Update app.py

app.py

@@ -1,31 +1,27 @@
-import gradio as gr
-from texify.inference import batch_inference
-from texify.model.model import load_model
-from texify.model.processor import load_processor
-from PIL import Image
-
-title="""# 🙋🏻‍♂️Welcome to🌟Tonic's👨🏻‍🔬Texify"""
-description="""You can upload a picture with a math formula and this model will return latex formulas. Texify is a multimodal input model. You can use this Space to test out the current model [vikp/texify2](https://huggingface.co/vikp/texify2) You can also use  vikp/texify2🚀 by cloning this space.   Simply click here: [Duplicate Space](https://huggingface.co/spaces/Tonic1/texify?duplicate=true)
-Join us:  TeamTonic  is always making cool demos! Join our active builder's community on  Discord: [Discord](https://discord.gg/nXx5wbX9) On  Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On  Github: [Polytonic](https://github.com/tonic-ai) & contribute to   [PolyGPT](https://github.com/tonic-ai/polygpt-alpha) You can also join the [texify community here](https://discord.gg/zJSDQJWDe8). Big thanks to Vik Paruchuri for the invite and Huggingface for the Community Grant. Your special attentions are much appreciated.
-"""
+from transformers import pipeline
 
+pipeline = pipeline(
+    "text-generation",
+    model="Nexusflow/NexusRaven-V2-13B",
+    torch_dtype="auto",
+    device_map="auto",
+)
 
-model = load_model()
-processor = load_processor()
+title="""# 🙋🏻‍♂️Welcome to🌟Tonic's🐦‍⬛NexusRaven"""
+description="""this model is used to select and return function calling arguments.
+"""
 
-def process_image(img):
-#   img = Image.fromarray(img)
-    
-    results = batch_inference([img], model, processor)
+prompt = prompt_template.format(query="What's the weather like in Seattle right now?")
 
-    return '\n'.join(results) if isinstance(results, list) else results
+result = pipeline(prompt, max_new_tokens=2048, return_full_text=False, do_sample=False, temperature=0.001)[0]["generated_text"]
+print (result)
 
 with gr.Blocks() as app:
     gr.Markdown(title)
     gr.Markdown(description)
     with gr.Row():
         with gr.Column():
-            image_input = gr.Image(type="pil")
+            input = gr.Textbox()
         with gr.Column():
             output = gr.Textbox()
     image_input.change(process_image, inputs=image_input, outputs=output)