cat-llm 0.0.65__py3-none-any.whl → 0.0.67__py3-none-any.whl

{cat_llm-0.0.65.dist-info → cat_llm-0.0.67.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.65
+Version: 0.0.67
 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-0.0.65.dist-info → cat_llm-0.0.67.dist-info}/RECORD

@@ -1,15 +1,15 @@
 catllm/CERAD_functions.py,sha256=q4HbP5e2Yu8NnZZ-2eX4sImyj6u3i8xWcq0pYU81iis,22676
-catllm/__about__.py,sha256=QeI7x2I4oYiFhztRrDnRvZOLW_kEShiCK7Y_hax8U8o,408
+catllm/__about__.py,sha256=hIVt-fQydvImRffcCyiHlTFeOR5F2aEchTWXAsWTPc4,430
 catllm/__init__.py,sha256=sf02zp7N0NW0mAQi7eQ4gliWR1EwoqvXkHN2HwwjcTE,372
 catllm/build_web_research.py,sha256=880dfE2bEQb-FrXP-42JoLLtyc9ox_sBULDr38xiTiQ,22655
 catllm/image_functions.py,sha256=8_FftRU285x1HT-AgNkaobefQVD-5q7ZY_t7JFdL3Sg,36177
-catllm/text_functions.py,sha256=Jf51lNaFtcS2QGnNLkhM8rFVJSD4tN0Bm_VfELvb47g,18686
+catllm/text_functions.py,sha256=_GMretLVBUs0ntL-wV6My0TRAvzvaPo_WU9ZqXlKxeM,19426
 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-0.0.65.dist-info/METADATA,sha256=77WCioobgfzMsP_o76XHbRncfNrXYayxFgZDrUVFv7k,22423
-cat_llm-0.0.65.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.65.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.65.dist-info/RECORD,,
+cat_llm-0.0.67.dist-info/METADATA,sha256=UR95eJdArTmJe6A2g2hH0Q9mZ9PkEQsJ2kVSg3KfQe4,22423
+cat_llm-0.0.67.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.67.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.67.dist-info/RECORD,,

catllm/__about__.py

@@ -1,10 +1,10 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.65"
+__version__ = "0.0.67"
 __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"
+__description__ = "An AI tool for categorizing and exploring text data, images, and building high quality datasets from the web."
 __url__ = "https://github.com/chrissoria/cat-llm" 
 __license__ = "GPL-3.0"

catllm/text_functions.py

@@ -7,7 +7,7 @@ def explore_corpus(
     specificity="broad",
     cat_num=10,
     divisions=5,
-    user_model="gpt-4o-2024-11-20",
+    user_model="gpt-5",
     creativity=None,
     filename="corpus_exploration.csv",
     model_source="OpenAI"
@@ -108,7 +108,7 @@ def explore_common_categories(
     top_n=10,
     cat_num=10,
     divisions=5,
-    user_model="gpt-4o",
+    user_model="gpt-5",
     creativity=None,
     specificity="broad",
     research_question=None,
@@ -223,12 +223,27 @@ Return the top {top_n} categories as a numbered list sorted from the most to lea
     return top_categories_final
 
 #multi-class text classification
+# what this function does:
+# does context prompting, giving the model a background on the task at hand and the user's survey question
+# system prompting, overall context and purpose for the language model
+# role prompting, assings a spacific identity to the model
+# also enables few shot prompting, allowing the user to input a few examples
+# provides POSITIVE INSTRUCTIONS reather than limitations/restrictions
+# GOAL: enable step-back prompting
+# GOAL 2: enable self-consistency
 def multi_class(
     survey_question, 
     survey_input,
     categories,
     api_key,
-    user_model="gpt-4o",
+    user_model="gpt-5",
+    user_prompt = None,
+    example1 = None,
+    example2 = None,
+    example3 = None,
+    example4 = None,
+    example5 = None,
+    example6 = None,
     creativity=None,
     safety=False,
     to_csv=False,
@@ -256,6 +271,11 @@ def multi_class(
     
     link1 = []
     extracted_jsons = []
+    #handling example inputs
+    examples = [example1, example2, example3, example4, example5, example6]
+    examples_text = "\n".join(
+    f"Example {i}: {ex}" for i, ex in enumerate(examples, 1) if ex is not None
+)
 
     for idx, response in enumerate(tqdm(survey_input, desc="Categorizing responses")):
         reply = None  
@@ -266,11 +286,13 @@ def multi_class(
             extracted_jsons.append(default_json)
             #print(f"Skipped NaN input.")
         else:
+
             prompt = f"""A respondent was asked: {survey_question}. \
-Categorize this survey response "{response}" into the following categories that apply: \
-{categories_str} \
-Provide your work in JSON format where the number belonging to each category is the key and a 1 if the category is present and a 0 if it is not present as key values."""
-            #print(prompt)
+            Categorize this survey response "{response}" into the following categories that apply: \
+            {categories_str}
+            {examples_text}
+            Provide your work in JSON format..."""
+
             if model_source == ("openai"):
                 from openai import OpenAI
                 client = OpenAI(api_key=api_key)