chore: update Marketing v2

app.py

@@ -32,8 +32,10 @@ time.sleep(3)
 # Load data from files required for the application
 UUID_MAP = read_json(MAPPING_UUID_PATH)
 ANONYMIZED_DOCUMENT = read_txt(ANONYMIZED_FILE_PATH)
-MAPPING_SENTENCES = read_pickle(MAPPING_SENTENCES_PATH)
+MAPPING_ANONYMIZED_SENTENCES = read_pickle(MAPPING_ANONYMIZED_SENTENCES_PATH)
+MAPPING_ENCRYPTED_SENTENCES = read_pickle(MAPPING_ENCRYPTED_SENTENCES_PATH)
 ORIGINAL_DOCUMENT = read_txt(ORIGINAL_FILE_PATH).split("\n\n")
+print(ORIGINAL_DOCUMENT)
 
 # 4. Data Processing and Operations (No specific operations shown here, assuming it's part of anonymizer or client usage)
 
@@ -44,9 +46,9 @@ ORIGINAL_DOCUMENT = read_txt(ORIGINAL_FILE_PATH).split("\n\n")
 USER_ID = numpy.random.randint(0, 2**32)
 
 
-def select_static_sentences_fn(selected_sentences: List):
+def select_static_anonymized_sentences_fn(selected_sentences: List):
 
-    selected_sentences = [MAPPING_SENTENCES[sentence] for sentence in selected_sentences]
+    selected_sentences = [MAPPING_ANONYMIZED_SENTENCES[sentence] for sentence in selected_sentences]
 
     anonymized_selected_sentence = sorted(selected_sentences, key=lambda x: x[0])
 
@@ -90,6 +92,16 @@ def key_gen_fn() -> Dict:
         print("Keys have been generated ✅")
         return {gen_key_btn: gr.update(value="Keys have been generated ✅")}
 
+def select_static_encrypted_sentences_fn(selected_sentences: List):
+
+    selected_sentences = [MAPPING_ENCRYPTED_SENTENCES[sentence] for sentence in selected_sentences]
+
+    anonymized_selected_sentence = sorted(selected_sentences, key=lambda x: x[0])
+
+    anonymized_selected_sentence = [sentence for _, sentence in anonymized_selected_sentence]
+
+    return {encrypted_doc_box: gr.update(value="\n\n".join(anonymized_selected_sentence))}
+
 
 def encrypt_query_fn(query):
 
@@ -141,10 +153,10 @@ def encrypt_query_fn(query):
         KEYS_DIR / f"{USER_ID}/encrypted_input_len", len(encrypted_tokens[0]).to_bytes(10, "big")
     )
 
-    encrypted_quant_tokens_hex = [token.hex()[500:675] for token in encrypted_tokens]
+    encrypted_quant_tokens_hex = [token.hex()[500:580] for token in encrypted_tokens]
 
     return {
-        output_encrypted_box: gr.update(value=" ".join(encrypted_quant_tokens_hex)),
+        output_encrypted_box: gr.update(value=" ".join(encrypted_quant_tokens_hex), lines=4),
         anonymized_text_output: gr.update(visible=True, value=None),
         identified_words_output_df: gr.update(visible=False, value=None),
     }
@@ -510,28 +522,26 @@ with demo:
     )
 
     with gr.Row():
-        with gr.Column():
-            gr.Markdown("**Original document:**")
-
-        with gr.Column():
-            gr.Markdown("**Encrypted document:**")
-
-
-    with gr.Row():
-        with gr.Column():
+        with gr.Column(scale=5):
             original_sentences_box = gr.CheckboxGroup(
                 ORIGINAL_DOCUMENT,
                 value=ORIGINAL_DOCUMENT,
-                show_label=False,
+                label="Contract:",
+                show_label=True,
             )
 
-        with gr.Column():
+        with gr.Column(scale=1, min_width=6):
+            gr.HTML("<div style='height: 77px;'></div>")
+            encrypt_doc_btn = gr.Button("Encrypt the document")
+
+        with gr.Column(scale=5):
             anonymized_doc_box = gr.Textbox(
-                show_label=False, value=ANONYMIZED_DOCUMENT, interactive=False, lines=11
+                label="Encrypted document:",
+                show_label=True, value=ANONYMIZED_DOCUMENT, interactive=False, lines=11
             )
 
     original_sentences_box.change(
-        fn=select_static_sentences_fn,
+        fn=select_static_anonymized_sentences_fn,
         inputs=[original_sentences_box],
         outputs=[anonymized_doc_box],
     )
@@ -541,12 +551,9 @@ with demo:
     gr.Markdown("<hr />")
     gr.Markdown("## Step 2.2: Select the prompt you want to encrypt\n\n"
         """Please choose from the predefined options in 
-        <span style='color:grey'>“Prompt examples”</span>" or craft a custom question in 
-        the <span style='color:grey'>“Customized prompt”</span>" text box.
-
-        Remain concise and relevant to the context. Any off-topic query will not be processed.
-        """
-    )
+        <span style='color:grey'>“Prompt examples”</span> or craft a custom question in 
+        the <span style='color:grey'>“Customized prompt”</span> text box.        
+        Remain concise and relevant to the context. Any off-topic query will not be processed.""")
 
     with gr.Row():
         with gr.Column(scale=5):
@@ -559,7 +566,7 @@ with demo:
             gr.Markdown("Or")
 
             query_box = gr.Textbox(
-                value="What is Alice international bank account number?", label="CUSTOMIZED PROMPT:", interactive=True
+                value="What is Kate international bank account number?", label="CUSTOMIZED PROMPT:", interactive=True
             )
 
             default_query_box.change(
@@ -592,9 +599,19 @@ with demo:
 
     run_fhe_btn = gr.Button("Anonymize using FHE")
 
-    anonymized_text_output = gr.Textbox(
-        label="Decrypted anonymized query that will be sent to ChatGPT:", lines=1, interactive=True
-    )
+    with gr.Row():
+        with gr.Column(scale=5):
+
+            anonymized_text_output = gr.Textbox(
+                label="Decrypted and anonymized document", lines=5, interactive=True
+            )
+
+        with gr.Column(scale=5):
+
+            anonymized_query_output = gr.Textbox(
+                label="Decrypted and anonymized prompt", lines=5, interactive=True
+            )
+
 
     identified_words_output_df = gr.Dataframe(label="Identified words:", visible=False)
 
@@ -618,7 +635,7 @@ with demo:
     ########################## ChatGpt Part ##########################
 
     gr.Markdown("<hr />")
-    gr.Markdown("## Spet 5: Secure your communication on ChatGPT with anonymized queries")
+    gr.Markdown("## Step 4: Send anonymized prompt to ChatGPT")
     gr.Markdown(
         """After securely anonymizing the query with FHE, 
         you can forward it to ChatGPT without having any concern about information leakage."""
@@ -627,9 +644,9 @@ with demo:
     chatgpt_button = gr.Button("Query ChatGPT")
 
     with gr.Row():
-        chatgpt_response_anonymized = gr.Textbox(label="ChatGPT's anonymized response:", lines=13)
+        chatgpt_response_anonymized = gr.Textbox(label="ChatGPT's anonymized response:", lines=5)
         chatgpt_response_deanonymized = gr.Textbox(
-            label="ChatGPT's non-anonymized response:", lines=13
+            label="ChatGPT's non-anonymized response:", lines=5
         )
 
     chatgpt_button.click(

files/anonymized_document.txt

@@ -1,10 +1,11 @@
-Hello, my name is ebe99761 53a9291d and I live in 6337f12f.
-My credit card number is e5b499b0 and my crypto wallet id is ac41d58b.
+Members: e3383f5b 70fc6ec5 and 2708cb61 cda521d5
 
-On September 18 I visited 0d574451 and sent an email to 1f78e797,  from the IP 116fe81e.
+Date: e381418b 3534158a, 96c403e5
 
-My passport: 59a83e41 and my phone number: 144a2acc d9e5704e.
+Scope: 2708cb61 agrees to provide graphic design services to e3383f5b for the creation of a company logo.
 
-This is a valid 71d0f51c Bank Account Number: 5ca977a4. Can you please check the status on bank account 9eb07461?
+Amount: Bob agrees to pay 2708cb61 500 upon completion and delivery of the logo.
 
-b474d794's social security number is d8da62f1.  Her driver license? it is 5e63c327.
+Deadline: The logo design must be completed and delivered to Bob within 14 days of the contract signing date.
+
+Payment terms: 2708cb61s international bank account N: 61294a43

files/encrypted_document.txt

@@ -0,0 +1,6 @@
+827c6bc946254b0ffe4695b4f0fc001f2383a4cf066b44312f9fa5a5733e6b6e097e69d08441b32ad93a3e84f95932e3142ce91a7502f5594eafdd6ccc2ad779e2e166ff0ac66e5e015ac64e5aac0979
+a2a7ebe458d32843738fe5e550642bfb2c7efeb0f3b65892c25c0ed4a329f90e62dd97a58f6c852d0a4f2e7bae863381a325b679761570df764a0f6aec3f01a23516f0cee88972e5ac324f6af45d8e7ee 
+2bb53d60fd24b7e24334179c30624dd49eea11c2210e2b63d2a5fc5ea20766be019c68e061cbbad75bdb3255b1428b1dd46d361ec0261dfcbc3081d1e43aaf1bfde51f81f9036e728c3931a9e3ff4b37 
+3b05e1c4a0adc1a82b3d471990b60990d7d4e66132ed15fc8a18a129432e4c73c2bb74ecc89be49571090b5de8934661928c1e153dd8746858aa8ece4d59452159147f8b54da923a9eb99d1c8006b389
+788027d896e0977b3012f6d50718153aac3b6642ad7e72383ecd9def3b8f4cc6c7e6851f4491eed1c5693b56dd9ac79f03fde97bf9ad0d3c6bc1c8f94e95901ceeb4a38893f2a189e63562b43a453c3a 
+426b376b438d9755946251b5da13f7585ab9557bec48f1e300c43cfa9e6f3f2bc1eef1a13d801161c8a59384914ffbd4da96b25dad84c51b77df73060a1319d72a2e5d4d7eea734ba72a1a6657aa93ba 

files/mapping_clear_to_anonymized.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944e5c32bd04e955194c513d35b91467615c08973c767745a1756d015b3e6ebb
-size 1085
+oid sha256:ce0f400a2f644ddf99bcbc76f856afc1ad79055b1f01133a69e7617d257de98c
+size 943

files/original_document.txt

@@ -1,10 +1,11 @@
-Hello, my name is David Johnson and I live in Maine.
-My credit card number is 4095-2609-9393-4932 and my crypto wallet id is 16Yeky6GMjeNkAiNcBY7ZhrLoMSgg1BoyZ.
+Members: David Johnson and Kate Hemingway
 
-On September 18 I visited microsoft.com and sent an email to test@presidio.site,  from the IP 192.168.0.1.
+Date: February 06, 2000
 
-My passport: 191280342 and my phone number: (212) 555-1234.
+Scope: Kate agrees to provide graphic design services to David for the creation of a company logo.
 
-This is a valid International Bank Account Number: IL150120690000003111111. Can you please check the status on bank account 954567876544?
+Amount: Bob agrees to pay Kate $500 upon completion and delivery of the logo.
 
-Kate's social security number is 078-05-1126.  Her driver license? it is 1234567A.
+Deadline: The logo design must be completed and delivered to Bob within 14 days of the contract signing date.
+
+Payment terms: Kate’s international bank account N°: IL150120690000003111111

files/original_document_uuid_mapping.json

@@ -1,19 +1,10 @@
 {
-    "078-05-1126": "d8da62f1",
-    "1234567A": "5e63c327",
-    "16Yeky6GMjeNkAiNcBY7ZhrLoMSgg1BoyZ": "ac41d58b",
-    "191280342": "59a83e41",
-    "192.168.0.1": "116fe81e",
-    "212": "144a2acc",
-    "4095-2609-9393-4932": "e5b499b0",
-    "555-1234": "d9e5704e",
-    "954567876544": "9eb07461",
-    "David": "ebe99761",
-    "IL150120690000003111111": "5ca977a4",
-    "International": "71d0f51c",
-    "Johnson": "53a9291d",
-    "Kate": "b474d794",
-    "Maine": "6337f12f",
-    "microsoft.com": "0d574451",
-    "test@presidio.site": "1f78e797"
+    "06": "3534158a",
+    "2000": "96c403e5",
+    "David": "e3383f5b",
+    "February": "e381418b",
+    "Hemingway": "cda521d5",
+    "IL150120690000003111111": "61294a43",
+    "Johnson": "70fc6ec5",
+    "Kate": "2708cb61"
 }

utils_demo.py

@@ -18,7 +18,7 @@ from pathlib import Path
 SERVER_URL = "http://localhost:8000/"
 
 # Maximum length for user queries
-MAX_USER_QUERY_LEN = 80
+MAX_USER_QUERY_LEN = 128
 
 # Base Directories
 CURRENT_DIR = Path(__file__).parent
@@ -38,15 +38,16 @@ LOGREG_MODEL_PATH = CURRENT_DIR / "models" / "cml_logreg.model"
 ORIGINAL_FILE_PATH = DATA_PATH / "original_document.txt"
 ANONYMIZED_FILE_PATH = DATA_PATH / "anonymized_document.txt"
 MAPPING_UUID_PATH = DATA_PATH / "original_document_uuid_mapping.json"
-MAPPING_SENTENCES_PATH = DATA_PATH / "mapping_clear_to_anonymized.pkl"
+MAPPING_ANONYMIZED_SENTENCES_PATH = DATA_PATH / "mapping_clear_to_anonymized.pkl"
+MAPPING_ENCRYPTED_SENTENCES_PATH = DATA_PATH / "mapping_clear_to_encrypted.pkl"
 PROMPT_PATH = DATA_PATH / "chatgpt_prompt.txt"
 
 
 # List of example queries for easy access
 DEFAULT_QUERIES = {
-    "Example Query 1": "Who visited microsoft.com?",
-    "Example Query 2": "Does Kate have a driving licence?",
-    "Example Query 3": "What's David Johnson's phone number?",
+    "Example Query 1": "What is the amount of the contract between David and Kate?",
+    "Example Query 2": "What's the duration of the contract?",
+    "Example Query 3": "Does Kate have an international bank account?",
 }
 
 # Load tokenizer and model