Update app.py

app.py

@@ -17,24 +17,6 @@ llm_models = [
     "meta-llama/Meta-Llama-3-8B-Instruct",
     "mistralai/Mistral-7B-Instruct-v0.2",
     "tiiuae/falcon-7b-instruct",
-    # "mistralai/Mixtral-8x22B-Instruct-v0.1",    ## 281GB>10GB
-    # "NousResearch/Yarn-Mistral-7b-64k",  ## 14GB>10GB
-    # "impira/layoutlm-document-qa",  ## ERR
-    # "Qwen/Qwen1.5-7B",      ## 15GB
-    # "Qwen/Qwen2.5-3B",      ## high response time
-    # "google/gemma-2-2b-jpn-it",   ## high response time
-    # "impira/layoutlm-invoices",   ## bad req
-    # "google/pix2struct-docvqa-large",  ## bad req
-    # "google/gemma-7b-it", ## 17GB > 10GB
-    # "google/gemma-2b-it",  ## high response time
-    # "HuggingFaceH4/zephyr-7b-beta",   ## high response time
-    # "HuggingFaceH4/zephyr-7b-gemma-v0.1",     ## bad req
-    # "microsoft/phi-2",    ## high response time
-    # "TinyLlama/TinyLlama-1.1B-Chat-v1.0",     ## high response time
-    # "mosaicml/mpt-7b-instruct",     ## 13GB>10GB
-    # "google/flan-t5-xxl" ## high respons time
-    # "NousResearch/Yarn-Mistral-7b-128k",  ## 14GB>10GB
-    # "Qwen/Qwen2.5-7B-Instruct",     ## 15GB>10GB
 ]
 
 embed_models = [
@@ -61,18 +43,12 @@ file_extractor = {
     '.xlsx': parser,  # Microsoft Excel files (requires additional processing for tables)
     '.pptx': parser,  # Microsoft PowerPoint files (for slides)
     '.html': parser,  # HTML files (web pages)
-    # '.rtf': parser,  # Rich Text Format files
-    # '.odt': parser,  # OpenDocument Text files
-    # '.epub': parser,  # ePub files (e-books)
 
     # Image files for OCR processing
     '.jpg': parser,  # JPEG images
     '.jpeg': parser,  # JPEG images
     '.png': parser,  # PNG images
-    # '.bmp': parser,  # Bitmap images
-    # '.tiff': parser,  # TIFF images
-    # '.tif': parser,  # TIFF images (alternative extension)
-    # '.gif': parser,  # GIF images (can contain text)
+
 
     # Scanned documents in image formats
     '.webp': parser,  # WebP images
@@ -132,20 +108,15 @@ def encode_image(image_path):
     with open(image_path, "rb") as image_file:
         return base64.b64encode(image_file.read()).decode('utf-8')
 
-# Encode the images
-github_logo_encoded = encode_image("Images/github-logo.png")
-linkedin_logo_encoded = encode_image("Images/linkedin-logo.png")
-website_logo_encoded = encode_image("Images/ai-logo.png")
-
 # UI Setup
 with gr.Blocks(theme=gr.themes.Soft(font=[gr.themes.GoogleFont("Roboto Mono")]), css='footer {visibility: hidden}') as demo:
-    gr.Markdown("# DocBot📄🤖")
+    gr.Markdown("# HundAI QA📄")
     with gr.Tabs():
-        with gr.TabItem("Intro"):
+        with gr.TabItem("Introduction"):
             gr.Markdown(md.description)
 
-        with gr.TabItem("DocBot"):
-            with gr.Accordion("=== IMPORTANT: READ ME FIRST ===", open=False):
+        with gr.TabItem("Chatbot"):
+            with gr.Accordion("IMPORTANT: READ ME FIRST", open=False):
                 guid = gr.Markdown(md.guide)
             with gr.Row():
                 with gr.Column(scale=1):
@@ -164,7 +135,7 @@ with gr.Blocks(theme=gr.themes.Soft(font=[gr.themes.GoogleFont("Roboto Mono")]),
                         theme = "soft",
                         show_progress='full',
                         # cache_mode='lazy',
-                        textbox=gr.Textbox(placeholder="Step-4: Ask me questions on the uploaded document!", container=False)
+                        textbox=gr.Textbox(placeholder="Ask me any questions on the uploaded document!", container=False)
                     )
     gr.HTML(md.footer.format(github_logo_encoded, linkedin_logo_encoded, website_logo_encoded))
     # Set up Gradio interactions