cat-llm 0.0.53__tar.gz → 0.0.55__tar.gz

{cat_llm-0.0.53 → cat_llm-0.0.55}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.53
+Version: 0.0.55
 Summary: A tool for categorizing text data and images using LLMs and vision models
 Project-URL: Documentation, https://github.com/chrissoria/cat-llm#readme
 Project-URL: Issues, https://github.com/chrissoria/cat-llm/issues
 Project-URL: Source, https://github.com/chrissoria/cat-llm
-Author-email: Christopher Soria <chrissoria@berkeley.edu>
+Author-email: Chris Soria <chrissoria@berkeley.edu>
 License-Expression: MIT
 License-File: LICENSE
 Keywords: categorizer,image classification,llm,structured output,survey data,text classification
@@ -19,7 +19,10 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.8
+Requires-Dist: openai
 Requires-Dist: pandas
+Requires-Dist: random
+Requires-Dist: requests
 Requires-Dist: tqdm
 Description-Content-Type: text/markdown
 

{cat_llm-0.0.53 → cat_llm-0.0.55}/pyproject.toml

@@ -11,7 +11,7 @@ requires-python = ">=3.8"
 license = "MIT"
 keywords = ["llm","categorizer","survey data", "image classification", "structured output", "text classification"]
 authors = [
-  { name = "Christopher Soria", email = "chrissoria@berkeley.edu" },
+  { name = "Chris Soria", email = "chrissoria@berkeley.edu" },
 ]
 classifiers = [
   "Development Status :: 4 - Beta",
@@ -26,7 +26,10 @@ classifiers = [
 ]
 dependencies = [
   "pandas",
-  "tqdm"
+  "tqdm",
+  "requests",
+  "openai",
+  "random"
 ]
 
 [project.urls]

{cat_llm-0.0.53 → cat_llm-0.0.55}/src/catllm/CERAD_functions.py

@@ -378,7 +378,7 @@ def cerad_drawn_score(
             image_files.reset_index(drop=True) if isinstance(image_files, (pd.DataFrame, pd.Series)) 
             else pd.Series(image_files)
         ),
-        'link1': pd.Series(link1).reset_index(drop=True),
+        'model_response': pd.Series(link1).reset_index(drop=True),
         'json': pd.Series(extracted_jsons).reset_index(drop=True)
     })
     categorized_data = pd.concat([categorized_data, normalized_data], axis=1)

{cat_llm-0.0.53 → cat_llm-0.0.55}/src/catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.53"
+__version__ = "0.0.55"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

{cat_llm-0.0.53 → cat_llm-0.0.55}/src/catllm/image_functions.py

@@ -225,7 +225,7 @@ def image_multi_class(
             # Save progress so far
             temp_df = pd.DataFrame({
                 'image_input': image_files[:i+1],
-                'link1': link1,
+                'model_response': link1,
                 'json': extracted_jsons
             })
             # Normalize processed jsons so far
@@ -522,7 +522,7 @@ def image_score_drawing(
             # Save progress so far
             temp_df = pd.DataFrame({
                 'image_input': image_files[:i+1],
-                'link1': link1,
+                'model_response': link1,
                 'json': extracted_jsons
             })
             # Normalize processed jsons so far
@@ -844,7 +844,7 @@ def image_features(
             image_files.reset_index(drop=True) if isinstance(image_files, (pd.DataFrame, pd.Series)) 
             else pd.Series(image_files)
         ),
-        'link1': pd.Series(link1).reset_index(drop=True),
+        'model_response': pd.Series(link1).reset_index(drop=True),
         'json': pd.Series(extracted_jsons).reset_index(drop=True)
     })
     categorized_data = pd.concat([categorized_data, normalized_data], axis=1)

{cat_llm-0.0.53 → cat_llm-0.0.55}/src/catllm/text_functions.py

@@ -227,6 +227,7 @@ def multi_class(
     user_model="gpt-4o",
     creativity=0,
     safety=False,
+    to_csv=False,
     filename="categorized_data.csv",
     save_directory=None,
     model_source="OpenAI"
@@ -307,6 +308,37 @@ Provide your work in JSON format where the number belonging to each category is
                 except Exception as e:
                     print(f"An error occurred: {e}")
                     link1.append(f"Error processing input: {e}")
+                    
+            elif model_source == "Google":
+                import requests
+                url = f"https://generativelanguage.googleapis.com/v1beta/models/{user_model}:generateContent"
+                try:
+                    headers = {
+                        "x-goog-api-key": api_key,
+                        "Content-Type": "application/json"
+                        }
+                    
+                    payload = {
+                        "contents": [{
+                            "parts": [{"text": prompt}]
+                            }]
+                            }
+                    
+                    response = requests.post(url, headers=headers, json=payload)
+                    response.raise_for_status()  # Raise exception for HTTP errors
+                    result = response.json()
+
+                    if "candidates" in result and result["candidates"]:
+                        reply = result["candidates"][0]["content"]["parts"][0]["text"]
+                    else:
+                        reply = "No response generated"
+
+                    link1.append(reply)
+                    print(reply)
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+
             elif model_source == "Mistral":
                 from mistralai import Mistral
                 client = Mistral(api_key=api_key)
@@ -359,7 +391,7 @@ Provide your work in JSON format where the number belonging to each category is
                     normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
             normalized_data = pd.concat(normalized_data_list, ignore_index=True)
             temp_df = pd.concat([temp_df, normalized_data], axis=1)
-            # Save to CSV
+            # save to CSV
             if save_directory is None:
                 save_directory = os.getcwd()
             temp_df.to_csv(os.path.join(save_directory, filename), index=False)
@@ -374,13 +406,18 @@ Provide your work in JSON format where the number belonging to each category is
             normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
     normalized_data = pd.concat(normalized_data_list, ignore_index=True)
     categorized_data = pd.DataFrame({
-        'image_input': (
+        'survey_input': (
             survey_input.reset_index(drop=True) if isinstance(survey_input, (pd.DataFrame, pd.Series)) 
             else pd.Series(survey_input)
         ),
-        'link1': pd.Series(link1).reset_index(drop=True),
+        'model_response': pd.Series(link1).reset_index(drop=True),
         'json': pd.Series(extracted_jsons).reset_index(drop=True)
     })
     categorized_data = pd.concat([categorized_data, normalized_data], axis=1)
+
+    if to_csv:
+        if save_directory is None:
+            save_directory = os.getcwd()
+        categorized_data.to_csv(os.path.join(save_directory, filename), index=False)
     
     return categorized_data