Merge pull request #26 from tmaier-kettering/claude/project-review-improvements-nryvsh

Refactor API client initialization and fix Pydantic validation

Author: tmaier-kettering

batch_processing/batch_creation.py

@@ -11,7 +11,6 @@
 from enum import Enum
 from io import BytesIO
 from typing import Optional, List
-import tkinter as tk
 from pydantic import BaseModel, ConfigDict, Field
 
 from file_handling.data_conversion import make_str_enum
@@ -108,7 +107,7 @@ def generate_multi_label_batch(labels, quotes) -> BytesIO | None:
     labels_enum = make_str_enum("Label", labels)
 
     class LabeledQuoteMulti(BaseModel):
-        label: List[labels_enum] = Field(..., min_items=1)
+        label: List[labels_enum] = Field(..., min_length=1)
         model_config = ConfigDict(use_enum_values=True, extra='forbid')
 
     SCHEMA = LabeledQuoteMulti.model_json_schema()
@@ -156,7 +155,7 @@ def generate_keyword_extraction_batch(texts) -> BytesIO | None:
     Returns a BytesIO whose .name is set to 'batchinput.jsonl'.
     """
     class KeywordExtraction(BaseModel):
-        keywords: list[str] = Field(..., min_items=1)
+        keywords: list[str] = Field(..., min_length=1)
         model_config = ConfigDict(extra='forbid')
 
     SCHEMA = KeywordExtraction.model_json_schema()

file_handling/data_import.py

@@ -360,17 +360,6 @@ def _initial_blank_preview():
         _fill_preview_rows([[""] * 5 for _ in range(5)])
         _update_dataset_name_preview()
 
-    def _current_header_labels() -> list[str]:
-        # Return the labels currently shown atop the preview
-        return [tree.heading(cid)["text"] for cid in tree["columns"]]
-
-    def _selected_header_label() -> str:
-        labels = _current_header_labels()
-        idx = selected_col.get()
-        if 0 <= idx < len(labels):
-            return str(labels[idx])
-        return ""
-
     def _update_dataset_name_controls_enabled():
         # Enable/disable "selected column header" radio based on has_headers + data present
         has_data = bool(_loaded_rows)

live_processing/keyword_extraction_live.py

@@ -8,29 +8,28 @@
 
 from typing import Optional
 import tkinter as tk
+from tkinter import messagebox
 from pydantic import BaseModel, ValidationError, Field, ConfigDict
-from openai import OpenAI
 from file_handling.data_import import import_data
 from file_handling.data_conversion import save_as_csv, to_long_df
-from settings import secrets_store, config
+from settings import config
+from batch_processing.batch_method import get_client
 
 # Progress UI lives in a separate module
 from ui.progress_ui import ProgressController
 
-# Initialize OpenAI client with stored API key
-try:
-    OPENAI_API_KEY = secrets_store.load_api_key()
-    client = OpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
-except Exception:
-    OPENAI_API_KEY = None
-    client = None
-
 
 def keyword_extraction_pipeline(parent: Optional[tk.Misc] = None):
     """
     Prompt for quotes CSVs, extract keywords from each quote,
     show progress, then save results to CSV.
     """
+    try:
+        client = get_client()
+    except Exception as e:
+        messagebox.showerror("API Key Required", str(e))
+        return
+
     # Get quotes data
     from_import = import_data(parent, "Select the quotes data")
     if from_import is None:
@@ -40,7 +39,7 @@ def keyword_extraction_pipeline(parent: Optional[tk.Misc] = None):
     class KeywordExtraction(BaseModel):
         id: int | None = None
         quote: str
-        keywords: list[str] = Field(..., min_items=1)
+        keywords: list[str] = Field(..., min_length=1)
         model_config = ConfigDict()
 
     total = len(quotes)

live_processing/multi_label_live.py

@@ -8,29 +8,28 @@
 
 from typing import Optional, List
 import tkinter as tk
+from tkinter import messagebox
 from pydantic import BaseModel, ValidationError, Field, ConfigDict
-from openai import OpenAI
 from file_handling.data_import import import_data
 from file_handling.data_conversion import make_str_enum, save_as_csv, to_long_df
-from settings import secrets_store, config
+from settings import config
+from batch_processing.batch_method import get_client
 
 # Progress UI lives in a separate module
 from ui.progress_ui import ProgressController
 
-# Initialize OpenAI client with stored API key
-try:
-    OPENAI_API_KEY = secrets_store.load_api_key()
-    client = OpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
-except Exception:
-    OPENAI_API_KEY = None
-    client = None
-
 
 def multi_label_pipeline(parent: Optional[tk.Misc] = None):
     """
     Prompt for labels/quotes CSVs, classify each quote with 1+ labels,
     show progress, then save results to CSV.
     """
+    try:
+        client = get_client()
+    except Exception as e:
+        messagebox.showerror("API Key Required", str(e))
+        return
+
     # Get labels data
     from_import = import_data(parent, "Select the labels data")
     if from_import is None:
@@ -47,7 +46,7 @@ def multi_label_pipeline(parent: Optional[tk.Misc] = None):
     class LabeledQuoteMulti(BaseModel):
         id: int | None = None
         quote: str
-        label: List[labels] = Field(..., min_items=1)
+        label: List[labels] = Field(..., min_length=1)
         model_config = ConfigDict(use_enum_values=True, extra='forbid')
 
     total = len(quotes)

live_processing/single_label_live.py

@@ -8,29 +8,28 @@
 
 from typing import Optional
 import tkinter as tk
+from tkinter import messagebox
 from pydantic import BaseModel, ValidationError, Field, ConfigDict
-from openai import OpenAI
 from file_handling.data_import import import_data
 from file_handling.data_conversion import make_str_enum, save_as_csv, to_long_df
-from settings import secrets_store, config
+from settings import config
+from batch_processing.batch_method import get_client
 
 # Progress UI lives in a separate module
 from ui.progress_ui import ProgressController
 
-# Initialize OpenAI client with stored API key
-try:
-    OPENAI_API_KEY = secrets_store.load_api_key()
-    client = OpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
-except Exception:
-    OPENAI_API_KEY = None
-    client = None
-
 
 def single_label_pipeline(parent: Optional[tk.Misc] = None):
     """
     Prompt for labels/quotes CSVs, classify each quote with exactly one label,
     show progress, then save results to CSV.
     """
+    try:
+        client = get_client()
+    except Exception as e:
+        messagebox.showerror("API Key Required", str(e))
+        return
+
     # Get labels data
     from_import = import_data(parent, "Select the labels data")
     if from_import is None:

ui/main_window.py

@@ -92,7 +92,12 @@ def build_ui(root: tk.Tk) -> None:
         root: The main Tkinter window to build the UI in
     """
     root.title(APP_TITLE)
-    root.iconbitmap(asset_path("app.ico"))
+    try:
+        # .ico files are only natively supported by iconbitmap on Windows;
+        # this raises TclError on Linux/macOS Tk builds.
+        root.iconbitmap(asset_path("app.ico"))
+    except tk.TclError:
+        pass
 
     # ===== Top-level grid: header, spacer, table area =====
     root.columnconfigure(0, weight=1)