chore(deps): bump transformers in /backend/python/coqui

Bumps [transformers](https://github.com/huggingface/transformers) from 4.48.3 to 5.10.2.
- [Release notes](https://github.com/huggingface/transformers/releases)
- [Commits](https://github.com/huggingface/transformers/compare/v4.48.3...v5.10.2)

---
updated-dependencies:
- dependency-name: transformers
  dependency-version: 5.10.2
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=28ca1e600c5dac1854fb7e09611914013430b037
+LLAMA_VERSION?=9e3b928fd8c9d14dbf15a8768b9fdd7e5c721d66
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -381,15 +381,6 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, const
             });
     }
 
-    // for each video in the request, add the video data
-    for (int i = 0; i < predict->videos_size(); i++) {
-        data["video_data"].push_back(json
-            {
-                {"id", i},
-                {"data",    predict->videos(i)},
-            });
-    }
-
     data["stop"] = predict->stopprompts();
     // data["n_probs"] = predict->nprobs();
     //TODO: images,
@@ -1512,7 +1503,7 @@ public:
                     msg_json["role"] = msg.role();
 
                     bool is_last_user_msg = (i == last_user_msg_idx);
-                    bool has_images_or_audio = (request->images_size() > 0 || request->audios_size() > 0 || request->videos_size() > 0);
+                    bool has_images_or_audio = (request->images_size() > 0 || request->audios_size() > 0);
 
                     // Handle content - can be string, null, or array
                     // For multimodal content, we'll embed images/audio from separate fields
@@ -1563,16 +1554,6 @@ public:
                                     content_array.push_back(audio_chunk);
                                 }
                             }
-                            if (request->videos_size() > 0) {
-                                for (int j = 0; j < request->videos_size(); j++) {
-                                    json video_chunk;
-                                    video_chunk["type"] = "input_video";
-                                    json input_video;
-                                    input_video["data"] = request->videos(j);
-                                    video_chunk["input_video"] = input_video;
-                                    content_array.push_back(video_chunk);
-                                }
-                            }
                             msg_json["content"] = content_array;
                         } else {
                             // Use content as-is (already array or not last user message)
@@ -1607,16 +1588,6 @@ public:
                                 content_array.push_back(audio_chunk);
                             }
                         }
-                        if (request->videos_size() > 0) {
-                            for (int j = 0; j < request->videos_size(); j++) {
-                                json video_chunk;
-                                video_chunk["type"] = "input_video";
-                                json input_video;
-                                input_video["data"] = request->videos(j);
-                                video_chunk["input_video"] = input_video;
-                                content_array.push_back(video_chunk);
-                            }
-                        }
                         msg_json["content"] = content_array;
                     } else if (msg.role() == "tool") {
                         // Tool role messages must have content field set, even if empty
@@ -2068,16 +2039,6 @@ public:
                         files.push_back(decoded_data);
                     }
                 }
-
-                const auto &video_data = data.find("video_data");
-                if (video_data != data.end() && video_data->is_array())
-                {
-                    for (const auto &video : *video_data)
-                    {
-                        auto decoded_data = base64_decode(video["data"].get<std::string>());
-                        files.push_back(decoded_data);
-                    }
-                }
             }
 
             const bool has_mtmd = ctx_server.impl->mctx != nullptr;
@@ -2330,7 +2291,7 @@ public:
                     }
 
                     bool is_last_user_msg = (i == last_user_msg_idx);
-                    bool has_images_or_audio = (request->images_size() > 0 || request->audios_size() > 0 || request->videos_size() > 0);
+                    bool has_images_or_audio = (request->images_size() > 0 || request->audios_size() > 0);
 
                     // Handle content - can be string, null, or array
                     // For multimodal content, we'll embed images/audio from separate fields
@@ -2383,16 +2344,6 @@ public:
                                     content_array.push_back(audio_chunk);
                                 }
                             }
-                            if (request->videos_size() > 0) {
-                                for (int j = 0; j < request->videos_size(); j++) {
-                                    json video_chunk;
-                                    video_chunk["type"] = "input_video";
-                                    json input_video;
-                                    input_video["data"] = request->videos(j);
-                                    video_chunk["input_video"] = input_video;
-                                    content_array.push_back(video_chunk);
-                                }
-                            }
                             msg_json["content"] = content_array;
                         } else {
                             // Use content as-is (already array or not last user message)
@@ -2432,16 +2383,6 @@ public:
                                 content_array.push_back(audio_chunk);
                             }
                         }
-                        if (request->videos_size() > 0) {
-                            for (int j = 0; j < request->videos_size(); j++) {
-                                json video_chunk;
-                                video_chunk["type"] = "input_video";
-                                json input_video;
-                                input_video["data"] = request->videos(j);
-                                video_chunk["input_video"] = input_video;
-                                content_array.push_back(video_chunk);
-                            }
-                        }
                         msg_json["content"] = content_array;
                         SRV_INF("[CONTENT DEBUG] Predict: Message %d created content array with media\n", i);
                     } else if (!msg.tool_calls().empty()) {
@@ -2904,16 +2845,6 @@ public:
                         files.push_back(decoded_data);
                     }
                 }
-
-                const auto &video_data = data.find("video_data");
-                if (video_data != data.end() && video_data->is_array())
-                {
-                    for (const auto &video : *video_data)
-                    {
-                        auto decoded_data = base64_decode(video["data"].get<std::string>());
-                        files.push_back(decoded_data);
-                    }
-                }
             }
 
             // process files

backend/python/coqui/requirements-cpu.txt

@@ -1,5 +1,5 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-transformers==4.48.3
+transformers==5.10.2
 accelerate
 torch==2.4.1
 torchaudio==2.4.1

backend/python/coqui/requirements-cublas12.txt

@@ -1,5 +1,5 @@
 torch==2.4.1
 torchaudio==2.4.1
-transformers==4.48.3
+transformers==5.10.2
 accelerate
 coqui-tts

backend/python/coqui/requirements-hipblas.txt

@@ -1,6 +1,6 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
 torch==2.10.0+rocm7.0
 torchaudio==2.10.0+rocm7.0
-transformers==4.48.3
+transformers==5.10.2
 accelerate
 coqui-tts

backend/python/coqui/requirements-intel.txt

@@ -3,6 +3,6 @@ torch==2.8.0+xpu
 torchaudio==2.8.0+xpu
 optimum[openvino]
 setuptools
-transformers==4.48.3
+transformers==5.10.2
 accelerate
 coqui-tts

backend/python/coqui/requirements-mps.txt

@@ -1,4 +1,4 @@
 torch==2.7.1
-transformers==4.48.3
+transformers==5.10.2
 accelerate
 coqui-tts

core/http/react-ui/src/hooks/useChat.js

@@ -216,12 +216,6 @@ export function useChat(initialModel = '') {
             audio_url: { url: `data:${file.type};base64,${file.base64}` },
           })
           userFiles.push({ name: file.name, type: 'audio' })
-        } else if (file.type?.startsWith('video/')) {
-          messageContent.push({
-            type: 'video_url',
-            video_url: { url: `data:${file.type};base64,${file.base64}` },
-          })
-          userFiles.push({ name: file.name, type: 'video' })
         } else {
 			// Text/PDF files - append to content
 			if (file.textContent) {

core/http/react-ui/src/pages/Chat.jsx

@@ -265,7 +265,7 @@ function UserMessageContent({ content, files }) {
         <div className="chat-message-files">
           {files.map((f, i) => (
             <span key={i} className="chat-file-inline">
-              <i className={`fas ${f.type === 'image' ? 'fa-image' : f.type === 'audio' ? 'fa-headphones' : f.type === 'video' ? 'fa-film' : 'fa-file'}`} />
+              <i className={`fas ${f.type === 'image' ? 'fa-image' : f.type === 'audio' ? 'fa-headphones' : 'fa-file'}`} />
               {f.name}
             </span>
           ))}
@@ -274,9 +274,6 @@ function UserMessageContent({ content, files }) {
       {Array.isArray(content) && content.filter(c => c.type === 'image_url').map((img, i) => (
         <img key={i} src={img.image_url.url} alt="attached" className="chat-inline-image" />
       ))}
-      {Array.isArray(content) && content.filter(c => c.type === 'video_url').map((vid, i) => (
-        <video key={i} src={vid.video_url.url} controls className="chat-inline-video" />
-      ))}
     </>
   )
 }
@@ -714,7 +711,7 @@ export default function Chat() {
     for (const file of e.target.files) {
       const base64 = await fileToBase64(file)
       const entry = { name: file.name, type: file.type, base64 }
-      if (!file.type.startsWith('image/') && !file.type.startsWith('audio/') && !file.type.startsWith('video/')) {
+      if (!file.type.startsWith('image/') && !file.type.startsWith('audio/')) {
         entry.textContent = await file.text().catch(() => '')
       }
       newFiles.push(entry)
@@ -1247,7 +1244,7 @@ export default function Chat() {
           <div className="chat-files">
             {files.map((f, i) => (
               <span key={i} className="chat-file-badge">
-                <i className={`fas ${f.type?.startsWith('image/') ? 'fa-image' : f.type?.startsWith('audio/') ? 'fa-headphones' : f.type?.startsWith('video/') ? 'fa-film' : 'fa-file'}`} />
+                <i className={`fas ${f.type?.startsWith('image/') ? 'fa-image' : f.type?.startsWith('audio/') ? 'fa-headphones' : 'fa-file'}`} />
                 {f.name}
                 <button onClick={() => setFiles(prev => prev.filter((_, idx) => idx !== i))}>
                   <i className="fas fa-xmark" />
@@ -1346,7 +1343,7 @@ export default function Chat() {
               ref={fileInputRef}
               type="file"
               multiple
-              accept="image/*,audio/*,video/*,application/pdf,.txt,.md,.csv,.json"
+              accept="image/*,audio/*,application/pdf,.txt,.md,.csv,.json"
               style={{ display: 'none' }}
               onChange={handleFileChange}
             />