Updates

app.py

@@ -4,7 +4,6 @@ import numpy as np
 import model2vec
 from reach import Reach
 from difflib import ndiff
-import time
 
 # Load the model at startup
 model = model2vec.StaticModel.from_pretrained("minishlab/M2V_base_output")
@@ -26,19 +25,7 @@ def batch_iterable(iterable, batch_size):
     for i in range(0, len(iterable), batch_size):
         yield iterable[i:i + batch_size]
 
-def log_time(message, start_time=None, logs=None):
-    """Helper function to log the start and end times."""
-    current_time = time.time()
-    if start_time is not None:
-        elapsed = current_time - start_time
-        log_message = f"{message} - Took {elapsed:.2f} seconds"
-    else:
-        log_message = f"{message} - Started"
-    
-    if logs is not None:
-        logs.append(log_message)
-
-def compute_embeddings(texts, batch_size, progress, logs, desc="Computing embeddings"):
+def compute_embeddings(texts, batch_size, progress, desc="Computing embeddings"):
     embeddings = []
     total_batches = (len(texts) + batch_size - 1) // batch_size
     for i, batch_texts in enumerate(batch_iterable(texts, batch_size)):
@@ -51,38 +38,26 @@ def deduplicate(
     embedding_matrix: np.ndarray,
     threshold: float,
     batch_size: int = 1024,
-    progress=None,
-    logs=None
+    progress=None
 ) -> tuple[np.ndarray, dict[int, int]]:
-    # Building the index
-    log_time("Building search index", logs=logs)
-    reach = Reach(
-        vectors=embedding_matrix, items=[str(i) for i in range(len(embedding_matrix))]
-    )
+    reach = Reach(vectors=embedding_matrix, items=[str(i) for i in range(len(embedding_matrix))])
 
     deduplicated_indices = set(range(len(embedding_matrix)))
     duplicate_to_original_mapping = {}
 
-    # Finding nearest neighbors
-    log_time("Finding nearest neighbors", logs=logs)
     results = reach.nearest_neighbor_threshold(
         embedding_matrix,
         threshold=threshold,
         batch_size=batch_size,
-        show_progressbar=False,  # Disable internal progress bar
+        show_progressbar=False,
     )
 
-    # Processing duplicates with a progress bar
     total_items = len(embedding_matrix)
-    log_time("Processing duplicates", logs=logs)
-    for i, similar_items in enumerate(
-        progress.tqdm(results, desc="Processing duplicates", total=total_items)
-    ):
+    for i, similar_items in enumerate(progress.tqdm(results, desc="Processing duplicates", total=total_items)):
         if i not in deduplicated_indices:
             continue
 
         similar_indices = [int(item[0]) for item in similar_items if int(item[0]) != i]
-
         for sim_idx in similar_indices:
             if sim_idx in deduplicated_indices:
                 deduplicated_indices.remove(sim_idx)
@@ -94,11 +69,6 @@ def display_word_differences(x: str, y: str) -> str:
     diff = ndiff(x.split(), y.split())
     return " ".join([word for word in diff if word.startswith(("+", "-"))])
 
-def encode_texts(texts, progress=None, logs=None):
-    embedding_matrix = model.encode(texts, show_progressbar=False)
-    log_time("Encoding texts completed", logs=logs)
-    return embedding_matrix
-
 def perform_deduplication(
     deduplication_type,
     dataset1_name,
@@ -110,59 +80,24 @@ def perform_deduplication(
     threshold=default_threshold,
     progress=gr.Progress(track_tqdm=True),
 ):
-    logs = []  # To store log messages
     try:
-        # Convert threshold to float
         threshold = float(threshold)
 
-        # Initialize status message
-        log_time("Deduplication started", logs=logs)
-
         if deduplication_type == "Single dataset":
-            # Load Dataset 1
-            start_time = time.time()
-            log_time("Loading Dataset 1", logs=logs)
-            if (
-                dataset1_name == default_dataset1_name
-                and dataset1_split == default_dataset1_split
-            ):
-                ds = ds_default1
-            else:
-                ds = load_dataset(dataset1_name, split=dataset1_split)
-            log_time("Loading Dataset 1 completed", start_time=start_time, logs=logs)
-
-            # Extract texts
-            start_time = time.time()
-            log_time("Extracting texts from Dataset 1", logs=logs)
+            ds = ds_default1 if dataset1_name == default_dataset1_name and dataset1_split == default_dataset1_split else load_dataset(dataset1_name, split=dataset1_split)
             texts = [example[dataset1_text_column] for example in ds]
-            log_time("Extracting texts from Dataset 1 completed", start_time=start_time, logs=logs)
-
-            # Compute embeddings
-            start_time = time.time()
-            log_time("Computing embeddings for Dataset 1", logs=logs)
-            embedding_matrix = encode_texts(texts, progress=progress, logs=logs)
-            log_time("Computing embeddings for Dataset 1 completed", start_time=start_time, logs=logs)
-
-            # Deduplicate
-            start_time = time.time()
-            log_time("Deduplicating embeddings", logs=logs)
-            deduplicated_indices, duplicate_to_original_mapping = deduplicate(
-                embedding_matrix, threshold, progress=progress, logs=logs
-            )
-            log_time("Deduplication completed", start_time=start_time, logs=logs)
-
-            # Prepare the results
+
+            embedding_matrix = compute_embeddings(texts, batch_size=64, progress=progress)
+            deduplicated_indices, duplicate_to_original_mapping = deduplicate(embedding_matrix, threshold, progress=progress)
+
             num_duplicates = len(duplicate_to_original_mapping)
             num_total = len(texts)
             num_deduplicated = len(deduplicated_indices)
 
             result_text = f"**Total documents:** {num_total}\n"
             result_text += f"**Number of duplicates found:** {num_duplicates}\n"
-            result_text += (
-                f"**Number of unique documents after deduplication:** {num_deduplicated}\n\n"
-            )
+            result_text += f"**Number of unique documents after deduplication:** {num_deduplicated}\n\n"
 
-            # Show deduplicated examples
             if num_duplicates > 0:
                 result_text += "**Examples of duplicates found:**\n\n"
                 num_examples = min(5, num_duplicates)
@@ -177,16 +112,12 @@ def perform_deduplication(
             else:
                 result_text += "No duplicates found."
 
-            log_time("Deduplication process finished", logs=logs)
-            full_log = "\n".join(logs)  # Combine all logs into one output
-            yield full_log, result_text
+            yield result_text
 
     except Exception as e:
-        full_log = "\n".join(logs)  # Combine all logs into one output in case of an error
-        yield f"An error occurred: {e}", ""
-        raise e
+        yield f"An error occurred: {e}"
 
-# Adjust the height of the status_output component using custom CSS
+# Gradio interface setup
 with gr.Blocks(css="#status_output { height: 150px; overflow: auto; }") as demo:
     gr.Markdown("# Semantic Deduplication")
 
@@ -209,22 +140,14 @@ with gr.Blocks(css="#status_output { height: 150px; overflow: auto; }") as demo:
             dataset2_split = gr.Textbox(value=default_dataset2_split, label="Dataset 2 Split")
             dataset2_text_column = gr.Textbox(value=default_text_column, label="Text Column Name")
 
-    threshold = gr.Slider(
-        minimum=0.0, maximum=1.0, value=default_threshold, label="Similarity Threshold"
-    )
+    threshold = gr.Slider(minimum=0.0, maximum=1.0, value=default_threshold, label="Similarity Threshold")
 
     compute_button = gr.Button("Compute")
 
-    # Use 'gr.Markdown' with 'elem_id' and custom CSS to adjust height
-    status_output = gr.Markdown(elem_id="status_output")
     result_output = gr.Markdown()
 
-    # Function to update the visibility of dataset2_inputs
     def update_visibility(deduplication_type_value):
-        if deduplication_type_value == "Cross-dataset":
-            return gr.update(visible=True)
-        else:
-            return gr.update(visible=False)
+        return gr.update(visible=True) if deduplication_type_value == "Cross-dataset" else gr.update(visible=False)
 
     deduplication_type.change(
         update_visibility, inputs=deduplication_type, outputs=dataset2_inputs
@@ -242,21 +165,19 @@ with gr.Blocks(css="#status_output { height: 150px; overflow: auto; }") as demo:
             dataset2_text_column,
             threshold,
         ],
-        outputs=[status_output, result_output],
+        outputs=[result_output],
     )
 
 demo.launch()
 
 
-
 # import gradio as gr
 # from datasets import load_dataset
 # import numpy as np
-# #from model2vec import StaticModel
 # import model2vec
 # from reach import Reach
 # from difflib import ndiff
-
+# import time
 
 # # Load the model at startup
 # model = model2vec.StaticModel.from_pretrained("minishlab/M2V_base_output")
@@ -273,13 +194,24 @@ demo.launch()
 # ds_default1 = load_dataset(default_dataset1_name, split=default_dataset1_split)
 # ds_default2 = load_dataset(default_dataset2_name, split=default_dataset2_split)
 
-
 # def batch_iterable(iterable, batch_size):
 #     """Helper function to create batches from an iterable."""
 #     for i in range(0, len(iterable), batch_size):
 #         yield iterable[i:i + batch_size]
 
-# def compute_embeddings(texts, batch_size, progress, desc="Computing embeddings"):
+# def log_time(message, start_time=None, logs=None):
+#     """Helper function to log the start and end times."""
+#     current_time = time.time()
+#     if start_time is not None:
+#         elapsed = current_time - start_time
+#         log_message = f"{message} - Took {elapsed:.2f} seconds"
+#     else:
+#         log_message = f"{message} - Started"
+    
+#     if logs is not None:
+#         logs.append(log_message)
+
+# def compute_embeddings(texts, batch_size, progress, logs, desc="Computing embeddings"):
 #     embeddings = []
 #     total_batches = (len(texts) + batch_size - 1) // batch_size
 #     for i, batch_texts in enumerate(batch_iterable(texts, batch_size)):
@@ -292,10 +224,11 @@ demo.launch()
 #     embedding_matrix: np.ndarray,
 #     threshold: float,
 #     batch_size: int = 1024,
-#     progress=None
+#     progress=None,
+#     logs=None
 # ) -> tuple[np.ndarray, dict[int, int]]:
 #     # Building the index
-#     progress(0, desc="Building search index...")
+#     log_time("Building search index", logs=logs)
 #     reach = Reach(
 #         vectors=embedding_matrix, items=[str(i) for i in range(len(embedding_matrix))]
 #     )
@@ -304,7 +237,7 @@ demo.launch()
 #     duplicate_to_original_mapping = {}
 
 #     # Finding nearest neighbors
-#     progress(0, desc="Finding nearest neighbors...")
+#     log_time("Finding nearest neighbors", logs=logs)
 #     results = reach.nearest_neighbor_threshold(
 #         embedding_matrix,
 #         threshold=threshold,
@@ -314,6 +247,7 @@ demo.launch()
 
 #     # Processing duplicates with a progress bar
 #     total_items = len(embedding_matrix)
+#     log_time("Processing duplicates", logs=logs)
 #     for i, similar_items in enumerate(
 #         progress.tqdm(results, desc="Processing duplicates", total=total_items)
 #     ):
@@ -333,9 +267,9 @@ demo.launch()
 #     diff = ndiff(x.split(), y.split())
 #     return " ".join([word for word in diff if word.startswith(("+", "-"))])
 
-
-# def encode_texts(texts, progress=None):
+# def encode_texts(texts, progress=None, logs=None):
 #     embedding_matrix = model.encode(texts, show_progressbar=False)
+#     log_time("Encoding texts completed", logs=logs)
 #     return embedding_matrix
 
 # def perform_deduplication(
@@ -349,17 +283,18 @@ demo.launch()
 #     threshold=default_threshold,
 #     progress=gr.Progress(track_tqdm=True),
 # ):
+#     logs = []  # To store log messages
 #     try:
 #         # Convert threshold to float
 #         threshold = float(threshold)
 
 #         # Initialize status message
-#         status = ""
+#         log_time("Deduplication started", logs=logs)
 
 #         if deduplication_type == "Single dataset":
 #             # Load Dataset 1
-#             status = "Loading Dataset 1..."
-#             yield status, ""
+#             start_time = time.time()
+#             log_time("Loading Dataset 1", logs=logs)
 #             if (
 #                 dataset1_name == default_dataset1_name
 #                 and dataset1_split == default_dataset1_split
@@ -367,29 +302,27 @@ demo.launch()
 #                 ds = ds_default1
 #             else:
 #                 ds = load_dataset(dataset1_name, split=dataset1_split)
+#             log_time("Loading Dataset 1 completed", start_time=start_time, logs=logs)
 
 #             # Extract texts
-#             status = "Extracting texts from Dataset 1..."
-#             yield status, ""
+#             start_time = time.time()
+#             log_time("Extracting texts from Dataset 1", logs=logs)
 #             texts = [example[dataset1_text_column] for example in ds]
+#             log_time("Extracting texts from Dataset 1 completed", start_time=start_time, logs=logs)
+
 #             # Compute embeddings
-#             status = "Computing embeddings for Dataset 1..."
-#             yield status, ""
-#             embedding_matrix = encode_texts(texts, progress=progress)
-#             #embedding_matrix = model.encode(texts, show_progressbar=True)
-#             # embedding_matrix = compute_embeddings(
-#             #     texts,
-#             #     batch_size=64,
-#             #     progress=progress,
-#             #     desc="Computing embeddings for Dataset 1",
-#             # )
+#             start_time = time.time()
+#             log_time("Computing embeddings for Dataset 1", logs=logs)
+#             embedding_matrix = encode_texts(texts, progress=progress, logs=logs)
+#             log_time("Computing embeddings for Dataset 1 completed", start_time=start_time, logs=logs)
 
 #             # Deduplicate
-#             status = "Deduplicating embeddings..."
-#             yield status, ""
+#             start_time = time.time()
+#             log_time("Deduplicating embeddings", logs=logs)
 #             deduplicated_indices, duplicate_to_original_mapping = deduplicate(
-#                 embedding_matrix, threshold, progress=progress
+#                 embedding_matrix, threshold, progress=progress, logs=logs
 #             )
+#             log_time("Deduplication completed", start_time=start_time, logs=logs)
 
 #             # Prepare the results
 #             num_duplicates = len(duplicate_to_original_mapping)
@@ -417,141 +350,15 @@ demo.launch()
 #             else:
 #                 result_text += "No duplicates found."
 
-#             # Final status
-#             status = "Deduplication completed."
-#             yield status, result_text
-
-#         elif deduplication_type == "Cross-dataset":
-#             # Similar code for cross-dataset deduplication
-#             # Load Dataset 1
-#             status = "Loading Dataset 1..."
-#             yield status, ""
-#             if (
-#                 dataset1_name == default_dataset1_name
-#                 and dataset1_split == default_dataset1_split
-#             ):
-#                 ds1 = ds_default1
-#             else:
-#                 ds1 = load_dataset(dataset1_name, split=dataset1_split)
-
-#             # Load Dataset 2
-#             status = "Loading Dataset 2..."
-#             yield status, ""
-#             if (
-#                 dataset2_name == default_dataset2_name
-#                 and dataset2_split == default_dataset2_split
-#             ):
-#                 ds2 = ds_default2
-#             else:
-#                 ds2 = load_dataset(dataset2_name, split=dataset2_split)
-
-#             # Extract texts from Dataset 1
-#             status = "Extracting texts from Dataset 1..."
-#             yield status, ""
-#             texts1 = [example[dataset1_text_column] for example in ds1]
-
-#             # Extract texts from Dataset 2
-#             status = "Extracting texts from Dataset 2..."
-#             yield status, ""
-#             texts2 = [example[dataset2_text_column] for example in ds2]
-
-#             # Compute embeddings for Dataset 1
-#             status = "Computing embeddings for Dataset 1..."
-#             yield status, ""
-#             embedding_matrix1 = compute_embeddings(
-#                 texts1,
-#                 batch_size=64,
-#                 progress=progress,
-#                 desc="Computing embeddings for Dataset 1",
-#             )
-
-#             # Compute embeddings for Dataset 2
-#             status = "Computing embeddings for Dataset 2..."
-#             yield status, ""
-#             embedding_matrix2 = compute_embeddings(
-#                 texts2,
-#                 batch_size=64,
-#                 progress=progress,
-#                 desc="Computing embeddings for Dataset 2",
-#             )
-
-#             # Deduplicate across datasets
-#             status = "Deduplicating embeddings across datasets..."
-#             yield status, ""
-#             duplicate_indices_in_ds2, duplicate_to_original_mapping = deduplicate_across_datasets(
-#                 embedding_matrix1, embedding_matrix2, threshold, progress=progress
-#             )
-
-#             num_duplicates = len(duplicate_indices_in_ds2)
-#             num_total_ds2 = len(texts2)
-#             num_unique_ds2 = num_total_ds2 - num_duplicates
-
-#             result_text = f"**Total documents in {dataset2_name}/{dataset2_split}:** {num_total_ds2}\n"
-#             result_text += f"**Number of duplicates found in {dataset2_name}/{dataset2_split}:** {num_duplicates}\n"
-#             result_text += f"**Number of unique documents in {dataset2_name}/{dataset2_split} after deduplication:** {num_unique_ds2}\n\n"
-
-#             # Show deduplicated examples
-#             if num_duplicates > 0:
-#                 result_text += "**Examples of duplicates found in Dataset 2:**\n\n"
-#                 num_examples = min(5, num_duplicates)
-#                 for duplicate_idx in duplicate_indices_in_ds2[:num_examples]:
-#                     original_idx = duplicate_to_original_mapping[duplicate_idx]
-#                     original_text = texts1[original_idx]
-#                     duplicate_text = texts2[duplicate_idx]
-#                     differences = display_word_differences(original_text, duplicate_text)
-#                     result_text += f"**Original text (Dataset 1):**\n{original_text}\n\n"
-#                     result_text += f"**Duplicate text (Dataset 2):**\n{duplicate_text}\n\n"
-#                     result_text += f"**Differences:**\n{differences}\n"
-#                     result_text += "-" * 50 + "\n\n"
-#             else:
-#                 result_text += "No duplicates found."
-
-#             # Final status
-#             status = "Deduplication completed."
-#             yield status, result_text
+#             log_time("Deduplication process finished", logs=logs)
+#             full_log = "\n".join(logs)  # Combine all logs into one output
+#             yield full_log, result_text
 
 #     except Exception as e:
+#         full_log = "\n".join(logs)  # Combine all logs into one output in case of an error
 #         yield f"An error occurred: {e}", ""
 #         raise e
 
-# def deduplicate_across_datasets(
-#     embedding_matrix_1: np.ndarray,
-#     embedding_matrix_2: np.ndarray,
-#     threshold: float,
-#     batch_size: int = 1024,
-#     progress=None
-# ) -> tuple[list[int], dict[int, int]]:
-#     # Building the index from Dataset 1
-#     progress(0, desc="Building search index from Dataset 1...")
-#     reach = Reach(
-#         vectors=embedding_matrix_1, items=[str(i) for i in range(len(embedding_matrix_1))]
-#     )
-
-#     duplicate_indices_in_test = []
-#     duplicate_to_original_mapping = {}
-
-#     # Finding nearest neighbors between datasets
-#     progress(0, desc="Finding nearest neighbors between datasets...")
-#     results = reach.nearest_neighbor_threshold(
-#         embedding_matrix_2,
-#         threshold=threshold,
-#         batch_size=batch_size,
-#         show_progressbar=False,  # Disable internal progress bar
-#     )
-
-#     total_items = len(embedding_matrix_2)
-#     # Processing duplicates with a progress bar
-#     for i, similar_items in enumerate(
-#         progress.tqdm(results, desc="Processing duplicates across datasets", total=total_items)
-#     ):
-#         similar_indices = [int(item[0]) for item in similar_items if item[1] >= threshold]
-
-#         if similar_indices:
-#             duplicate_indices_in_test.append(i)
-#             duplicate_to_original_mapping[i] = similar_indices[0]
-
-#     return duplicate_indices_in_test, duplicate_to_original_mapping
-
 # # Adjust the height of the status_output component using custom CSS
 # with gr.Blocks(css="#status_output { height: 150px; overflow: auto; }") as demo:
 #     gr.Markdown("# Semantic Deduplication")
@@ -612,3 +419,369 @@ demo.launch()
 #     )
 
 # demo.launch()
+
+
+
+# # import gradio as gr
+# # from datasets import load_dataset
+# # import numpy as np
+# # #from model2vec import StaticModel
+# # import model2vec
+# # from reach import Reach
+# # from difflib import ndiff
+
+
+# # # Load the model at startup
+# # model = model2vec.StaticModel.from_pretrained("minishlab/M2V_base_output")
+
+# # # Default dataset parameters
+# # default_dataset1_name = "sst2"
+# # default_dataset1_split = "train"
+# # default_dataset2_name = "sst2"
+# # default_dataset2_split = "validation"
+# # default_text_column = "sentence"
+# # default_threshold = 0.9
+
+# # # Load the default datasets at startup
+# # ds_default1 = load_dataset(default_dataset1_name, split=default_dataset1_split)
+# # ds_default2 = load_dataset(default_dataset2_name, split=default_dataset2_split)
+
+
+# # def batch_iterable(iterable, batch_size):
+# #     """Helper function to create batches from an iterable."""
+# #     for i in range(0, len(iterable), batch_size):
+# #         yield iterable[i:i + batch_size]
+
+# # def compute_embeddings(texts, batch_size, progress, desc="Computing embeddings"):
+# #     embeddings = []
+# #     total_batches = (len(texts) + batch_size - 1) // batch_size
+# #     for i, batch_texts in enumerate(batch_iterable(texts, batch_size)):
+# #         batch_embeddings = model.encode(batch_texts, show_progressbar=False)
+# #         embeddings.append(batch_embeddings)
+# #         progress((i + 1) / total_batches, desc=desc)
+# #     return np.concatenate(embeddings, axis=0)
+
+# # def deduplicate(
+# #     embedding_matrix: np.ndarray,
+# #     threshold: float,
+# #     batch_size: int = 1024,
+# #     progress=None
+# # ) -> tuple[np.ndarray, dict[int, int]]:
+# #     # Building the index
+# #     progress(0, desc="Building search index...")
+# #     reach = Reach(
+# #         vectors=embedding_matrix, items=[str(i) for i in range(len(embedding_matrix))]
+# #     )
+
+# #     deduplicated_indices = set(range(len(embedding_matrix)))
+# #     duplicate_to_original_mapping = {}
+
+# #     # Finding nearest neighbors
+# #     progress(0, desc="Finding nearest neighbors...")
+# #     results = reach.nearest_neighbor_threshold(
+# #         embedding_matrix,
+# #         threshold=threshold,
+# #         batch_size=batch_size,
+# #         show_progressbar=False,  # Disable internal progress bar
+# #     )
+
+# #     # Processing duplicates with a progress bar
+# #     total_items = len(embedding_matrix)
+# #     for i, similar_items in enumerate(
+# #         progress.tqdm(results, desc="Processing duplicates", total=total_items)
+# #     ):
+# #         if i not in deduplicated_indices:
+# #             continue
+
+# #         similar_indices = [int(item[0]) for item in similar_items if int(item[0]) != i]
+
+# #         for sim_idx in similar_indices:
+# #             if sim_idx in deduplicated_indices:
+# #                 deduplicated_indices.remove(sim_idx)
+# #                 duplicate_to_original_mapping[sim_idx] = i
+
+# #     return np.array(list(deduplicated_indices)), duplicate_to_original_mapping
+
+# # def display_word_differences(x: str, y: str) -> str:
+# #     diff = ndiff(x.split(), y.split())
+# #     return " ".join([word for word in diff if word.startswith(("+", "-"))])
+
+
+# # def encode_texts(texts, progress=None):
+# #     embedding_matrix = model.encode(texts, show_progressbar=False)
+# #     return embedding_matrix
+
+# # def perform_deduplication(
+# #     deduplication_type,
+# #     dataset1_name,
+# #     dataset1_split,
+# #     dataset1_text_column,
+# #     dataset2_name="",
+# #     dataset2_split="",
+# #     dataset2_text_column="",
+# #     threshold=default_threshold,
+# #     progress=gr.Progress(track_tqdm=True),
+# # ):
+# #     try:
+# #         # Convert threshold to float
+# #         threshold = float(threshold)
+
+# #         # Initialize status message
+# #         status = ""
+
+# #         if deduplication_type == "Single dataset":
+# #             # Load Dataset 1
+# #             status = "Loading Dataset 1..."
+# #             yield status, ""
+# #             if (
+# #                 dataset1_name == default_dataset1_name
+# #                 and dataset1_split == default_dataset1_split
+# #             ):
+# #                 ds = ds_default1
+# #             else:
+# #                 ds = load_dataset(dataset1_name, split=dataset1_split)
+
+# #             # Extract texts
+# #             status = "Extracting texts from Dataset 1..."
+# #             yield status, ""
+# #             texts = [example[dataset1_text_column] for example in ds]
+# #             # Compute embeddings
+# #             status = "Computing embeddings for Dataset 1..."
+# #             yield status, ""
+# #             embedding_matrix = encode_texts(texts, progress=progress)
+# #             #embedding_matrix = model.encode(texts, show_progressbar=True)
+# #             # embedding_matrix = compute_embeddings(
+# #             #     texts,
+# #             #     batch_size=64,
+# #             #     progress=progress,
+# #             #     desc="Computing embeddings for Dataset 1",
+# #             # )
+
+# #             # Deduplicate
+# #             status = "Deduplicating embeddings..."
+# #             yield status, ""
+# #             deduplicated_indices, duplicate_to_original_mapping = deduplicate(
+# #                 embedding_matrix, threshold, progress=progress
+# #             )
+
+# #             # Prepare the results
+# #             num_duplicates = len(duplicate_to_original_mapping)
+# #             num_total = len(texts)
+# #             num_deduplicated = len(deduplicated_indices)
+
+# #             result_text = f"**Total documents:** {num_total}\n"
+# #             result_text += f"**Number of duplicates found:** {num_duplicates}\n"
+# #             result_text += (
+# #                 f"**Number of unique documents after deduplication:** {num_deduplicated}\n\n"
+# #             )
+
+# #             # Show deduplicated examples
+# #             if num_duplicates > 0:
+# #                 result_text += "**Examples of duplicates found:**\n\n"
+# #                 num_examples = min(5, num_duplicates)
+# #                 for duplicate_idx, original_idx in list(duplicate_to_original_mapping.items())[:num_examples]:
+# #                     original_text = texts[original_idx]
+# #                     duplicate_text = texts[duplicate_idx]
+# #                     differences = display_word_differences(original_text, duplicate_text)
+# #                     result_text += f"**Original text:**\n{original_text}\n\n"
+# #                     result_text += f"**Duplicate text:**\n{duplicate_text}\n\n"
+# #                     result_text += f"**Differences:**\n{differences}\n"
+# #                     result_text += "-" * 50 + "\n\n"
+# #             else:
+# #                 result_text += "No duplicates found."
+
+# #             # Final status
+# #             status = "Deduplication completed."
+# #             yield status, result_text
+
+# #         elif deduplication_type == "Cross-dataset":
+# #             # Similar code for cross-dataset deduplication
+# #             # Load Dataset 1
+# #             status = "Loading Dataset 1..."
+# #             yield status, ""
+# #             if (
+# #                 dataset1_name == default_dataset1_name
+# #                 and dataset1_split == default_dataset1_split
+# #             ):
+# #                 ds1 = ds_default1
+# #             else:
+# #                 ds1 = load_dataset(dataset1_name, split=dataset1_split)
+
+# #             # Load Dataset 2
+# #             status = "Loading Dataset 2..."
+# #             yield status, ""
+# #             if (
+# #                 dataset2_name == default_dataset2_name
+# #                 and dataset2_split == default_dataset2_split
+# #             ):
+# #                 ds2 = ds_default2
+# #             else:
+# #                 ds2 = load_dataset(dataset2_name, split=dataset2_split)
+
+# #             # Extract texts from Dataset 1
+# #             status = "Extracting texts from Dataset 1..."
+# #             yield status, ""
+# #             texts1 = [example[dataset1_text_column] for example in ds1]
+
+# #             # Extract texts from Dataset 2
+# #             status = "Extracting texts from Dataset 2..."
+# #             yield status, ""
+# #             texts2 = [example[dataset2_text_column] for example in ds2]
+
+# #             # Compute embeddings for Dataset 1
+# #             status = "Computing embeddings for Dataset 1..."
+# #             yield status, ""
+# #             embedding_matrix1 = compute_embeddings(
+# #                 texts1,
+# #                 batch_size=64,
+# #                 progress=progress,
+# #                 desc="Computing embeddings for Dataset 1",
+# #             )
+
+# #             # Compute embeddings for Dataset 2
+# #             status = "Computing embeddings for Dataset 2..."
+# #             yield status, ""
+# #             embedding_matrix2 = compute_embeddings(
+# #                 texts2,
+# #                 batch_size=64,
+# #                 progress=progress,
+# #                 desc="Computing embeddings for Dataset 2",
+# #             )
+
+# #             # Deduplicate across datasets
+# #             status = "Deduplicating embeddings across datasets..."
+# #             yield status, ""
+# #             duplicate_indices_in_ds2, duplicate_to_original_mapping = deduplicate_across_datasets(
+# #                 embedding_matrix1, embedding_matrix2, threshold, progress=progress
+# #             )
+
+# #             num_duplicates = len(duplicate_indices_in_ds2)
+# #             num_total_ds2 = len(texts2)
+# #             num_unique_ds2 = num_total_ds2 - num_duplicates
+
+# #             result_text = f"**Total documents in {dataset2_name}/{dataset2_split}:** {num_total_ds2}\n"
+# #             result_text += f"**Number of duplicates found in {dataset2_name}/{dataset2_split}:** {num_duplicates}\n"
+# #             result_text += f"**Number of unique documents in {dataset2_name}/{dataset2_split} after deduplication:** {num_unique_ds2}\n\n"
+
+# #             # Show deduplicated examples
+# #             if num_duplicates > 0:
+# #                 result_text += "**Examples of duplicates found in Dataset 2:**\n\n"
+# #                 num_examples = min(5, num_duplicates)
+# #                 for duplicate_idx in duplicate_indices_in_ds2[:num_examples]:
+# #                     original_idx = duplicate_to_original_mapping[duplicate_idx]
+# #                     original_text = texts1[original_idx]
+# #                     duplicate_text = texts2[duplicate_idx]
+# #                     differences = display_word_differences(original_text, duplicate_text)
+# #                     result_text += f"**Original text (Dataset 1):**\n{original_text}\n\n"
+# #                     result_text += f"**Duplicate text (Dataset 2):**\n{duplicate_text}\n\n"
+# #                     result_text += f"**Differences:**\n{differences}\n"
+# #                     result_text += "-" * 50 + "\n\n"
+# #             else:
+# #                 result_text += "No duplicates found."
+
+# #             # Final status
+# #             status = "Deduplication completed."
+# #             yield status, result_text
+
+# #     except Exception as e:
+# #         yield f"An error occurred: {e}", ""
+# #         raise e
+
+# # def deduplicate_across_datasets(
+# #     embedding_matrix_1: np.ndarray,
+# #     embedding_matrix_2: np.ndarray,
+# #     threshold: float,
+# #     batch_size: int = 1024,
+# #     progress=None
+# # ) -> tuple[list[int], dict[int, int]]:
+# #     # Building the index from Dataset 1
+# #     progress(0, desc="Building search index from Dataset 1...")
+# #     reach = Reach(
+# #         vectors=embedding_matrix_1, items=[str(i) for i in range(len(embedding_matrix_1))]
+# #     )
+
+# #     duplicate_indices_in_test = []
+# #     duplicate_to_original_mapping = {}
+
+# #     # Finding nearest neighbors between datasets
+# #     progress(0, desc="Finding nearest neighbors between datasets...")
+# #     results = reach.nearest_neighbor_threshold(
+# #         embedding_matrix_2,
+# #         threshold=threshold,
+# #         batch_size=batch_size,
+# #         show_progressbar=False,  # Disable internal progress bar
+# #     )
+
+# #     total_items = len(embedding_matrix_2)
+# #     # Processing duplicates with a progress bar
+# #     for i, similar_items in enumerate(
+# #         progress.tqdm(results, desc="Processing duplicates across datasets", total=total_items)
+# #     ):
+# #         similar_indices = [int(item[0]) for item in similar_items if item[1] >= threshold]
+
+# #         if similar_indices:
+# #             duplicate_indices_in_test.append(i)
+# #             duplicate_to_original_mapping[i] = similar_indices[0]
+
+# #     return duplicate_indices_in_test, duplicate_to_original_mapping
+
+# # # Adjust the height of the status_output component using custom CSS
+# # with gr.Blocks(css="#status_output { height: 150px; overflow: auto; }") as demo:
+# #     gr.Markdown("# Semantic Deduplication")
+
+# #     deduplication_type = gr.Radio(
+# #         choices=["Single dataset", "Cross-dataset"],
+# #         label="Deduplication Type",
+# #         value="Single dataset",
+# #     )
+
+# #     with gr.Row():
+# #         dataset1_name = gr.Textbox(value=default_dataset1_name, label="Dataset 1 Name")
+# #         dataset1_split = gr.Textbox(value=default_dataset1_split, label="Dataset 1 Split")
+# #         dataset1_text_column = gr.Textbox(value=default_text_column, label="Text Column Name")
+
+# #     dataset2_inputs = gr.Column(visible=False)
+# #     with dataset2_inputs:
+# #         gr.Markdown("### Dataset 2")
+# #         with gr.Row():
+# #             dataset2_name = gr.Textbox(value=default_dataset2_name, label="Dataset 2 Name")
+# #             dataset2_split = gr.Textbox(value=default_dataset2_split, label="Dataset 2 Split")
+# #             dataset2_text_column = gr.Textbox(value=default_text_column, label="Text Column Name")
+
+# #     threshold = gr.Slider(
+# #         minimum=0.0, maximum=1.0, value=default_threshold, label="Similarity Threshold"
+# #     )
+
+# #     compute_button = gr.Button("Compute")
+
+# #     # Use 'gr.Markdown' with 'elem_id' and custom CSS to adjust height
+# #     status_output = gr.Markdown(elem_id="status_output")
+# #     result_output = gr.Markdown()
+
+# #     # Function to update the visibility of dataset2_inputs
+# #     def update_visibility(deduplication_type_value):
+# #         if deduplication_type_value == "Cross-dataset":
+# #             return gr.update(visible=True)
+# #         else:
+# #             return gr.update(visible=False)
+
+# #     deduplication_type.change(
+# #         update_visibility, inputs=deduplication_type, outputs=dataset2_inputs
+# #     )
+
+# #     compute_button.click(
+# #         fn=perform_deduplication,
+# #         inputs=[
+# #             deduplication_type,
+# #             dataset1_name,
+# #             dataset1_split,
+# #             dataset1_text_column,
+# #             dataset2_name,
+# #             dataset2_split,
+# #             dataset2_text_column,
+# #             threshold,
+# #         ],
+# #         outputs=[status_output, result_output],
+# #     )
+
+# # demo.launch()