fix upload error

app.py

@@ -111,18 +111,30 @@ def gradio_reset(chat_state, img_list):
         img_list = []
     return None, gr.update(value=None, interactive=True), gr.update(value=None, interactive=True), gr.update(placeholder='Please upload your video first', interactive=False),gr.update(value="Upload & Start Chat", interactive=True), chat_state, img_list
 
-def upload_imgorvideo(gr_video, text_input, chat_state,chatbot):
+def upload_imgorvideo(gr_video, gr_img, text_input, chat_state,chatbot):
     if args.model_type == 'vicuna':
         chat_state = default_conversation.copy()
     else:
         chat_state = conv_llava_llama_2.copy()
-    
-    print(gr_video)
-    chatbot = chatbot + [((gr_video,), None)]
-    chat_state.system =  "You are able to understand the visual content that the user provides. Follow the instructions carefully and explain your answers in detail."
-    img_list = []
-    llm_message = chat.upload_video_without_audio(gr_video, chat_state, img_list)
-    return gr.update(interactive=False), gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list,chatbot
+    if gr_img is None and gr_video is None:
+        return None, None, None, gr.update(interactive=True), chat_state, None
+    elif gr_img is not None and gr_video is None:
+        print(gr_img)
+        chatbot = chatbot + [((gr_img,), None)]
+        chat_state.system =  "You are able to understand the visual content that the user provides. Follow the instructions carefully and explain your answers in detail."
+        img_list = []
+        llm_message = chat.upload_img(gr_img, chat_state, img_list)
+        return gr.update(interactive=False), gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list,chatbot
+    elif gr_video is not None and gr_img is None:
+        print(gr_video)
+        chatbot = chatbot + [((gr_video,), None)]
+        chat_state.system =  "You are able to understand the visual content that the user provides. Follow the instructions carefully and explain your answers in detail."
+        img_list = []
+        llm_message = chat.upload_video_without_audio(gr_video, chat_state, img_list)
+        return gr.update(interactive=False), gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list,chatbot
+    else:
+        # img_list = []
+        return gr.update(interactive=False), gr.update(interactive=False, placeholder='Currently, only one input is supported'), gr.update(value="Currently, only one input is supported", interactive=False), chat_state, None,chatbot
 
 def gradio_ask(user_message, chatbot, chat_state):
     if len(user_message) == 0:
@@ -185,7 +197,7 @@ with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column(scale=0.5):
             video = gr.Video()
-            #image = gr.Image(type="filepath")
+            image = gr.Image(type="filepath")
             #gr.Markdown(case_note_upload)
 
             upload_button = gr.Button(value="Upload & Start Chat", interactive=True, variant="primary")
@@ -226,8 +238,9 @@ with gr.Blocks() as demo:
         ], inputs=[video, text_input])'''
         
     gr.Markdown(cite_markdown)
-    upload_button.click(upload_imgorvideo, [video, text_input, chat_state,chatbot], [video, text_input, upload_button, chat_state, img_list,chatbot])
-    
+    #upload_button.click(upload_imgorvideo, [video, text_input, chat_state,chatbot], [video, text_input, upload_button, chat_state, img_list,chatbot])
+    upload_button.click(upload_imgorvideo, [video, image, text_input, chat_state,chatbot], [video, image, text_input, upload_button, chat_state, img_list,chatbot])
+
     text_input.submit(gradio_ask, [text_input, chatbot, chat_state], [text_input, chatbot, chat_state]).then(
         gradio_answer, [chatbot, chat_state, img_list, num_beams, temperature], [chatbot, chat_state, img_list]
     )

global_local/models/video_instruction_ft_model.py

@@ -127,6 +127,7 @@ class VideoInstructionFTLLAMA(Blip2Base):
 
         logging.info('Loading LLAMA Tokenizer')
         self.llama_tokenizer = LlamaTokenizer.from_pretrained(llama_model, use_fast=False, token=os.environ['LLAMA_TOKEN'])
+        #self.llama_tokenizer = LlamaTokenizer.from_pretrained(llama_model, use_fast=False)
         if self.llama_tokenizer.pad_token is None:
             self.llama_tokenizer.pad_token = self.llama_tokenizer.unk_token 
         DEFAULT_IMAGE_PATCH_TOKEN = '<ImageHere>'