cat-llm 0.0.75__py3-none-any.whl → 0.0.77__py3-none-any.whl

{cat_llm-0.0.75.dist-info → cat_llm-0.0.77.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.75
+Version: 0.0.77
 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-0.0.75.dist-info → cat_llm-0.0.77.dist-info}/RECORD

@@ -1,10 +1,10 @@
 catllm/CERAD_functions.py,sha256=q4HbP5e2Yu8NnZZ-2eX4sImyj6u3i8xWcq0pYU81iis,22676
-catllm/__about__.py,sha256=v46F-9gCzROey89qHYByH-uJth4LZKkHhUfnitLnzzo,430
+catllm/__about__.py,sha256=7ns6QhLryp-E7SvdG6rrirf5LNNgvqmDLZk-zvKaZRY,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=Gj0BrhprOMBgLpuJByG3woqFclYFLNjbK_4jh72ZOo8,35355
+catllm/text_functions.py,sha256=OHlWdErhUG6YPJKk-9vAR-jY3gj2zb5MOy3P0cJu_Fc,35714
 catllm/calls/CoVe.py,sha256=Y9OGJbaeJ3Odwira92cPXUlnm_ADFqvpOSFSNjFzMMU,10847
 catllm/calls/__init__.py,sha256=fWuMwLeSGa6zXJYd4s8IyNblsD62G-1NMUsOKrNIkoI,725
 catllm/calls/all_calls.py,sha256=AeN1QocOvL3Z36lDkq6bO0LB3ruz6pXyedvdci0YCxQ,16627
@@ -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-0.0.75.dist-info/METADATA,sha256=f20lG5JACNATG6u4tv7DWxShs86UHU_JgWmE74S803I,23214
-cat_llm-0.0.75.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.75.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.75.dist-info/RECORD,,
+cat_llm-0.0.77.dist-info/METADATA,sha256=Z2QqNq_gV_9RDkbG1c7R40qILnkqIk640pqToPZxCDc,23214
+cat_llm-0.0.77.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.77.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.77.dist-info/RECORD,,

catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.75"
+__version__ = "0.0.77"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

catllm/text_functions.py

@@ -313,14 +313,7 @@ Number your categories from 1 through {cat_num} and be concise with the category
     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
+# GOAL: enable self-consistency
 def multi_class(
     survey_input,
     categories,
@@ -341,6 +334,10 @@ def multi_class(
     chain_of_thought = True,
     step_back_prompt = False,
     context_prompt = False,
+    top_n = 12,
+    cat_num = 10,
+    divisions = 10,
+    research_question = None,
     filename = "categorized_data.csv",
     save_directory = None,
     model_source = "auto"
@@ -351,6 +348,7 @@ def multi_class(
     import regex
     from tqdm import tqdm
 
+    #used in chain of verification 
     def remove_numbering(line):
         line = line.strip()
     
@@ -399,16 +397,35 @@ def multi_class(
             raise ValueError(f"❌ Could not auto-detect model source from '{user_model}'. Please specify model_source explicitly: OpenAI, Anthropic, Perplexity, Google, Huggingface, or Mistral")
     else:
         model_source = model_source.lower()
-    
+
+    if categories == "auto":
+        if survey_question == "": # step back requires the survey question to function well
+            raise TypeError("survey_question is required when using step_back_prompt. Please provide the survey question you are analyzing.")
+
+        categories = explore_common_categories(
+            survey_question=survey_question,
+            survey_input=survey_input,
+            research_question=research_question,
+            api_key=api_key,
+            model_source=model_source,
+            user_model=user_model,
+            top_n=top_n,
+            cat_num=cat_num,
+            divisions=divisions
+        )
+        
     categories_str = "\n".join(f"{i + 1}. {cat}" for i, cat in enumerate(categories))
     cat_num = len(categories)
     category_dict = {str(i+1): "0" for i in range(cat_num)}
     example_JSON = json.dumps(category_dict, indent=4)
 
-    # ensure number of categories is what user wants
     print(f"\nThe categories you entered to be coded by {model_source} {user_model}:")
-    for i, cat in enumerate(categories, 1):
-        print(f"{i}. {cat}")
+
+    if categories != "auto":
+    # ensure number of categories is what user wants
+
+        for i, cat in enumerate(categories, 1):
+            print(f"{i}. {cat}")
     
     link1 = []
     extracted_jsons = []