Update app.py

app.py

@@ -97,11 +97,11 @@ def generate_image(model_name: str, text: str, image: Image.Image,
         processor = processor_o
         model = model_o
     else:
-        yield "Invalid model selected."
+        yield "Invalid model selected.", "Invalid model selected."
         return
 
     if image is None:
-        yield "Please upload an image."
+        yield "Please upload an image.", "Please upload an image."
         return
 
     messages = [{
@@ -127,9 +127,8 @@ def generate_image(model_name: str, text: str, image: Image.Image,
     buffer = ""
     for new_text in streamer:
         buffer += new_text
-        #buffer = buffer.replace("<|im_end|>", "")
         time.sleep(0.01)
-        yield buffer
+        yield buffer, buffer
 
 @spaces.GPU
 def generate_video(model_name: str, text: str, video_path: str,
@@ -151,11 +150,11 @@ def generate_video(model_name: str, text: str, video_path: str,
         processor = processor_o
         model = model_o
     else:
-        yield "Invalid model selected."
+        yield "Invalid model selected.", "Invalid model selected."
         return
 
     if video_path is None:
-        yield "Please upload a video."
+        yield "Please upload a video.", "Please upload a video."
         return
 
     frames = downsample_video(video_path)
@@ -194,7 +193,7 @@ def generate_video(model_name: str, text: str, video_path: str,
         buffer += new_text
         buffer = buffer.replace("<|im_end|>", "")
         time.sleep(0.01)
-        yield buffer
+        yield buffer, buffer
 
 # Define examples for image and video inference
 image_examples = [
@@ -202,7 +201,6 @@ image_examples = [
     ["Convert this page to doc [text] precisely.", "images/4.png"],
     ["Convert this page to doc [text] precisely.", "images/1.png"],
     ["Convert chart to OTSL.", "images/2.png"]
-
 ]
 
 video_examples = [
@@ -250,6 +248,7 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 repetition_penalty = gr.Slider(label="Repetition penalty", minimum=1.0, maximum=2.0, step=0.05, value=1.2)
         with gr.Column():
             output = gr.Textbox(label="Output", interactive=False, lines=2, scale=2)
+            markdown_output = gr.Markdown(label="Result.Md", scale=2)
             model_choice = gr.Radio(
                 choices=["DREX-062225-exp", "VIREX-062225-exp", "olmOCR-7B-0225"],
                 label="Select Model",
@@ -259,17 +258,17 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Doc-VLMs/discussions)")
             gr.Markdown("> [DREX-062225-exp](https://huggingface.co/prithivMLmods/DREX-062225-exp): the drex-062225-exp (document retrieval and extraction expert) model is a specialized fine-tuned version of docscopeocr-7b-050425-exp, optimized for document retrieval, content extraction, and analysis recognition. built on top of the qwen2.5-vl architecture.")
             gr.Markdown("> [VIREX-062225-exp](https://huggingface.co/prithivMLmods/VIREX-062225-exp): the virex-062225-exp (video information retrieval and extraction expert - experimental) model is a fine-tuned version of qwen2.5-vl-7b-instruct, specifically optimized for advanced video understanding, image comprehension, sense of reasoning, and natural language decision-making through cot reasoning.")
-            gr.Markdown("> [olmOCR-7B-0225](https://huggingface.co/allenai/olmOCR-7B-0225-preview): the olmocr-7b-0225-preview model is based on qwen2-vl-7b, optimized for document-level optical character recognition (ocr), long-context vision-language understanding, and accurate image-to-text conversion with mathematical latex formatting. designed with a focus on high-fidelity visual-textual comprehension.")             
+            gr.Markdown("> [olmOCR-7B-0225](https://huggingface.co/allenai/olmOCR-7B-0225-preview): the olmocr-7b-0225-preview model is based on qwen2-vl-7b, optimized for document-level optical character recognition (ocr), long-context vision-language understanding, and accurate image-to-text conversion with mathematical latex formatting. designed with a focus on high-fidelity visual-textual comprehension.")           
 
     image_submit.click(
         fn=generate_image,
         inputs=[model_choice, image_query, image_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],
-        outputs=output
+        outputs=[output, markdown_output]
     )
     video_submit.click(
         fn=generate_video,
         inputs=[model_choice, video_query, video_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],
-        outputs=output
+        outputs=[output, markdown_output]
     )
 
 if __name__ == "__main__":