ISSUES ON {len(issues_found)} SLIDE(S):")
|
||||
for r in issues_found:
|
||||
print(f" Slide {r['slide']}:")
|
||||
for key in ["overlap", "overflow", "contrast", "layout", "content", "symbols"]:
|
||||
val = r.get(key, "")
|
||||
if val and val not in ("none", "ok", ""):
|
||||
print(f" {key}: {val}")
|
||||
else:
|
||||
print("ALL SLIDES CLEAN ✅")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,175 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Validate a .pptx file for PowerPoint compatibility.
|
||||
|
||||
Checks for issues that LibreOffice tolerates but PowerPoint rejects:
|
||||
- Negative shape dimensions (cx, cy ≤ 0) in <a:ext> elements
|
||||
- Negative shape positions (x, y < 0) in <a:off> elements
|
||||
- Missing required OOXML parts ([Content_Types].xml, presentation.xml, etc.)
|
||||
- Malformed XML in any part
|
||||
- Broken relationship references (rId in slide XML not found in .rels)
|
||||
- Missing Content_Type overrides for slides
|
||||
|
||||
Usage:
|
||||
python3 validate_pptx_compat.py <file.pptx>
|
||||
|
||||
Exit codes:
|
||||
0 = all checks passed
|
||||
1 = issues found (printed to stderr)
|
||||
"""
|
||||
|
||||
import sys
|
||||
import zipfile
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
NS_A = "http://schemas.openxmlformats.org/drawingml/2006/main"
|
||||
NS_P = "http://schemas.openxmlformats.org/presentationml/2006/main"
|
||||
NS_R = "http://schemas.openxmlformats.org/officeDocument/2006/relationships"
|
||||
NS_REL = "{http://schemas.openxmlformats.org/package/2006/relationships}"
|
||||
|
||||
|
||||
def validate(pptx_path: str) -> list[str]:
|
||||
"""Return a list of issue strings; empty list means clean."""
|
||||
issues = []
|
||||
|
||||
with zipfile.ZipFile(pptx_path, "r") as z:
|
||||
# 1. Zip integrity
|
||||
bad = z.testzip()
|
||||
if bad:
|
||||
issues.append(f"BAD ZIP ENTRY: {bad}")
|
||||
|
||||
# 2. XML parse check on all XML/rels parts
|
||||
for name in z.namelist():
|
||||
if name.endswith(".xml") or name.endswith(".rels"):
|
||||
try:
|
||||
ET.parse(z.open(name))
|
||||
except ET.ParseError as e:
|
||||
issues.append(f"XML PARSE ERROR in {name}: {e}")
|
||||
|
||||
# 3. Required parts
|
||||
required = [
|
||||
"[Content_Types].xml",
|
||||
"_rels/.rels",
|
||||
"ppt/presentation.xml",
|
||||
"ppt/_rels/presentation.xml.rels",
|
||||
"ppt/theme/theme1.xml",
|
||||
]
|
||||
for req in required:
|
||||
if req not in z.namelist():
|
||||
issues.append(f"MISSING REQUIRED PART: {req}")
|
||||
|
||||
# 4. Slide rels existence
|
||||
slides = [
|
||||
f for f in z.namelist()
|
||||
if f.startswith("ppt/slides/slide") and f.endswith(".xml")
|
||||
]
|
||||
for s in sorted(slides):
|
||||
rels = s.replace("ppt/slides/", "ppt/slides/_rels/") + ".rels"
|
||||
if rels not in z.namelist():
|
||||
issues.append(f"MISSING RELS for {s}")
|
||||
|
||||
# 5. Content_Type overrides for slides
|
||||
ct = ET.parse(z.open("[Content_Types].xml"))
|
||||
ct_ns = {"ct": "http://schemas.openxmlformats.org/package/2006/content-types"}
|
||||
overrides = [
|
||||
o.get("PartName") for o in ct.findall(".//ct:Override", ct_ns)
|
||||
]
|
||||
for s in sorted(slides):
|
||||
part_name = "/" + s
|
||||
if part_name not in overrides:
|
||||
issues.append(f"Missing Content_Type override for {s}")
|
||||
|
||||
# 6. Negative dimensions and positions (THE key check)
|
||||
for i in range(1, len(slides) + 1):
|
||||
slide_path = f"ppt/slides/slide{i}.xml"
|
||||
if slide_path not in z.namelist():
|
||||
continue
|
||||
root = ET.parse(z.open(slide_path)).getroot()
|
||||
|
||||
for sp in root.iter(f"{{{NS_P}}}sp"):
|
||||
spPr = sp.find(f".//{{{NS_P}}}spPr")
|
||||
if spPr is None:
|
||||
continue
|
||||
|
||||
# Get shape name for reporting
|
||||
cNvPr = sp.find(f".//{{{NS_P}}}cNvPr")
|
||||
name = cNvPr.get("name", "?") if cNvPr is not None else "?"
|
||||
|
||||
xfrm = spPr.find(f"{{{NS_A}}}xfrm")
|
||||
if xfrm is None:
|
||||
continue
|
||||
|
||||
off = xfrm.find(f"{{{NS_A}}}off")
|
||||
ext = xfrm.find(f"{{{NS_A}}}ext")
|
||||
|
||||
if ext is not None:
|
||||
cx = int(ext.get("cx", "0"))
|
||||
cy = int(ext.get("cy", "0"))
|
||||
if cx <= 0 or cy <= 0:
|
||||
issues.append(
|
||||
f"slide{i}: shape \"{name}\" has zero/negative extent: "
|
||||
f"cx={cx} cy={cy}"
|
||||
)
|
||||
|
||||
if off is not None:
|
||||
x = int(off.get("x", "0"))
|
||||
y = int(off.get("y", "0"))
|
||||
if x < 0 or y < 0:
|
||||
issues.append(
|
||||
f"slide{i}: shape \"{name}\" has negative position: "
|
||||
f"x={x} y={y}"
|
||||
)
|
||||
|
||||
# 7. Broken image embed references
|
||||
for i in range(1, len(slides) + 1):
|
||||
slide_path = f"ppt/slides/slide{i}.xml"
|
||||
if slide_path not in z.namelist():
|
||||
continue
|
||||
root = ET.parse(z.open(slide_path)).getroot()
|
||||
|
||||
rels_path = f"ppt/slides/_rels/slide{i}.xml.rels"
|
||||
if rels_path not in z.namelist():
|
||||
continue
|
||||
rels_tree = ET.parse(z.open(rels_path))
|
||||
rels_root = rels_tree.getroot()
|
||||
valid_rids = {
|
||||
rel.get("Id") for rel in rels_root.findall(f"{NS_REL}Relationship")
|
||||
}
|
||||
|
||||
for blip in root.iter(f"{{{NS_A}}}blip"):
|
||||
embed = blip.get(f"{{{NS_R}}}embed")
|
||||
if embed is not None and embed not in valid_rids:
|
||||
issues.append(
|
||||
f"slide{i}: blipFill embed '{embed}' not found in rels"
|
||||
)
|
||||
|
||||
return issues
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 2:
|
||||
print("Usage: validate_pptx_compat.py <file.pptx>", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
pptx_path = sys.argv[1]
|
||||
try:
|
||||
issues = validate(pptx_path)
|
||||
except FileNotFoundError:
|
||||
print(f"File not found: {pptx_path}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
except zipfile.BadZipFile:
|
||||
print(f"Not a valid ZIP/PPTX file: {pptx_path}", file=sys.stderr)
|
||||
sys.exit(2)
|
||||
|
||||
if issues:
|
||||
print(f"❌ {len(issues)} issue(s) found:", file=sys.stderr)
|
||||
for iss in issues:
|
||||
print(f" • {iss}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
else:
|
||||
print(f"✅ {pptx_path}: all checks passed")
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user