Update app.py

app.py

@@ -1,63 +1,42 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from PIL import Image
+from transformers import pipeline, AutoModelForVision2Seq, AutoProcessor
+import torch
+
+# Load the OpenGVLab/InternVL-Chat-V1-5 model and processor
+processor = AutoProcessor.from_pretrained("OpenGVLab/InternVL-Chat-V1-5")
+model = AutoModelForVision2Seq.from_pretrained("OpenGVLab/InternVL-Chat-V1-5")
+
+# Load the Llama3 model for text processing
+llama_model = pipeline("text2text-generation", model="llama3")
+
+def process_image(image):
+    # Process the image to extract the recipe using OpenGVLab
+    inputs = processor(images=image, return_tensors="pt")
+    generated_ids = model.generate(**inputs)
+    extracted_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    return extracted_text
+
+def adjust_recipe(extracted_text, adjustment):
+    # Create the prompt for Llama3 to adjust the recipe
+    prompt = f"Here is a recipe: {extracted_text}. Please {adjustment} the recipe."
+    response = llama_model(prompt)
+    return response[0]['generated_text']
+
+def app(image, adjustment):
+    extracted_text = process_image(image)
+    adjusted_recipe = adjust_recipe(extracted_text, adjustment)
+    return adjusted_recipe
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=app,
+    inputs=[gr.inputs.Image(type="pil"), gr.inputs.Dropdown(["double", "halve"])],
+    outputs="text",
+    title="Recipe Adjuster",
+    description="Upload an image of a recipe, and this app will double or halve the recipe."
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()