cat-llm 0.0.79__py3-none-any.whl → 0.0.81__py3-none-any.whl

{cat_llm-0.0.79.dist-info → cat_llm-0.0.81.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.79
+Version: 0.0.81
 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-0.0.79.dist-info → cat_llm-0.0.81.dist-info}/RECORD

@@ -1,10 +1,10 @@
 catllm/CERAD_functions.py,sha256=q4HbP5e2Yu8NnZZ-2eX4sImyj6u3i8xWcq0pYU81iis,22676
-catllm/__about__.py,sha256=Hhks3oZjWJZKC5zFBlb8LHrC6eHYOJbln8mQEulNQCA,430
+catllm/__about__.py,sha256=JWaGFu-r637kdvMsJcvfun8_Hi3c_vhw4yi-_YOGtzo,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=GilnjNlmnyvLfX1_jzx41q--ZzABuYtrGMTOFmioreY,35750
+catllm/text_functions.py,sha256=2qyYqB2hwKFXOKn9RaGssCsVIri9uvdWmsNZhiabT_I,37154
 catllm/calls/CoVe.py,sha256=Y9OGJbaeJ3Odwira92cPXUlnm_ADFqvpOSFSNjFzMMU,10847
 catllm/calls/__init__.py,sha256=fWuMwLeSGa6zXJYd4s8IyNblsD62G-1NMUsOKrNIkoI,725
 catllm/calls/all_calls.py,sha256=15xvGSCwVQGVsrAWgn0alLuZblEYOUgIhpbzUM_875w,16592
@@ -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-0.0.79.dist-info/METADATA,sha256=Sj-3ZGOC4EhurRauEjEcumuNndYIjdeltub5lagezGY,23214
-cat_llm-0.0.79.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.79.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.79.dist-info/RECORD,,
+cat_llm-0.0.81.dist-info/METADATA,sha256=_9i0JqmzSGLnQQmbrmR0hg2oFcoU6SG8MaJwAKAwhWk,23214
+cat_llm-0.0.81.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.81.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.81.dist-info/RECORD,,

catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.79"
+__version__ = "0.0.81"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

catllm/text_functions.py

@@ -8,7 +8,7 @@ from .calls.all_calls import (
     chain_of_verification_anthropic,
     chain_of_verification_mistral,
     get_openai_top_n,
-    get_anthropic_top_n,
+    get_anthropic_top_n
 )
 
 
@@ -114,7 +114,6 @@ Number your categories from 1 through {cat_num} and be concise with the category
     
     return df
 
-#extract top categories from corpus
 #extract top categories from corpus
 def explore_common_categories(
     survey_question, 
@@ -168,15 +167,28 @@ Number your categories from 1 through {cat_num} and be concise with the category
         
         if model_source == "openai":
             try:
-                reply = get_openai_top_n(
-                    prompt=prompt,
-                    user_model=user_model,
-                    specificity=specificity,
-                    api_key=api_key,
-                    model_source=model_source,
-                    research_question=research_question,
-                    creativity=creativity
+                from openai import OpenAI
+
+                base_url = (
+                    "https://api.perplexity.ai" if model_source == "perplexity" 
+                    else "https://router.huggingface.co/v1" if model_source == "huggingface"
+                    else None
+                )
+
+                client = OpenAI(api_key=api_key, base_url=base_url)
+
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[
+                        {'role': 'system', 'content': f"""You are a helpful assistant that extracts categories from survey responses. \
+                                        The specific task is to identify {specificity} categories of responses to a survey question. \
+                                        The research question is: {research_question}""" if research_question else "You are a helpful assistant."},
+                        {'role': 'user', 'content': prompt}
+                        ],
+                        **({"temperature": creativity} if creativity is not None else {})
                 )
+    
+                reply = response_obj.choices[0].message.content
 
                 responses.append(reply)
 
@@ -192,16 +204,29 @@ Number your categories from 1 through {cat_num} and be concise with the category
 
         elif model_source == "anthropic":
             
-            reply = get_anthropic_top_n(
-                prompt=prompt,
-                user_model=user_model,
-                specificity=specificity,
-                model_source=model_source,
-                api_key=api_key,
-                research_question=research_question,
-                creativity=creativity
+            import anthropic
+            client = anthropic.Anthropic(api_key=api_key)
+
+            # Build system prompt
+            if research_question:
+                system_content = (f"You are a helpful assistant that extracts categories from survey responses. "
+                        f"The specific task is to identify {specificity} categories of responses to a survey question. "
+                        f"The research question is: {research_question}")
+            else:
+                system_content = "You are a helpful assistant."
+    
+            response_obj = client.messages.create(
+                model=user_model,
+                max_tokens=4096,
+                system=system_content,
+                messages=[
+                    {'role': 'user', 'content': prompt}
+                ],
+                **({"temperature": creativity} if creativity is not None else {})
             )
 
+            reply = response_obj.content[0].text
+    
             responses.append(reply)
         else:
             raise ValueError(f"Unsupported model_source: {model_source}")