cat-llm 0.0.36__tar.gz → 0.0.38__tar.gz

{cat_llm-0.0.36 → cat_llm-0.0.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.36
+Version: 0.0.38
 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
@@ -20,6 +20,7 @@ Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.8
 Requires-Dist: pandas
+Requires-Dist: pkg-resources
 Requires-Dist: tqdm
 Description-Content-Type: text/markdown
 
@@ -367,10 +368,10 @@ Processes each image individually, evaluating the drawn shapes based on CERAD cr
 - `user_model` (str, default="gpt-4o"): Specific model to use
 - `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
 - `reference_in_image` (bool, default=False): Whether a reference shape is present in the image for comparison
-- `provide_reference` (bool, default=False): Whether to provide a reference example image or description
+- `provide_reference` (bool, default=False): Whether to provide a reference example image (built in reference image)
 - `safety` (bool, default=False): Enable safety checks and save results at each API call step
 - `filename` (str, default="categorized_data.csv"): Filename for CSV output
-- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
+- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Mistral")
 
 **Returns:**
 - `pandas.DataFrame`: DataFrame with image paths, CERAD scores, and analysis details

{cat_llm-0.0.36 → cat_llm-0.0.38}/README.md

@@ -342,10 +342,10 @@ Processes each image individually, evaluating the drawn shapes based on CERAD cr
 - `user_model` (str, default="gpt-4o"): Specific model to use
 - `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
 - `reference_in_image` (bool, default=False): Whether a reference shape is present in the image for comparison
-- `provide_reference` (bool, default=False): Whether to provide a reference example image or description
+- `provide_reference` (bool, default=False): Whether to provide a reference example image (built in reference image)
 - `safety` (bool, default=False): Enable safety checks and save results at each API call step
 - `filename` (str, default="categorized_data.csv"): Filename for CSV output
-- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
+- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Mistral")
 
 **Returns:**
 - `pandas.DataFrame`: DataFrame with image paths, CERAD scores, and analysis details

{cat_llm-0.0.36 → cat_llm-0.0.38}/pyproject.toml

@@ -26,7 +26,8 @@ classifiers = [
 ]
 dependencies = [
   "pandas",
-  "tqdm"
+  "tqdm",
+  "pkg_resources"
 ]
 
 [project.urls]

{cat_llm-0.0.36 → cat_llm-0.0.38}/src/catllm/CERAD_functions.py

@@ -165,14 +165,13 @@ def cerad_drawn_score(
             if provide_reference:
                 prompt.append({
                     "type": "image_url", 
-                    "image_url": {"url": reference_image, "detail": "high"}
+                    "image_url": {"url": encoded_ref_image, "detail": "high"}
                 })
                                 
             prompt.append({
                 "type": "image_url",
                 "image_url": {"url": encoded_image, "detail": "high"}
             })
-            print(prompt)   
         
         elif model_source == "Anthropic":
             prompt = [
@@ -190,16 +189,29 @@ def cerad_drawn_score(
                         f"Example:\n"
                         f"{example_JSON}"
                     ),
-                },
-                {
+                }
+            ]
+
+            if provide_reference:
+                prompt.append({
+                    "type": "image",
+                    "source": {
+                        "type": "base64",
+                        "media_type": "image/png",
+                        "data": encoded_ref
+                    }
+                }
+                )
+
+            prompt.append({
                     "type": "image",
                     "source": {
                         "type": "base64",
                         "media_type": "image/jpeg",
                         "data": encoded
                     }
-                    }
-            ]
+            }
+            )
 
         elif model_source == "Mistral":
             prompt = [
@@ -217,12 +229,18 @@ def cerad_drawn_score(
                         f"Example:\n"
                         f"{example_JSON}"
                     ),
-                },
-                {
-                    "type": "image_url",
-                    "image_url": f"data:image/jpeg;base64,{encoded}"
                 }
             ]
+            if provide_reference:
+                prompt.append({
+                    "type": "image_url",
+                    "image_url": f"data:image/{ext};base64,{encoded_ref}"
+                })
+
+            prompt.append({
+                "type": "image_url",
+                "image_url": f"data:image/{ext};base64,{encoded_image}"
+            })
             
         if model_source == "OpenAI":
             from openai import OpenAI

{cat_llm-0.0.36 → cat_llm-0.0.38}/src/catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.36"
+__version__ = "0.0.38"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"