cat-llm 0.0.53__py3-none-any.whl → 0.0.55__py3-none-any.whl

{cat_llm-0.0.53.dist-info → cat_llm-0.0.55.dist-info}/METADATA

@@ -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.dist-info → cat_llm-0.0.55.dist-info}/RECORD

@@ -1,15 +1,15 @@
-catllm/CERAD_functions.py,sha256=NNEu_Q10tClV7vRIVEgSQY8ujlXDbpWDzo1AbqlN7nQ,22462
-catllm/__about__.py,sha256=9ibCFe0aysD41qIPAN3LS-HE5Z0iMmnMJiYSMUPghak,404
+catllm/CERAD_functions.py,sha256=ZCKyCiv-2eUPzJ7Yhrz4Y0OJK4iEyWMnOUI7mFDsoEI,22471
+catllm/__about__.py,sha256=VaZlPOW_B39qUtTpqKKsmCDpMCtV8MCv3LFokpKtjVI,404
 catllm/__init__.py,sha256=sf02zp7N0NW0mAQi7eQ4gliWR1EwoqvXkHN2HwwjcTE,372
 catllm/build_web_research.py,sha256=CYGhxnonJLBw80ATEBkpRjOKJgCYntHTgx4s4Pb8g88,6833
-catllm/image_functions.py,sha256=Gz-djnXVaLT8GOR0sc8aPjjuC9L_gIT2AjUMjsjjmi0,35492
-catllm/text_functions.py,sha256=YK9BcpTbEo5FhkA5aiNfK8c72kyiW6AYzuILYNqGjqc,16603
+catllm/image_functions.py,sha256=8dUpwHwVe4Vf06wjFNgLnh54q5upo4E-P87-TKaSECE,35519
+catllm/text_functions.py,sha256=iAfd6roKxxSrrKQ4VvEc5y_ZWyIgW9fVzQOaDITyFDU,18116
 catllm/images/circle.png,sha256=JWujAWAh08-TajAoEr_TAeFNLlfbryOLw6cgIBREBuQ,86202
 catllm/images/cube.png,sha256=nFec3e5bmRe4zrBCJ8QK-HcJLrG7u7dYdKhmdMfacfE,77275
 catllm/images/diamond.png,sha256=rJDZKtsnBGRO8FPA0iHuA8FvHFGi9PkI_DWSFdw6iv0,99568
 catllm/images/overlapping_pentagons.png,sha256=VO5plI6eoVRnjfqinn1nNzsCP2WQhuQy71V0EASouW4,71208
 catllm/images/rectangles.png,sha256=2XM16HO9EYWj2yHgN4bPXaCwPfl7iYQy0tQUGaJX9xg,40692
-cat_llm-0.0.53.dist-info/METADATA,sha256=p9ov-gGpzkVF1APkaqozr7G4BxEX-2c17P5dWsLPdkE,21459
-cat_llm-0.0.53.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.53.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.53.dist-info/RECORD,,
+cat_llm-0.0.55.dist-info/METADATA,sha256=rOd1FlzPT3uFmUb4vdyaBPrVaI-zyt3ZRcBsYLGY3f8,21521
+cat_llm-0.0.55.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.55.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.55.dist-info/RECORD,,

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)

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"

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)

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