cat-llm 0.0.62__py3-none-any.whl → 0.0.63__py3-none-any.whl

{cat_llm-0.0.62.dist-info → cat_llm-0.0.63.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.62
+Version: 0.0.63
 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-0.0.62.dist-info → cat_llm-0.0.63.dist-info}/RECORD

@@ -1,15 +1,15 @@
-catllm/CERAD_functions.py,sha256=05n7h27TuAp3klkOnrH--m1wMreYqYuObM9NIab934o,22603
-catllm/__about__.py,sha256=R0Mt1NOAMAQCF7SHD4XDl2P4gF92EnfjYXaJ1Xo0vdc,408
+catllm/CERAD_functions.py,sha256=q4HbP5e2Yu8NnZZ-2eX4sImyj6u3i8xWcq0pYU81iis,22676
+catllm/__about__.py,sha256=NCCTWpJ4xKqiFOIwB1tnv4BLyeGVzeNfFegpbJQicgw,408
 catllm/__init__.py,sha256=sf02zp7N0NW0mAQi7eQ4gliWR1EwoqvXkHN2HwwjcTE,372
 catllm/build_web_research.py,sha256=nAKfkg7lihjXrYrLvltsKCvpb5zRFYpNp95A-0zpDb8,9159
-catllm/image_functions.py,sha256=KDb2UxDLrioerlqKZjKAX7lqfW-S_TSQCK6YxtJRKwI,35958
-catllm/text_functions.py,sha256=xfpwAYivnPnDlsU21vp1Pma9mDR24tn1lcBZQfsyIrc,18467
+catllm/image_functions.py,sha256=8_FftRU285x1HT-AgNkaobefQVD-5q7ZY_t7JFdL3Sg,36177
+catllm/text_functions.py,sha256=Jf51lNaFtcS2QGnNLkhM8rFVJSD4tN0Bm_VfELvb47g,18686
 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-0.0.62.dist-info/METADATA,sha256=jstvau7l_g2KqYSheIcZJxC8DX2Bf_lA_wLNzPO5-qw,22395
-cat_llm-0.0.62.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-cat_llm-0.0.62.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
-cat_llm-0.0.62.dist-info/RECORD,,
+cat_llm-0.0.63.dist-info/METADATA,sha256=y9kIgflPVthWZEiNVkabYIJ8p82IW-pO4FliuS5T8AE,22395
+cat_llm-0.0.63.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+cat_llm-0.0.63.dist-info/licenses/LICENSE,sha256=Vje2sS5WV4TnIwY5uQHrF4qnBAM3YOk1pGpdH0ot-2o,34969
+cat_llm-0.0.63.dist-info/RECORD,,

catllm/CERAD_functions.py

@@ -44,6 +44,8 @@ def cerad_drawn_score(
     from pathlib import Path
     import pkg_resources
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     shape = shape.lower()
     shape = "rectangles" if shape == "overlapping rectangles" else shape
     if shape == "circle":
@@ -155,7 +157,7 @@ def cerad_drawn_score(
         else:
             reference_text = f"Image is expected to show within it a drawing of a {shape}.\n\n"
 
-        if model_source == "OpenAI" and valid_image:
+        if model_source == "openai" and valid_image:
             prompt = [
                 {
                     "type": "text",
@@ -185,7 +187,7 @@ def cerad_drawn_score(
                 "image_url": {"url": encoded_image, "detail": "high"}
             })
         
-        elif model_source == "Anthropic" and valid_image:
+        elif model_source == "anthropic" and valid_image:
             prompt = [
                 {
                     "type": "text",
@@ -225,7 +227,7 @@ def cerad_drawn_score(
             }
             )
 
-        elif model_source == "Mistral" and valid_image:
+        elif model_source == "mistral" and valid_image:
             prompt = [
                 {
                     "type": "text",
@@ -254,7 +256,7 @@ def cerad_drawn_score(
                 "image_url": f"data:image/{ext};base64,{encoded_image}"
             })
 
-        if model_source == "OpenAI" and valid_image:
+        if model_source == "openai" and valid_image:
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
             try:
@@ -272,7 +274,7 @@ def cerad_drawn_score(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Anthropic"  and valid_image:
+        elif model_source == "anthropic"  and valid_image:
             import anthropic
             client = anthropic.Anthropic(api_key=api_key)
             try:
@@ -291,7 +293,7 @@ def cerad_drawn_score(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Mistral"  and valid_image:
+        elif model_source == "mistral"  and valid_image:
             from mistralai import Mistral
             reply = None
             client = Mistral(api_key=api_key)

catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.62"
+__version__ = "0.0.63"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

catllm/image_functions.py

@@ -33,6 +33,8 @@ def image_multi_class(
     '*.psd'
     ]
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     if not isinstance(image_input, list):
         # If image_input is a filepath (string)
         image_files = []
@@ -86,7 +88,7 @@ def image_multi_class(
     
     # Handle extension safely
         ext = Path(img_path).suffix.lstrip(".").lower()
-        if model_source == "OpenAI" or model_source == "Mistral":
+        if model_source == "openai" or model_source == "mistral":
             encoded_image = f"data:image/{ext};base64,{encoded}"
             prompt = [
                 {
@@ -110,7 +112,7 @@ def image_multi_class(
                 },
             ]
             
-        elif model_source == "Anthropic":
+        elif model_source == "anthropic":
             encoded_image = f"data:image/{ext};base64,{encoded}"
             prompt = [
                 {"type": "text",
@@ -136,7 +138,7 @@ def image_multi_class(
                     }
                 }
             ]
-        if model_source == "OpenAI":
+        if model_source == "openAI":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
             try:
@@ -154,7 +156,7 @@ def image_multi_class(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Anthropic":
+        elif model_source == "anthropic":
             import anthropic
             reply = None
             client = anthropic.Anthropic(api_key=api_key)
@@ -174,7 +176,7 @@ def image_multi_class(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Mistral":
+        elif model_source == "mistral":
             from mistralai import Mistral
             client = Mistral(api_key=api_key)
             try:
@@ -305,6 +307,8 @@ def image_score_drawing(
     '*.psd'
     ]
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     if not isinstance(image_input, list):
         # If image_input is a filepath (string)
         image_files = []
@@ -354,7 +358,7 @@ def image_score_drawing(
         ext = Path(img_path).suffix.lstrip(".").lower()
         encoded_image = f"data:image/{ext};base64,{encoded}"
 
-        if model_source == "OpenAI" or model_source == "Mistral":
+        if model_source == "openai" or model_source == "mistral":
             prompt = [
                 {
                     "type": "text",
@@ -390,7 +394,7 @@ def image_score_drawing(
                 }
             ]
 
-        elif model_source == "Anthropic":  # Changed to elif
+        elif model_source == "anthropic":  # Changed to elif
             prompt = [
                 {
                     "type": "text",
@@ -435,7 +439,7 @@ def image_score_drawing(
             ]
 
             
-        if model_source == "OpenAI":
+        if model_source == "openai":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
             try:
@@ -453,7 +457,7 @@ def image_score_drawing(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Anthropic":
+        elif model_source == "anthropic":
             import anthropic
             client = anthropic.Anthropic(api_key=api_key)
             try:
@@ -472,7 +476,7 @@ def image_score_drawing(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Mistral":
+        elif model_source == "mistral":
             from mistralai import Mistral
             client = Mistral(api_key=api_key)
             try:
@@ -598,6 +602,8 @@ def image_features(
     '*.psd'
     ]
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     if not isinstance(image_input, list):
         # If image_input is a filepath (string)
         image_files = []
@@ -644,7 +650,7 @@ def image_features(
             encoded_image = f"data:image/{ext};base64,{encoded}"
             valid_image = True
 
-        if model_source == "OpenAI" or model_source == "Mistral":
+        if model_source == "openai" or model_source == "mistral":
             prompt = [
                 {
                     "type": "text",
@@ -674,7 +680,7 @@ def image_features(
                             "image_url": {"url": encoded_image, "detail": "high"},
                             },
             ]
-        elif model_source == "Anthropic":
+        elif model_source == "anthropic":
             prompt = [
                 {
                     "type": "text",
@@ -708,7 +714,7 @@ def image_features(
                     }
                 }
             ]
-        if model_source == "OpenAI":
+        if model_source == "openai":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
             try:
@@ -726,7 +732,7 @@ def image_features(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Perplexity":
+        elif model_source == "perplexity":
             from openai import OpenAI
             client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
             try:
@@ -744,7 +750,7 @@ def image_features(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Anthropic":
+        elif model_source == "anthropic":
             import anthropic
             client = anthropic.Anthropic(api_key=api_key)
             try:
@@ -763,7 +769,7 @@ def image_features(
                     print("An error occurred: {e}")
                     link1.append("Error processing input: {e}")
 
-        elif model_source == "Mistral":
+        elif model_source == "mistral":
             from mistralai import Mistral
             client = Mistral(api_key=api_key)
             try:

catllm/text_functions.py

@@ -22,6 +22,8 @@ def explore_corpus(
     print(f"Exploring class for question: '{survey_question}'.\n          {cat_num * divisions} unique categories to be extracted.")
     print()
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     chunk_size = round(max(1, len(survey_input) / divisions),0)
     chunk_size = int(chunk_size)
 
@@ -46,7 +48,7 @@ Responses are each separated by a semicolon. \
 Responses are contained within triple backticks here: ```{survey_participant_chunks}``` \
 Number your categories from 1 through {cat_num} and be concise with the category labels and provide no description of the categories."""
         
-        if model_source == "OpenAI":
+        if model_source == "openai":
             client = OpenAI(api_key=api_key)
             try:
                 response_obj = client.chat.completions.create(
@@ -123,6 +125,8 @@ def explore_common_categories(
     print(f"Exploring class for question: '{survey_question}'.\n          {cat_num * divisions} unique categories to be extracted and {top_n} to be identified as the most common.")
     print()
 
+    model_source = model_source.lower() # eliminating case sensitivity 
+
     chunk_size = round(max(1, len(survey_input) / divisions),0)
     chunk_size = int(chunk_size)
 
@@ -147,7 +151,7 @@ Responses are each separated by a semicolon. \
 Responses are contained within triple backticks here: ```{survey_participant_chunks}``` \
 Number your categories from 1 through {cat_num} and be concise with the category labels and provide no description of the categories."""
         
-        if model_source == "OpenAI":
+        if model_source == "openai":
             client = OpenAI(api_key=api_key)
             try:
                 response_obj = client.chat.completions.create(
@@ -198,7 +202,7 @@ Number your categories from 1 through {cat_num} and be concise with the category
 The categories are contained within triple backticks here: ```{df['Category'].tolist()}``` \
 Return the top {top_n} categories as a numbered list sorted from the most to least common and keep the categories {specificity}, with no additional text or explanation."""
         
-    if model_source == "OpenAI":
+    if model_source == "openai":
         client = OpenAI(api_key=api_key)
         response_obj = client.chat.completions.create(
             model=user_model,
@@ -237,6 +241,8 @@ def multi_class(
     import pandas as pd
     import regex
     from tqdm import tqdm
+
+    model_source = model_source.lower() # eliminating case sensitivity 
     
     categories_str = "\n".join(f"{i + 1}. {cat}" for i, cat in enumerate(categories))
     cat_num = len(categories)
@@ -265,7 +271,7 @@ Categorize this survey response "{response}" into the following categories that
 {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)
-            if model_source == ("OpenAI"):
+            if model_source == ("openai"):
                 from openai import OpenAI
                 client = OpenAI(api_key=api_key)
                 try:
@@ -279,7 +285,7 @@ Provide your work in JSON format where the number belonging to each category is
                 except Exception as e:
                     print(f"An error occurred: {e}")
                     link1.append(f"Error processing input: {e}")
-            elif model_source == "Perplexity":
+            elif model_source == "perplexity":
                 from openai import OpenAI
                 client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
                 try:
@@ -293,7 +299,7 @@ Provide your work in JSON format where the number belonging to each category is
                 except Exception as e:
                     print(f"An error occurred: {e}")
                     link1.append(f"Error processing input: {e}")
-            elif model_source == "Anthropic":
+            elif model_source == "anthropic":
                 import anthropic
                 client = anthropic.Anthropic(api_key=api_key)
                 try:
@@ -309,7 +315,7 @@ Provide your work in JSON format where the number belonging to each category is
                     print(f"An error occurred: {e}")
                     link1.append(f"Error processing input: {e}")
                     
-            elif model_source == "Google":
+            elif model_source == "google":
                 import requests
                 url = f"https://generativelanguage.googleapis.com/v1beta/models/{user_model}:generateContent"
                 try:
@@ -339,7 +345,7 @@ Provide your work in JSON format where the number belonging to each category is
                     print(f"An error occurred: {e}")
                     link1.append(f"Error processing input: {e}")
 
-            elif model_source == "Mistral":
+            elif model_source == "mistral":
                 from mistralai import Mistral
                 client = Mistral(api_key=api_key)
                 try: