cat-stack 1.0.1__tar.gz → 1.0.2__tar.gz

{cat_stack-1.0.1 → cat_stack-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-stack
-Version: 1.0.1
+Version: 1.0.2
 Summary: Domain-agnostic text, image, PDF, and DOCX classification engine powered by LLMs
 Project-URL: Documentation, https://github.com/chrissoria/cat-stack#readme
 Project-URL: Issues, https://github.com/chrissoria/cat-stack/issues

{cat_stack-1.0.1 → cat_stack-1.0.2}/src/cat_stack/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-stack"

{cat_stack-1.0.1 → cat_stack-1.0.2}/src/cat_stack/text_functions_ensemble.py

@@ -3232,6 +3232,7 @@ def build_output_dataframes(
 
     # Initialize data structures
     combined_data = {
+        "input_index": [],
         "input_data": [],
         "processing_status": [],
         "failed_models": [],
@@ -3267,8 +3268,13 @@ def build_output_dataframes(
             combined_data[f"category_{i}_resolved_by"] = []
 
     # Populate data
-    for result in all_results:
-        combined_data["input_data"].append(result["response"])
+    for idx, result in enumerate(all_results):
+        combined_data["input_index"].append(idx)
+        # Truncate input_data for readability
+        raw = result["response"]
+        clean = " ".join(str(raw).split())  # collapse whitespace/newlines
+        preview = clean[:100] + "..." if len(clean) > 100 else clean
+        combined_data["input_data"].append(preview)
         aggregated = result["aggregated"]
 
         # Add PDF metadata if present
@@ -4007,13 +4013,20 @@ def summarize_ensemble(
         if is_pdf_mode and isinstance(item, tuple) and len(item) == 3:
             pdf_path, page_index, page_label = item
             row = {
+                "input_index": entry["idx"],
                 "input_data": page_label,
                 "pdf_path": pdf_path,
                 "page_index": page_index,
             }
             original_text_for_synthesis = page_label  # Use page label for synthesis context
         else:
-            row = {"input_data": item}
+            # Truncate input_data for readability; add input_index for joining
+            clean = " ".join(str(item).split())  # collapse whitespace/newlines
+            preview = clean[:100] + "..." if len(clean) > 100 else clean
+            row = {
+                "input_index": entry["idx"],
+                "input_data": preview,
+            }
             original_text_for_synthesis = item
 
         # Extract summaries from each model