Update server/README.md

Author: cchadowitz

tools/server/README.md

@@ -172,6 +172,8 @@ The project is under active development, and we are [looking for feedback and co
 | `--host HOST` | ip address to listen, or bind to an UNIX socket if the address ends with .sock (default: 127.0.0.1)<br/>(env: LLAMA_ARG_HOST) |
 | `--port PORT` | port to listen (default: 8080)<br/>(env: LLAMA_ARG_PORT) |
 | `--path PATH` | path to serve static files from (default: )<br/>(env: LLAMA_ARG_STATIC_PATH) |
+| `--allowed-local-media-path PATH` | path from which local media files are allowed to be read from (default: none)<br/>(env: LLAMA_ARG_ALLOWED_LOCAL_MEDIA_PATH) |
+| `--local-media-max-size-mb N` | max size in mb for local media files (default: 15)<br/>(env: LLAMA_ARG_LOCAL_MEDIA_MAX_SIZE_MB) |
 | `--api-prefix PREFIX` | prefix path the server serves from, without the trailing slash (default: )<br/>(env: LLAMA_ARG_API_PREFIX) |
 | `--no-webui` | Disable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_NO_WEBUI) |
 | `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
@@ -1213,6 +1215,8 @@ Given a ChatML-formatted json description in `messages`, it returns the predicte
 
 If model supports multimodal, you can input the media file via `image_url` content part. We support both base64 and remote URL as input. See OAI documentation for more.
 
+We also support local files as input (e.g. `file://`) if enabled (see `--allowed-local-media-path` and `--local-media-max-size-mb` for details).
+
 *Options:*
 
 See [OpenAI Chat Completions API documentation](https://platform.openai.com/docs/api-reference/chat). llama.cpp `/completion`-specific features such as `mirostat` are also supported.