Document bring-your-own-OCR support (0.7.0)

README.md

@@ -29,9 +29,9 @@ in your browser.
 pip install eka-pii-redaction
 ```
 
-System dependency: **Tesseract OCR** — required for the **image** modality
-(it OCRs the document before classifying words); not needed for the
-text-only modality.
+System dependency: **Tesseract OCR** — used by the **image** modality's
+built-in OCR step. Not needed for the text-only modality, nor if you bring
+your own OCR (`detect(..., words=..., boxes=...)`).
 
 ```bash
 # Debian/Ubuntu
@@ -62,6 +62,11 @@ entities = redactor.detect("page.jpg")   # list[PIIEntity] — the core call
 for e in entities:
     print(e.kind, e.category, e.bbox, e.text, e.score)
 
+# Bring your own OCR (skips the built-in Tesseract step; your pixel-space
+# word boxes pass through to the emitted entities):
+entities = redactor.detect("page.jpg", words=["John", "Doe"],
+                           boxes=[[100, 20, 140, 40], [145, 20, 180, 40]])
+
 # One detection, three possible outputs:
 redactor.redact("page.jpg", entities).save("redacted.png")
 redactor.anonymize("page.jpg", entities).save("anonymized.png")