cat-llm 0.0.58__py3-none-any.whl → 0.0.60__py3-none-any.whl

{cat_llm-0.0.58.dist-info → cat_llm-0.0.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.58
+Version: 0.0.60
 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

cat_llm-0.0.60.dist-info/RECORD

@@ -0,0 +1,15 @@
+catllm/CERAD_functions.py,sha256=05n7h27TuAp3klkOnrH--m1wMreYqYuObM9NIab934o,22603
+catllm/__about__.py,sha256=gKDClCOutqX8Ni28O3IFIGdeLkzJrrrx6miHt3rKX8g,408
+catllm/__init__.py,sha256=sf02zp7N0NW0mAQi7eQ4gliWR1EwoqvXkHN2HwwjcTE,372
+catllm/build_web_research.py,sha256=1mp1z59ed5-wfG79xMDH0jjjQYZSuo1ko-i0_GO6iE4,8253
+catllm/image_functions.py,sha256=KDb2UxDLrioerlqKZjKAX7lqfW-S_TSQCK6YxtJRKwI,35958
+catllm/text_functions.py,sha256=XjhkwCEd3P9tYVvwASdVX7arUs74JIeX8tPsliMkmEs,18466
+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-0.0.60.dist-info/METADATA,sha256=2ckdqzCdkO73slhe92-JfvYuhj5aBJj-rH7YIiHwQak,22370
+cat_llm-0.0.60.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.60.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.60.dist-info/RECORD,,

catllm/CERAD_functions.py

@@ -27,7 +27,7 @@ def cerad_drawn_score(
     image_input,
     api_key,
     user_model="gpt-4o",
-    creativity=0,
+    creativity=None,
     reference_in_image=False,
     provide_reference=False,
     safety=False,
@@ -261,7 +261,7 @@ def cerad_drawn_score(
                 response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 link1.append(reply)
@@ -279,8 +279,8 @@ def cerad_drawn_score(
                 message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
-                    messages=[{"role": "user", "content": prompt}]
+                    messages=[{"role": "user", "content": prompt}],
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = message.content[0].text  # Anthropic returns content as list
                 link1.append(reply)
@@ -301,7 +301,7 @@ def cerad_drawn_score(
                     messages=[
                     {'role': 'user', 'content': prompt}
                 ],
-                temperature=creativity
+                **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response.choices[0].message.content
                 link1.append(reply)

catllm/__about__.py

@@ -1,10 +1,10 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.58"
+__version__ = "0.0.60"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"
 __description__ = "A tool for categorizing and exploring text data and images using LLMs and vision models"
 __url__ = "https://github.com/chrissoria/cat-llm" 
-__license__ = "MIT"
+__license__ = "GPL-3.0"

catllm/build_web_research.py

@@ -7,7 +7,7 @@ def build_web_research_dataset(
     additional_instructions = "",
     categories = ['Answer','URL'],
     user_model="claude-sonnet-4-20250514",
-    creativity=0,
+    creativity=None,
     safety=False,
     filename="categorized_data.csv",
     save_directory=None,
@@ -75,8 +75,8 @@ def build_web_research_dataset(
                     message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
                     messages=[{"role": "user", "content": prompt}],
+                    **({"temperature": creativity} if creativity is not None else {}),
                     tools=[{
                     "type": "web_search_20250305", 
                     "name": "web_search"
@@ -88,13 +88,43 @@ def build_web_research_dataset(
                         if getattr(block, "type", "") == "text"
                     ).strip()
                     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 == "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}]}],
+                        "tools": [{"google_search": {}}],
+                        **({"generationConfig": {"temperature": creativity}} if creativity is not None else {})
+                    }
+        
+                    response = requests.post(url, headers=headers, json=payload)
+                    response.raise_for_status()
+                    result = response.json()
+        
+                    # extract reply from Google's response structure
+                    if "candidates" in result and result["candidates"]:
+                        reply = result["candidates"][0]["content"]["parts"][0]["text"]
+                    else:
+                        reply = "No response generated"
+            
+                    link1.append(reply)
+        
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+
             else:
-                raise ValueError("Unknown source! Currently this function only supports 'Anthropic' as model_source.")
+                raise ValueError("Unknown source! Currently this function only supports 'Anthropic' or 'Google' as model_source.")
             # in situation that no JSON is found
             if reply is not None:
                 extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
@@ -126,7 +156,7 @@ def build_web_research_dataset(
             # Save progress so far
             temp_df = pd.DataFrame({
                 'survey_response': search_input[:idx+1],
-                'link1': link1,
+                'model_response': link1,
                 'json': extracted_jsons
             })
             # Normalize processed jsons so far

catllm/image_functions.py

@@ -5,7 +5,7 @@ def image_multi_class(
     categories,
     api_key,
     user_model="gpt-4o",
-    creativity=0,
+    creativity=None,
     to_csv=False,
     safety=False,
     filename="categorized_data.csv",
@@ -143,7 +143,7 @@ def image_multi_class(
                 response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 link1.append(reply)
@@ -162,8 +162,8 @@ def image_multi_class(
                 message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
-                    messages=[{"role": "user", "content": prompt}]
+                    messages=[{"role": "user", "content": prompt}],
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = message.content[0].text
                 link1.append(reply)
@@ -183,7 +183,7 @@ def image_multi_class(
                     messages=[
                     {'role': 'user', 'content': prompt}
                 ],
-                temperature=creativity
+                **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response.choices[0].message.content
                 link1.append(reply)
@@ -277,7 +277,7 @@ def image_score_drawing(
     api_key,
     columns="numbered",
     user_model="gpt-4o-2024-11-20",
-    creativity=0,
+    creativity=None,
     to_csv=False,
     safety=False,
     filename="categorized_data.csv",
@@ -442,7 +442,7 @@ def image_score_drawing(
                 response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 link1.append(reply)
@@ -460,8 +460,8 @@ def image_score_drawing(
                 message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
-                    messages=[{"role": "user", "content": prompt}]
+                    messages=[{"role": "user", "content": prompt}],
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = message.content[0].text  # Anthropic returns content as list
                 link1.append(reply)
@@ -481,7 +481,7 @@ def image_score_drawing(
                     messages=[
                     {'role': 'user', 'content': prompt}
                 ],
-                temperature=creativity
+                **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response.choices[0].message.content
                 link1.append(reply)
@@ -574,7 +574,7 @@ def image_features(
     features_to_extract,
     api_key,
     user_model="gpt-4o-2024-11-20",
-    creativity=0,
+    creativity=None,
     to_csv=False,
     safety=False,
     filename="categorized_data.csv",
@@ -715,7 +715,7 @@ def image_features(
                 response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 link1.append(reply)
@@ -733,7 +733,7 @@ def image_features(
                 response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 link1.append(reply)
@@ -751,8 +751,8 @@ def image_features(
                 message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
-                    messages=[{"role": "user", "content": prompt}]
+                    messages=[{"role": "user", "content": prompt}],
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = message.content[0].text  # Anthropic returns content as list
                 link1.append(reply)
@@ -772,7 +772,7 @@ def image_features(
                     messages=[
                     {'role': 'user', 'content': prompt}
                 ],
-                temperature=creativity
+                **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response.choices[0].message.content
                 link1.append(reply)

catllm/text_functions.py

@@ -8,7 +8,7 @@ def explore_corpus(
     cat_num=10,
     divisions=5,
     user_model="gpt-4o-2024-11-20",
-    creativity=0,
+    creativity=None,
     filename="corpus_exploration.csv",
     model_source="OpenAI"
 ):
@@ -57,7 +57,7 @@ Number your categories from 1 through {cat_num} and be concise with the category
                          The research question is: {research_question}""" if research_question else "You are a helpful assistant."},
                         {'role': 'user', 'content': prompt}
                     ],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 responses.append(reply)
@@ -107,7 +107,7 @@ def explore_common_categories(
     cat_num=10,
     divisions=5,
     user_model="gpt-4o",
-    creativity=0,
+    creativity=None,
     specificity="broad",
     research_question=None,
     filename=None,
@@ -158,7 +158,7 @@ Number your categories from 1 through {cat_num} and be concise with the category
                          The research question is: {research_question}""" if research_question else "You are a helpful assistant."},
                         {'role': 'user', 'content': prompt}
                     ],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                 reply = response_obj.choices[0].message.content
                 responses.append(reply)
@@ -225,7 +225,7 @@ def multi_class(
     categories,
     api_key,
     user_model="gpt-4o",
-    creativity=0,
+    creativity=None,
     safety=False,
     to_csv=False,
     filename="categorized_data.csv",
@@ -272,7 +272,7 @@ Provide your work in JSON format where the number belonging to each category is
                     response_obj = client.chat.completions.create(
                     model=user_model,
                     messages=[{'role': 'user', 'content': prompt}],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                     reply = response_obj.choices[0].message.content
                     link1.append(reply)
@@ -286,7 +286,7 @@ Provide your work in JSON format where the number belonging to each category is
                     response_obj = client.chat.completions.create(
                         model=user_model,
                         messages=[{'role': 'user', 'content': prompt}],
-                        temperature=creativity
+                        **({"temperature": creativity} if creativity is not None else {})
                     )
                     reply = response_obj.choices[0].message.content
                     link1.append(reply)
@@ -300,7 +300,7 @@ Provide your work in JSON format where the number belonging to each category is
                     message = client.messages.create(
                     model=user_model,
                     max_tokens=1024,
-                    temperature=creativity,
+                    **({"temperature": creativity} if creativity is not None else {})
                     messages=[{"role": "user", "content": prompt}]
                 )
                     reply = message.content[0].text  # Anthropic returns content as list
@@ -321,7 +321,8 @@ Provide your work in JSON format where the number belonging to each category is
                     payload = {
                         "contents": [{
                             "parts": [{"text": prompt}]
-                            }]
+                            }],
+                            **({"generationConfig": {"temperature": creativity}} if creativity is not None else {})
                             }
                     
                     response = requests.post(url, headers=headers, json=payload)
@@ -347,7 +348,7 @@ Provide your work in JSON format where the number belonging to each category is
                     messages=[
                         {'role': 'user', 'content': prompt}
                     ],
-                    temperature=creativity
+                    **({"temperature": creativity} if creativity is not None else {})
                 )
                     reply = response.choices[0].message.content
                     link1.append(reply)

cat_llm-0.0.58.dist-info/RECORD

@@ -1,15 +0,0 @@
-catllm/CERAD_functions.py,sha256=ZCKyCiv-2eUPzJ7Yhrz4Y0OJK4iEyWMnOUI7mFDsoEI,22471
-catllm/__about__.py,sha256=ls0j3CbC_fGEd6cnbBqQ1CGN6kJm_00v72c5EJ7Ko6s,404
-catllm/__init__.py,sha256=sf02zp7N0NW0mAQi7eQ4gliWR1EwoqvXkHN2HwwjcTE,372
-catllm/build_web_research.py,sha256=CYGhxnonJLBw80ATEBkpRjOKJgCYntHTgx4s4Pb8g88,6833
-catllm/image_functions.py,sha256=8dUpwHwVe4Vf06wjFNgLnh54q5upo4E-P87-TKaSECE,35519
-catllm/text_functions.py,sha256=EL-jbVX6GJ9MX4yULz_RJOOhsYEjooaEK5lAagTeyWY,18083
-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-0.0.58.dist-info/METADATA,sha256=bBX058D_9CyXe5zbeeHTcTWVZwgECQsXfGmJ5x22YNQ,22370
-cat_llm-0.0.58.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.58.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.58.dist-info/RECORD,,