tfm_ainventory/config/ai_prompt.md

Technical Inventory Hardware Extraction Protocol

Extract ALL relevant hardware items from the image with precise, standardized formatting.

Filtering Rules

• INCLUDE: Physical hardware, modules, cables, servers, storage, transceivers
• EXCLUDE: Generic mounting hardware (screws, brackets, rails), paper licenses, empty packaging
• Multi-item labels: Treat each SKU/variant as a separate item (e.g., "5m cable" and "7m cable" = 2 items)

Item Field Format (CRITICAL)

[]

Component Rules:

• <size_or_length>:

  • STORAGE CAPACITY - HUMAN READABLE: Convert to largest unit (TB/MB).
    • Examples: "1600GB" → "1.6TB", "256GB" → "256GB", "512MB" → "512MB"
    • Rule: If ≥1000GB, use TB. If ≥1000MB, use GB. Otherwise use MB.
  • CABLE/WIRE LENGTH: Meters only. Examples: "5m", "10m", "50m"
  • RAM DIMM: Capacity in GB. Examples: "128GB", "32GB", "8GB"

• <part_number>: Part number ONLY if visible. If the item has an identifiable Part Number, search web for what item this is and extract needed informations or compare with what was already identified, and correct all fields. Omit serial numbers.

• <type>: Asset class. One of: DDR3/DDR4/DDR5, SSD/HDD/NVMe, SATA/SAS, Patchcord/Fiber/Cable, SFP/Transceiver, DIMM, etc.

• <vendor>: Manufacturer (HP, HPE, Dell, Samsung, Cisco, Hynix, Intel, Broadcom)

• <connector>: Physical interface (RJ45, LC-LC, MPO, U.3, SATA, SAS, ST, SC). Omit if N/A.

Item Examples (WITH HUMAN-READABLE SIZES):

• 1.6TB NVMe HPE U.3 P66093-002 (not 1600GB)
• 256GB SSD Dell SATA SK-8765 (already human-readable)
• 5m Patchcord LC-LC
• 128GB DDR4 Hynix
• 512MB Cache Samsung SATA (stays MB if under 1GB)

Size Conversion Examples:

• 1600GB → 1.6TB
• 2048GB → 2TB
• 512GB → 512GB (under 1TB threshold)
• 256MB → 256MB
• 1024MB → 1GB

Restrictions:

• No comments in parenthesis
• No measurement units in Item field (e.g., "1.6TB" not "1.6TB Storage")
• No secondary vendors
• No diameter/mm in Item field
• ONE vendor only (primary manufacturer)

Other Fields

• Type: Repeat the asset class (DDR4, SSD, NVMe, Patchcord, etc.)
• Description: Technical summary, max 5 words. Examples: "High-speed fiber optic", "Enterprise Gen4 storage"
• Category: Memory, Storage, Network, Cabling, Compute, Optical, Transceiver
• Connector: Interface type from Item field. Examples: "LC-LC", "RJ45", "U.3"
• Size: HUMAN-READABLE capacity or length. Examples: "1.6TB", "256GB", "5m" (NOT "1600GB")
• Color: Physical color if distinguishing
• PartNr: Part number only (no serial numbers)
• OCR: Robust matching key for OCR tolerance

OCR Field Rules (CRITICAL)

Generate a SHORT, clean matching key:

• Format: UPPERCASE space-separated, NO special chars, NO duplicates
• Include ONLY: Type + Size + Primary Vendor + Connector + Part Number
• EXCLUDE: Serial numbers, secondary vendors, duplicate tokens, EMC/SK labels
• USE HUMAN-READABLE SIZE: Use TB/GB from Item field, not original notation

OCR Format: TYPE SIZE VENDOR CONNECTOR PARTNUMBER

OCR Examples (WITH HUMAN-READABLE SIZES):

• Item: 1.6TB NVMe HPE U.3 P66093-002 → OCR: NVME 1.6TB HPE U3 P66093002
• Item: 5m Patchcord LC-LC → OCR: PATCHCORD 5M LC LC
• Item: 256GB SSD Samsung SAS SK-8765 → OCR: SSD 256GB SAMSUNG SAS SK8765
• Item: 128GB DDR4 Hynix → OCR: DDR4 128GB HYNIX

OCR Constraints:

• NO duplicate part numbers
• NO secondary vendor names
• NO extraneous labels
• Each token appears ONE time only
• Remove hyphens/special chars for fuzzy matching
• Use HUMAN-READABLE sizes (1.6TB not 1600GB)

Image Processing Guidance (NEW)

Analyze the image layout and return crop/rotation metadata to optimize photo storage:

Crop Bounds Analysis

• Identify the PRIMARY ITEM in the image (main object, not background/clutter)
• Return bounding box: {x, y, width, height} in pixel coordinates
• Rules:
  • x, y: top-left corner of item (pixel offset from image top-left)
  • width, height: dimensions of item bounding box
  • Include minimal padding (10-15 pixels) around item edges
  • Ignore background clutter, other items, hands, reflections

Rotation Analysis (CRITICAL - MEASURE TEXT ANGLE)

PRIORITY: Measure text orientation, not item orientation

1. Locate readable text on the item (part numbers, manufacturer names, specifications, labels)
2. Measure the baseline angle of that text:
   • Baseline = the invisible line the text sits on
   • 0° = text baseline is HORIZONTAL (readable left-to-right)
   • Positive degrees = text rotated counter-clockwise from horizontal
   • Negative degrees = text rotated clockwise from horizontal
3. Return clockwise rotation needed to make text horizontal:
   • If text tilted 22° counter-clockwise → return +22 (rotate 22° clockwise to fix)
   • If text tilted 15° clockwise → return -15 (rotate 15° counter-clockwise to fix)
   • If text already horizontal → return 0
4. Calibration examples (measure the text angle precisely):
   • Text reads perfectly left-to-right → rotation_degrees: 0
   • Text tilted counter-clockwise, needs ~22° clockwise to straighten → rotation_degrees: 22
   • Text vertical, pointing left (rotated 90° counter-clockwise) → rotation_degrees: 90
   • Text vertical, pointing right (rotated 90° clockwise) → rotation_degrees: -90
   • Text tilted clockwise by ~45° → rotation_degrees: -45

Confidence Score

• Return confidence: 0.0-1.0 indicating reliability of crop/rotation analysis
• 0.9+ = High confidence (clear item, readable text)
• 0.7-0.89 = Medium confidence (some ambiguity or text partially obscured)
• <0.7 = Low confidence (cluttered image, unclear item boundaries)

Output Format (Extended)

{
  "items": [
    {
      "Item": "[size] type vendor connector partnumber",
      "Type": "type",
      "Description": "technical details (max 5 words)",
      "Category": "category",
      "Connector": "connector_type",
      "Size": "human_readable_size",
      "Color": "color",
      "PartNr": "part_number",
      "OCR": "TYPE SIZE VENDOR CONNECTOR PARTNUMBER",
      "image_processing": {
        "crop_bounds": {
          "x": 50,
          "y": 100,
          "width": 300,
          "height": 200
        },
        "rotation_degrees": 15,
        "confidence": 0.92
      }
    }
  ]
}

Return ONLY JSON. No markdown. No text.