Create app.py

app.py

@@ -0,0 +1,209 @@
+import base64
+import os
+from datetime import datetime
+from openai import OpenAI
+import gradio as gr
+import oci
+import io
+import re
+import tempfile
+from collections import Counter
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+
+# === OpenAI API Setup ===
+openai_api_key = os.environ.get("OPENAI_API_KEY")
+if not openai_api_key:
+    raise ValueError("OPENAI_API_KEY environment variable is not set.")
+
+client = OpenAI(api_key=openai_api_key)
+
+# === OCI Object Storage Setup ===
+oci_config = {
+    "user": os.environ.get("OCI_USER"),
+    "tenancy": os.environ.get("OCI_TENANCY"),
+    "fingerprint": os.environ.get("OCI_FINGERPRINT"),
+    "region": os.environ.get("OCI_REGION"),
+    "key_content": os.environ.get("OCI_PRIVATE_KEY")
+}
+
+namespace = os.environ.get("OCI_NAMESPACE")
+bucket_name = os.environ.get("OCI_BUCKET_NAME")
+
+try:
+    object_storage = oci.object_storage.ObjectStorageClient(oci_config)
+except Exception as e:
+    print("Failed to initialize OCI Object Storage client:", e)
+
+# === Prompts ===
+system_prompt = (
+    "You are a detail-oriented assistant that specializes in transcribing and polishing "
+    "handwritten notes from images. Your goal is to turn rough, casual, or handwritten "
+    "content into clean, structured, and professional-looking text that sounds like it "
+    "was written by a human—not an AI. You do not include icons, emojis, or suggest next "
+    "steps unless explicitly instructed."
+)
+
+user_prompt_template = (
+    "You will receive an image of handwritten notes. Transcribe the content accurately, "
+    "correcting any spelling or grammar issues. Then, organize it clearly with headings, "
+    "bullet points, and proper formatting. Maintain the original intent and voice of the "
+    "author, but enhance readability and flow. Do not add embellishments or AI-style phrasing."
+)
+
+# === Encode uploaded bytes ===
+def encode_image_to_base64(file_bytes):
+    return base64.b64encode(file_bytes).decode("utf-8")
+
+# === Upload transcription result to OCI ===
+def upload_to_object_storage(user_name, text):
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    filename = f"{user_name.replace(' ', '_')}_{timestamp}.txt"
+    object_storage.put_object(
+        namespace_name=namespace,
+        bucket_name=bucket_name,
+        object_name=filename,
+        put_object_body=text.encode("utf-8")
+    )
+    return filename
+
+# === List and Filter ===
+def list_object_store():
+    try:
+        objects = object_storage.list_objects(namespace, bucket_name)
+        return [obj.name for obj in objects.data.objects if obj.name.endswith(".txt")]
+    except Exception as e:
+        return [f"Failed to list objects: {str(e)}"]
+
+def filter_object_store(query):
+    return [name for name in list_object_store() if query.lower() in name.lower()]
+
+# === View file contents ===
+def view_transcription(file_name):
+    try:
+        response = object_storage.get_object(namespace, bucket_name, file_name)
+        return response.data.text
+    except Exception as e:
+        return f"Failed to load file: {str(e)}"
+
+# === Analyze content with OpenAI ===
+def summarize_selected_files(file_list):
+    combined_text = ""
+    for name in file_list:
+        combined_text += view_transcription(name) + "\n"
+    if not combined_text.strip():
+        return "No content found."
+    response = client.chat.completions.create(
+        model="gpt-4-turbo",
+        messages=[
+            {"role": "system", "content": "You are a summarization expert."},
+            {"role": "user", "content": "Please summarize the following transcriptions in detail:\n" + combined_text}
+        ],
+        max_tokens=1500
+    )
+    return response.choices[0].message.content
+
+def recommend_from_selected_files(file_list):
+    combined_text = ""
+    for name in file_list:
+        combined_text += view_transcription(name) + "\n"
+    if not combined_text.strip():
+        return "No content found."
+    response = client.chat.completions.create(
+        model="gpt-4-turbo",
+        messages=[
+            {"role": "system", "content": "You are an operations consultant."},
+            {"role": "user", "content": "Please recommend next steps based on these transcriptions:\n" + combined_text}
+        ],
+        max_tokens=1500
+    )
+    return response.choices[0].message.content
+
+# === Generate word cloud from selected files ===
+def generate_word_map_from_files(file_list):
+    combined_text = ""
+    for name in file_list:
+        combined_text += view_transcription(name) + "\n"
+    if not combined_text.strip():
+        return "No content found."
+
+    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(combined_text)
+    plt.figure(figsize=(10, 5))
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis("off")
+    buf = io.BytesIO()
+    plt.savefig(buf, format="png")
+    buf.seek(0)
+
+    # Upload image to object storage
+    filename = f"wordcloud_{datetime.now().strftime('%Y%m%d_%H%M%S')}.png"
+    object_storage.put_object(
+        namespace_name=namespace,
+        bucket_name=bucket_name,
+        object_name=filename,
+        put_object_body=buf.read()
+    )
+
+    buf.seek(0)
+    return gr.Image.update(value=buf)
+
+# === Transcription logic ===
+def transcribe_image(file_bytes, user_name):
+    if not file_bytes:
+        return "No image uploaded."
+    encoded = encode_image_to_base64(file_bytes)
+    image_url = f"data:image/jpeg;base64,{encoded}"
+    response = client.chat.completions.create(
+        model="gpt-4-turbo",
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": [
+                {"type": "text", "text": user_prompt_template},
+                {"type": "image_url", "image_url": {"url": image_url}}
+            ]}
+        ],
+        max_tokens=1500
+    )
+    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    result = f"🗓️ Transcribed on: {timestamp}\n\n{response.choices[0].message.content}"
+    upload_to_object_storage(user_name, result)
+    return result
+
+# === Gradio Interface ===
+with gr.Blocks() as app:
+    gr.Markdown("## Handwritten Note Transcriber & Analyzer")
+
+    with gr.Row():
+        user_dropdown = gr.Dropdown(
+            choices=["Jim Goodwin", "Zahabiya Ali rampurawala", "Keith Gauvin"],
+            label="Who is uploading this?"
+        )
+
+    input_file = gr.File(label="Upload image", type="binary", file_types=[".jpg", ".jpeg", ".png"])
+    output_text = gr.Textbox(label="Transcription Output", lines=30)
+    input_file.change(fn=transcribe_image, inputs=[input_file, user_dropdown], outputs=output_text)
+
+    gr.Markdown("### View Transcription")
+    search_box = gr.Textbox(label="Filter by uploader or keyword")
+    filtered_dropdown = gr.Dropdown(label="Select transcription file")
+    view_output = gr.Textbox(label="File Content")
+    search_box.change(fn=filter_object_store, inputs=search_box, outputs=filtered_dropdown)
+    filtered_dropdown.change(fn=view_transcription, inputs=filtered_dropdown, outputs=view_output)
+
+    gr.Markdown("### Summarize or Recommend")
+    file_multiselect = gr.Dropdown(choices=list_object_store(), label="Select files to analyze", multiselect=True)
+    summary_output = gr.Textbox(label="Summary")
+    rec_output = gr.Textbox(label="Recommendations")
+    gr.Button("Summarize Files").click(fn=summarize_selected_files, inputs=file_multiselect, outputs=summary_output)
+    gr.Button("Recommend from Files").click(fn=recommend_from_selected_files, inputs=file_multiselect, outputs=rec_output)
+
+    gr.Markdown("### Word Cloud from Files")
+    gr.Button("Generate Word Map from Files").click(
+        fn=generate_word_map_from_files,
+        inputs=file_multiselect,
+        outputs=gr.Image()
+    )
+
+# === Launch App ===
+if __name__ == "__main__":
+    app.launch(share=True)