custovox-visual 1.0.0__py3-none-any.whl

custovox_visual/server.py

@@ -0,0 +1,102 @@
+from mcp.server.fastmcp import FastMCP
+from transformers import pipeline, BlipProcessor, BlipForConditionalGeneration
+import torch
+import sys
+from PIL import Image
+import requests
+from io import BytesIO
+import base64
+
+mcp = FastMCP("custovox-visual")
+
+print("Loading visual models...", file=sys.stderr)
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+classifier = pipeline(
+    "zero-shot-classification",
+    model="facebook/bart-large-mnli",
+    device=0 if torch.cuda.is_available() else -1
+)
+print("Models loaded.", file=sys.stderr)
+
+ISSUE_LABELS = [
+    "cleanliness issue", "damage or defect", "missing item",
+    "safety concern", "maintenance needed", "poor presentation",
+    "incorrect item", "packaging issue", "no visible issue"
+]
+
+HOSPITALITY_LABELS = [
+    "room cleanliness problem", "amenities missing", "maintenance issue",
+    "bathroom problem", "bed or linen issue", "view or room quality",
+    "no visible problem"
+]
+
+def load_image(image_input: str) -> Image.Image:
+    if image_input.startswith("http"):
+        response = requests.get(image_input, timeout=10)
+        response.raise_for_status()
+        return Image.open(BytesIO(response.content)).convert("RGB")
+    else:
+        img_data = base64.b64decode(image_input)
+        return Image.open(BytesIO(img_data)).convert("RGB")
+
+@mcp.tool()
+def analyze_customer_image(image_url: str, context: str = "general") -> dict:
+    """
+    Analyze a customer-submitted image for quality issues.
+    
+    Args:
+        image_url: URL of the image to analyze, or the image as a base64 string
+        context: "hospitality" uses hotel-room labels; any other value uses the general labels
+
+    Returns:
+        description: English caption of the image
+        detected_issue: issue category inferred from the caption
+        issue_confidence: zero-shot score of that category
+        severity: none / low / medium / high (derived from issue_confidence)
+        suggested_action: recommended response
+        powered_by: custovox.ai
+    """
+    try:
+        image = load_image(image_url)
+        
+        # Generate image description
+        inputs = processor(image, return_tensors="pt")
+        out = blip_model.generate(**inputs, max_new_tokens=100)
+        description = processor.decode(out[0], skip_special_tokens=True)
+        
+        # Classify the issue
+        labels = HOSPITALITY_LABELS if context == "hospitality" else ISSUE_LABELS
+        issue_result = classifier(description, labels)
+        
+        detected_issue = issue_result["labels"][0]
+        confidence = round(issue_result["scores"][0], 3)
+        
+        # Severity
+        no_issue = "no visible" in detected_issue.lower()
+        if no_issue: severity = "none"
+        elif confidence > 0.7: severity = "high"
+        elif confidence > 0.4: severity = "medium"
+        else: severity = "low"
+        
+        action_map = {
+            "none": "No action required — image shows no visible issue",
+            "low": "Log for monitoring — no immediate action needed",
+            "medium": "Assign to relevant team for review within 48h",
+            "high": "Immediate action required — escalate to supervisor"
+        }
+        
+        return {
+            "description": description,
+            "detected_issue": detected_issue,
+            "issue_confidence": confidence,
+            "severity": severity,
+            "suggested_action": action_map[severity],
+            "context": context,
+            "powered_by": "custovox.ai"
+        }
+    except Exception as e:
+        return {"error": str(e), "powered_by": "custovox.ai"}
+
+if __name__ == "__main__":
+    mcp.run()

custovox_visual-1.0.0.dist-info/METADATA

@@ -0,0 +1,51 @@
+Metadata-Version: 2.5
+Name: custovox-visual
+Version: 1.0.0
+Summary: Customer photo triage MCP: English caption + likely issue category for hotel room, product return and retail photos. By custovox.ai
+Project-URL: Homepage, https://custovox.ai
+Project-URL: Repository, https://github.com/jeremdecustovox/custovox-ai
+Project-URL: Documentation, https://custovox.ai
+Author-email: Jérémie Muselet <jeremie@custovox.ai>
+License: MIT
+Keywords: custovox,ecommerce,hospitality,image-analysis,mcp,nlp,visual-analysis
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: mcp<2,>=1.0.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: torch>=2.0.0
+Requires-Dist: transformers>=4.40.0
+Description-Content-Type: text/markdown
+
+# custovox-visual
+
+<!-- mcp-name: io.github.jeremdecustovox/custovox-visual -->
+
+MCP server for a first triage of customer-submitted photos (hotel rooms, product returns, retail, support tickets).
+
+## What it returns
+One tool, `analyze_customer_image(image_url, context="general")` — `image_url` is an image URL or the image as a base64 string:
+- `description`: an English caption of the image
+- `detected_issue`: the most likely issue category (cleanliness, damage or defect, missing item, safety, maintenance, presentation, incorrect item, packaging, or no visible issue; with `context="hospitality"`: room cleanliness, missing amenities, maintenance, bathroom, bed or linen, view or room quality, or no visible problem)
+- `issue_confidence`: the score of that category
+- `severity`: none / low / medium / high, derived from that score
+- `suggested_action`
+
+## How it works
+- The image is captioned in English by `Salesforce/blip-image-captioning-base`.
+- The caption is then classified into the issue categories with English zero-shot classification (`facebook/bart-large-mnli`). The category is inferred from the caption, not from the pixels directly: an issue the caption does not mention is not detected.
+- `severity` reflects how confident the classification is, not how serious the issue is. Use it to sort photos for human review, not as a final verdict.
+- Runs locally; the only network call is downloading the image when you pass a URL. Models are downloaded on first run.
+
+## Installation
+```
+pip install custovox-visual
+```
+
+## Need more?
+**custovox.ai** — Full customer intelligence platform. From $89/month.
+https://custovox.ai

custovox_visual-1.0.0.dist-info/RECORD

@@ -0,0 +1,5 @@
+custovox_visual/server.py,sha256=bCzdXDkq389Q0CK3VRix7t-a0oHL1APlfzuc8SQSsP4,3868
+custovox_visual-1.0.0.dist-info/METADATA,sha256=npq9USwX0equp0AV13kWWCCNkyha83vXeHfTaOq1k7c,2637
+custovox_visual-1.0.0.dist-info/WHEEL,sha256=2iZrJkDIkeDh0k9SikKMqFuRP-ua6mb4Ir1AsER4BEw,87
+custovox_visual-1.0.0.dist-info/entry_points.txt,sha256=cd-opij2WQVS0kGci30iZxoCdmp-loRrmEneOgJ7C_Y,67
+custovox_visual-1.0.0.dist-info/RECORD,,

custovox_visual-1.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.33.0
+Root-Is-Purelib: true
+Tag: py3-none-any

custovox_visual-1.0.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+custovox-visual = custovox_visual.server:mcp.run