mtmd_default_marker()

Author: ngxson

tools/mtmd/mtmd-cli.cpp

@@ -283,8 +283,8 @@ int main(int argc, char ** argv) {
 
     if (is_single_turn) {
         g_is_generating = true;
-        if (params.prompt.find(MTMD_DEFAULT_MEDIA_MARKER) == std::string::npos) {
-            params.prompt += MTMD_DEFAULT_MEDIA_MARKER;
+        if (params.prompt.find(mtmd_default_marker()) == std::string::npos) {
+            params.prompt += mtmd_default_marker();
         }
         common_chat_msg msg;
         msg.role = "user";
@@ -348,7 +348,7 @@ int main(int argc, char ** argv) {
                 std::string media_path = line.substr(7);
                 if (ctx.load_media(media_path)) {
                     LOG("%s %s loaded\n", media_path.c_str(), is_image ? "image" : "audio");
-                    content += MTMD_DEFAULT_MEDIA_MARKER;
+                    content += mtmd_default_marker();
                 }
                 // else, error is already printed by libmtmd
                 continue;

tools/mtmd/mtmd.cpp

@@ -79,14 +79,18 @@ enum mtmd_slice_tmpl {
     // TODO @ngxson : add support for idefics (SmolVLM)
 };
 
+const char * mtmd_default_marker() {
+    return "<__media__>";
+}
+
 mtmd_context_params mtmd_context_params_default() {
     mtmd_context_params params;
     params.use_gpu = true;
     params.print_timings = true;
     params.n_threads = 4;
     params.verbosity = GGML_LOG_LEVEL_INFO;
     params.image_marker = MTMD_DEFAULT_IMAGE_MARKER;
-    params.media_marker = MTMD_DEFAULT_MEDIA_MARKER;
+    params.media_marker = mtmd_default_marker();
     return params;
 }
 

tools/mtmd/mtmd.h

@@ -39,9 +39,7 @@
 #    define MTMD_API
 #endif
 
-#define MTMD_DEFAULT_MEDIA_MARKER "<__media__>"
-
-// deprecated marker, use MTMD_DEFAULT_MEDIA_MARKER instead
+// deprecated marker, use mtmd_default_marker() instead
 #define MTMD_DEFAULT_IMAGE_MARKER "<__image__>"
 
 #ifdef __cplusplus
@@ -87,6 +85,8 @@ struct mtmd_context_params {
     const char * media_marker;
 };
 
+MTMD_API const char * mtmd_default_marker(void);
+
 MTMD_API struct mtmd_context_params mtmd_context_params_default(void);
 
 // initialize the mtmd context
@@ -172,7 +172,7 @@ MTMD_API llama_pos    mtmd_image_tokens_get_n_pos   (const mtmd_image_tokens * i
 
 // tokenize an input text prompt and a list of bitmaps (images/audio)
 // the prompt must have the input image marker (default: "<__media__>") in it
-// the default marker is defined by MTMD_DEFAULT_MEDIA_MARKER
+// the default marker is defined by mtmd_default_marker()
 // the marker will be replaced with the image/audio chunk
 // for example:
 //   "here is an image: <__media__>\ndescribe it in detail."

tools/server/utils.hpp

@@ -710,7 +710,7 @@ static json oaicompat_completion_params_parse(
 
                 // replace this chunk with a marker
                 p["type"] = "text";
-                p["text"] = MTMD_DEFAULT_MEDIA_MARKER;
+                p["text"] = mtmd_default_marker();
                 p.erase("image_url");
             }
         }