cat-llm 0.0.73__py3-none-any.whl → 0.0.74__py3-none-any.whl

{cat_llm-0.0.73.dist-info → cat_llm-0.0.74.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.73
+Version: 0.0.74
 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
@@ -200,6 +200,7 @@ Processes each text response individually, assigning one or more categories from
 - `safety` (bool, default=False): Enable safety checks on responses and saves to CSV at each API call step
 - `to_csv` (bool, default=False): Whether to save results to CSV
 - `chain_of_verification` (bool, default=False): Enable Chain-of-Verification prompting technique for improved accuracy
+- `chain_of_thought` (bool, default=False): Enable Chain-of-Thought prompting technique for improved accuracy
 - `step_back_prompt` (bool, default=False): Enable step-back prompting to analyze higher-level context before classification
 - `context_prompt` (bool, default=False): Add expert role and behavioral guidelines to the prompt
 - `filename` (str, default="categorized_data.csv"): Filename for CSV output

{cat_llm-0.0.73.dist-info → cat_llm-0.0.74.dist-info}/RECORD

@@ -1,10 +1,10 @@
 catllm/CERAD_functions.py,sha256=q4HbP5e2Yu8NnZZ-2eX4sImyj6u3i8xWcq0pYU81iis,22676
-catllm/__about__.py,sha256=QIxgPsG9zGrIHx80hZ1HkOlxVi_F52MocXySU5cHB7Q,430
+catllm/__about__.py,sha256=E0enlOPQDj7XaMZv62lffULZGOUEAqpRIyZ12A6f3zk,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/model_reference_list.py,sha256=37pWwMcgnf4biE3BVRluH5oz2P6ccdJJiCVNHodBH8k,2307
-catllm/text_functions.py,sha256=Yhb4ukFjNE9jHFdDC8Qa9rFhYAiyS6FTwAM7pG5TzR8,32521
+catllm/text_functions.py,sha256=O6wfDh50Xtc0JvQtjWb9L9PgtBP6cjxWBw-PCNmbiaE,33371
 catllm/calls/CoVe.py,sha256=Y9OGJbaeJ3Odwira92cPXUlnm_ADFqvpOSFSNjFzMMU,10847
 catllm/calls/__init__.py,sha256=fWuMwLeSGa6zXJYd4s8IyNblsD62G-1NMUsOKrNIkoI,725
 catllm/calls/all_calls.py,sha256=E25KpZ_MakMDeCpNCOOM8kQvlfex6UMjnGN1wHkA4AI,14356
@@ -13,7 +13,7 @@ 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-0.0.73.dist-info/METADATA,sha256=bLNW2lUDfJ32VOX56JglxWRszev6oYXTNvGSn80CyWo,23104
-cat_llm-0.0.73.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.73.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.73.dist-info/RECORD,,
+cat_llm-0.0.74.dist-info/METADATA,sha256=DYaL_OFgi9MuFpWLd1DHgqVi_osTwK1DJH-E5Q2kaa8,23214
+cat_llm-0.0.74.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.74.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.74.dist-info/RECORD,,

catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.73"
+__version__ = "0.0.74"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

catllm/text_functions.py

@@ -260,6 +260,7 @@ def multi_class(
     safety = False,
     to_csv = False,
     chain_of_verification = False,
+    chain_of_thought = True,
     step_back_prompt = False,
     context_prompt = False,
     filename = "categorized_data.csv",
@@ -397,12 +398,27 @@ def multi_class(
             extracted_jsons.append(default_json)
             #print(f"Skipped NaN input.")
         else:
+            if chain_of_thought:
+                prompt = f"""{survey_question_context}
 
-            prompt = f"""{survey_question_context} \
-            Categorize this survey response "{response}" into the following categories that apply: \
-            {categories_str}
-            {examples_text}
-            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."""
+                Categorize this survey response "{response}" into the following categories that apply: 
+                {categories_str}
+
+                Let's think step by step:
+                1. First, identify the main themes mentioned in the response
+                2. Then, match each theme to the relevant categories
+                3. Finally, assign 1 to matching categories and 0 to non-matching categories
+
+                {examples_text}
+
+                Provide your reasoning for each category, then provide your final answer 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."""
+            else:
+
+                prompt = f"""{survey_question_context} \
+                Categorize this survey response "{response}" into the following categories that apply: \
+                {categories_str}
+                {examples_text}
+                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."""
 
             if context_prompt:
                 context = """You are an expert researcher in survey data categorization.