Add updated code

app.py

@@ -0,0 +1,87 @@
+# Standard library imports
+import os
+import re
+import io
+
+# External libraries for image processing and visualization
+from PIL import Image
+
+# Azure AI services
+from azure.core.credentials import AzureKeyCredential
+from azure.ai.formrecognizer import DocumentAnalysisClient
+
+# Gradio for creating interfaces
+import gradio as gr
+
+# Other libraries
+import numpy as np
+import openai
+
+# Azure Cognitive Services endpoint and key
+endpoint = "https://herbariumsamplerecognition.cognitiveservices.azure.com/"
+key = os.environ['KEY1']
+
+
+def sanitize_filename(filename):
+    # Remove characters that are not alphanumeric, spaces, dots, or underscores
+    return re.sub(r'[^\w\s\.-]', '', filename)
+
+def extract_info(text):
+    # Set your OpenAI API key
+    openai.api_key = os.environ['KEY2']
+
+    # Prepare the prompt for the API
+    prompt = f"From the provided text, return only the relevant information in a JSON format according to the Darwin Core standard for biodiversity specimen. Note: make sure that each output has a 'country' field. If you do not find an explicit country, make your best guess at the country using the context of the other text.\n{text}\n{text}"
+
+    try:
+        # Send the request to the API
+        response = openai.ChatCompletion.create(
+            model="gpt-4-1106-preview",
+            messages=[{"role": "system", "content": "You are a helpful assistant."}, 
+                      {"role": "user", "content": prompt}]
+        )
+
+        # Extract the response
+        return response.choices[0].message['content'] if response.choices else "No response from the API."
+
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+def analyze_read(image_stream):
+    try:
+        document_analysis_client = DocumentAnalysisClient(
+            endpoint=endpoint, credential=AzureKeyCredential(key)
+        )
+
+        poller = document_analysis_client.begin_analyze_document(
+            "prebuilt-read", image_stream)
+        result = poller.result()
+
+        # Collect the content from the document
+        document_content = result.content
+        extracted_info = extract_info(document_content)
+
+        return extracted_info
+
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+def model_function(image):
+    # Convert the NumPy array to a PIL Image object
+    image = Image.fromarray(np.uint8(image)).convert('RGB')
+
+    # Convert the uploaded image to a byte stream
+    image_bytes = io.BytesIO()
+    image.save(image_bytes, format='JPEG')  # Using 'JPEG' as the format
+    image_bytes = image_bytes.getvalue()
+
+    output_text = analyze_read(image_bytes)
+    return output_text
+
+title = "HerbariaOCR"
+description = "Upload your Herbaria specimen and let the Azure-GPT pipeline work its magic!\nYou will find all the textual data from the image extracted in the DarwinCore json format standard."
+article = "Check out [the GitHub repository](https://github.com/BU-Spark/HerbariaOCR) that this demo is based off of."
+
+iface = gr.Interface(fn=model_function,title=title,
+    description=description,article=article, inputs="image", outputs="text")
+iface.launch(share=True)

requirements.txt

@@ -0,0 +1,7 @@
+gradio==3.48.0
+pydantic==1.10.11
+typing-extensions
+pillow
+azure-ai-formrecognizer
+openai==0.28
+ipywidgets