Batch fixes 2

docs/content/Deploying/Docker-Deploying.mdx

@@ -48,7 +48,7 @@ The fastest way to try out DocsGPT is by using the public API endpoint. This req
     Navigate to the root directory of the DocsGPT repository in your terminal and run:
 
     ```bash
-    docker compose -f deployment/docker-compose.yaml up -d
+    docker compose --env-file .env -f deployment/docker-compose.yaml up -d
     ```
 
     The `-d` flag runs Docker Compose in detached mode (in the background).

docs/content/Deploying/DocsGPT-Settings.mdx

@@ -222,7 +222,7 @@ for the engines and flows.
 | `OCR_DEEPSEEK_MODEL` | `deepseek-ocr:3b` | Model name at that endpoint. |
 | `OCR_DEEPSEEK_TIMEOUT` | `300` | Seconds allowed per page request to the DeepSeek endpoint, on both backends (the native backend sends pages one at a time). |
 | `OCR_RENDER_DPI` | `200` | Native backend: resolution at which pages without a text layer are rendered before OCR (clamped to 72-600). |
-| `OCR_MIN_CHARS_PER_PAGE` | `20` | Chars-per-page floor below which an OCR'd parse is treated as an OCR dropout and fails loudly instead of indexing an empty document; `0` disables. Alias: `DOCLING_OCR_MIN_CHARS_PER_PAGE`. |
+| `OCR_MIN_CHARS_PER_PAGE` | `20` | Chars-per-page floor for the OCR dropout guard: a multi-page parse whose OCR returns nothing fails loudly instead of indexing an empty document (docling retries once on full-page OCR first); output below the floor but non-empty is indexed with a warning. `0` disables. Alias: `DOCLING_OCR_MIN_CHARS_PER_PAGE`. |
 
 ## Speech-to-Text Settings