# catllm
[](https://pypi.org/project/cat-llm)
[](https://pypi.org/project/cat-llm)
-----
## Table of Contents
- [Installation](#installation)
- [Quick Start](#quick-start)
- [Configuration](#configuration)
- [Supported Models](#supported-models)
- [API Reference](#api-reference)
- [explore_corpus()](#explore_corpus)
- [explore_common_categories()](#explore_common_categories)
- [multi_class()](#multi_class)
- [image_score()](#image_score)
- [image_features()](#image_features)
- [cerad_drawn_score()](#cerad_drawn_score)
- [Academic Research](#academic-research)
- [License](#license)
## Installation
```console
pip install cat-llm
```
## Quick Start
CatLLM helps social scientists and demographers automatically categorize open-ended survey responses using AI models like GPT-4 and Claude.
Simply provide your survey responses and category list - the package handles the rest and outputs clean data ready for statistical analysis. It works with single or multiple categories per response and automatically skips missing data to save API costs.
Perfect for turning messy text data into structured categories you can actually analyze.
## Configuration
### Get Your OpenAI API Key
1. **Create an OpenAI Developer Account**:
- Go to [platform.openai.com](https://platform.openai.com) (separate from regular ChatGPT)
- Sign up with email, Google, Microsoft, or Apple
2. **Generate an API Key**:
- Log into your account and click your name in the top right corner
- Click "View API keys" or navigate to the "API keys" section
- Click "Create new secret key"
- Give your key a descriptive name
- Set permissions (choose "All" for full access)
3. **Add Payment Details**:
- Add a payment method to your OpenAI account
- Purchase credits (start with $5 - it lasts a long time for most research use)
- **Important**: Your API key won't work without credits
4. **Save Your Key Securely**:
- Copy the key immediately (you won't be able to see it again)
- Store it safely and never share it publicly
5. Copy and paste your key into catllm in the api_key parameter
## Supported Models
- **OpenAI**: GPT-4o, GPT-4, GPT-3.5-turbo, etc.
- **Anthropic**: Claude Sonnet 3.7, Claude Haiku, etc.
- **Perplexity**: Sonnar Large, Sonnar Small, etc.
- **Mistral**: Mistral Large, Mistral Small, etc.
## API Reference
### `explore_corpus()`
Extracts categories from a corpus of text responses and returns frequency counts.
**Methodology:**
The function divides the corpus into random chunks to address the probabilistic nature of LLM outputs. By processing multiple chunks and averaging results across many API calls rather than relying on a single call, this approach significantly improves reproducibility and provides more stable categorical frequency estimates.
**Parameters:**
- `survey_question` (str): The survey question being analyzed
- `survey_input` (list): List of text responses to categorize
- `api_key` (str): API key for the LLM service
- `cat_num` (int, default=10): Number of categories to extract in each iteration
- `divisions` (int, default=5): Number of chunks to divide the data into (larger corpora might require larger divisions)
- `specificity` (str, default="broad"): Category precision level (e.g., "broad", "narrow")
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
- `user_model` (str, default="got-4o"): Specific model (e.g., "gpt-4o", "claude-opus-4-20250514")
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `filename` (str, optional): Output file path for saving results
**Returns:**
- `pandas.DataFrame`: Two-column dataset with category names and frequencies
**Example:***
```
import catllm as cat
categories = cat.explore_corpus(
survey_question="What motivates you most at work?",
survey_input=["flexible schedule", "good pay", "interesting projects"],
api_key="OPENAI_API_KEY",
cat_num=5,
divisions=10
)
```
### `explore_common_categories()`
Identifies the most frequently occurring categories across a text corpus and returns the top N categories by frequency count.
**Methodology:**
Divides the corpus into random chunks and averages results across multiple API calls to improve reproducibility and provide stable frequency estimates for the most prevalent categories, addressing the probabilistic nature of LLM outputs.
**Parameters:**
- `survey_question` (str): Survey question being analyzed
- `survey_input` (list): Text responses to categorize
- `api_key` (str): API key for the LLM service
- `top_n` (int, default=10): Number of top categories to return by frequency
- `cat_num` (int, default=10): Number of categories to extract per iteration
- `divisions` (int, default=5): Number of data chunks (increase for larger corpora)
- `user_model` (str, default="gpt-4o"): Specific model to use
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `specificity` (str, default="broad"): Category precision level ("broad", "narrow")
- `research_question` (str, optional): Contextual research question to guide categorization
- `filename` (str, optional): File path to save output dataset
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
**Returns:**
- `pandas.DataFrame`: Dataset with category names and frequencies, limited to top N most common categories
**Example:**
```
import catllm as cat
top_10_categories = cat.explore_common_categories(
survey_question="What motivates you most at work?",
survey_input=["flexible schedule", "good pay", "interesting projects"],
api_key="OPENAI_API_KEY",
top_n=10,
cat_num=5,
divisions=10
)
print(categories)
```
### `multi_class()`
Performs multi-label classification of text responses into user-defined categories, returning structured results with optional CSV export.
**Methodology:**
Processes each text response individually, assigning one or more categories from the provided list. Supports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows.
**Parameters:**
- `survey_question` (str): The survey question being analyzed
- `survey_input` (list): List of text responses to classify
- `categories` (list): List of predefined categories for classification
- `api_key` (str): API key for the LLM service
- `user_model` (str, default="gpt-4o"): Specific model to use
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `safety` (bool, default=False): Enable safety checks on responses and saves to CSV at each API call step
- `filename` (str, default="categorized_data.csv"): Filename for CSV output
- `save_directory` (str, optional): Directory path to save the CSV file
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
**Returns:**
- `pandas.DataFrame`: DataFrame with classification results, columns formatted as specified
**Example:**
```
import catllm as cat
user_categories = ["to start living with or to stay with partner/spouse",
"relationship change (divorce, breakup, etc)",
"the person had a job or school or career change, including transferred and retired",
"the person's partner's job or school or career change, including transferred and retired",
"financial reasons (rent is too expensive, pay raise, etc)",
"related specifically features of the home, such as a bigger or smaller yard"]
question = "Why did you move?"
move_reasons = cat.multi_class(
survey_question=question,
survey_input= df[column1],
user_model="gpt-4o",
creativity=0,
categories=user_categories,
safety =TRUE,
api_key="OPENAI_API_KEY")
```
### `image_multi_class()`
Performs multi-label image classification into user-defined categories, returning structured results with optional CSV export.
**Methodology:**
Processes each image individually, assigning one or more categories from the provided list. Supports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows.
**Parameters:**
- `image_description` (str): A description of what the model should expect to see
- `image_input` (list): List of file paths or a folder to pull file paths from
- `categories` (list): List of predefined categories for classification
- `api_key` (str): API key for the LLM service
- `user_model` (str, default="gpt-4o"): Specific model to use
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `safety` (bool, default=False): Enable safety checks on responses and saves to CSV at each API call step
- `filename` (str, default="categorized_data.csv"): Filename for CSV output
- `save_directory` (str, optional): Directory path to save the CSV file
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
**Returns:**
- `pandas.DataFrame`: DataFrame with classification results, columns formatted as specified
**Example:**
```
import catllm as cat
user_categories = ["has a cat somewhere in it",
"looks cartoonish",
"Adrian Brody is in it"]
description = "Should be an image of a child's drawing"
image_categories = cat.image_multi_class(
image_description=description,
image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'],
user_model="gpt-4o",
creativity=0,
categories=user_categories,
safety =TRUE,
api_key="OPENAI_API_KEY")
```
### `image_score_drawing()`
Performs quality scoring of images against a reference description and optional reference image, returning structured results with optional CSV export.
**Methodology:**
Processes each image individually, assigning a drawing quality score on a 5-point scale based on similarity to the expected description:
- **1**: No meaningful similarity (fundamentally different)
- **2**: Barely recognizable similarity (25% match)
- **3**: Partial match (50% key features)
- **4**: Strong alignment (75% features)
- **5**: Near-perfect match (90%+ similarity)
Supports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows[5].
**Parameters:**
- `reference_image_description` (str): A description of what the model should expect to see
- `image_input` (list): List of image file paths or folder path containing images
- `reference_image` (str): A file path to the reference image
- `api_key` (str): API key for the LLM service
- `user_model` (str, default="gpt-4o"): Specific vision model to use
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `safety` (bool, default=False): Enable safety checks and save results at each API call step
- `filename` (str, default="image_scores.csv"): Filename for CSV output
- `save_directory` (str, optional): Directory path to save the CSV file
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
**Returns:**
- `pandas.DataFrame`: DataFrame with image paths, quality scores, and analysis details
**Example:**
```
import catllm as cat
image_scores = cat.image_score(
reference_image_description='Adrien Brody sitting in a lawn chair,
image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'],
user_model="gpt-4o",
creativity=0,
safety =TRUE,
api_key="OPENAI_API_KEY")
```
### `image_features()`
Extracts specific features and attributes from images, returning exact answers to user-defined questions (e.g., counts, colors, presence of objects).
**Methodology:**
Processes each image individually using vision models to extract precise information about specified features. Unlike scoring and multi-class functions, this returns factual data such as object counts, color identification, or presence/absence of specific elements. Supports flexible output formatting and optional CSV export for quantitative analysis workflows.
**Parameters:**
- `image_description` (str): A description of what the model should expect to see
- `image_input` (list): List of image file paths or folder path containing images
- `features_to_extract` (list): List of specific features to extract (e.g., ["number of people", "primary color", "contains text"])
- `api_key` (str): API key for the LLM service
- `user_model` (str, default="gpt-4o"): Specific vision model to use
- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)
- `to_csv` (bool, default=False): Whether to save the output to a CSV file
- `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
- `save_directory` (str, optional): Directory path to save the CSV file
- `model_source` (str, default="OpenAI"): Model provider ("OpenAI", "Anthropic", "Perplexity", "Mistral")
**Returns:**
- `pandas.DataFrame`: DataFrame with image paths and extracted feature values for each specified attribute[1][4]
**Example:**
```
import catllm as cat
image_scores = cat.image_features(
image_description='An AI generated image of Spongebob dancing with Patrick',
features_to_extract=['Spongebob is yellow','Both are smiling','Patrick is chunky']
image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'],
model_source= 'OpenAI',
user_model="gpt-4o",
creativity=0,
safety =TRUE,
api_key="OPENAI_API_KEY")
```
### `cerad_drawn_score()`
Automatically scores drawings of circles, diamonds, overlapping rectangles, and cubes according to the official Consortium to Establish a Registry for Alzheimer's Disease (CERAD) scoring system, returning structured results with optional CSV export. Works even with images that contain other drawings or writing.
**Methodology:**
Processes each image individually, evaluating the drawn shapes based on CERAD criteria. Supports optional inclusion of reference shapes within images and can provide reference examples if requested. The function outputs standardized scores facilitating reproducible analysis and integrates optional safety checks and CSV export for research workflows.
**Parameters:**
- `shape` (str): The type of shape to score (e.g., "circle", "diamond", "overlapping rectangles", "cube")
- `image_input` (list): List of image file paths or folder path containing images
- `api_key` (str): API key for the LLM service
- `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 (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", "Mistral")
**Returns:**
- `pandas.DataFrame`: DataFrame with image paths, CERAD scores, and analysis details
**Example:**
```
import catllm as cat
diamond_scores = cat.cerad_score(
shape="diamond",
image_input=df['diamond_pic_path'],
api_key=open_ai_key,
safety=True,
filename="diamond_gpt_score.csv",
)
```
## Academic Research
This package implements methodology from research on LLM performance in social science applications, including the UC Berkeley Social Networks Study. The package addresses reproducibility challenges in LLM-assisted research by providing standardized interfaces and consistent output formatting.
If you use this package for research, please cite:
Soria, C. (2025). CatLLM (0.0.8). Zenodo. https://doi.org/10.5281/zenodo.15532317
## License
`cat-llm` is distributed under the terms of the [GNU](https://www.gnu.org/licenses/gpl-3.0.en.html) license.
Raw data
{
"_id": null,
"home_page": null,
"name": "cat-llm",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "categorizer, image classification, llm, structured output, survey data, text classification",
"author": null,
"author_email": "Christopher Soria <chrissoria@berkeley.edu>",
"download_url": "https://files.pythonhosted.org/packages/4a/91/4a2d091d428d21a8633a0af28ea23c2ff183380ba4ee8a02b84dcf64724b/cat_llm-0.0.39.tar.gz",
"platform": null,
"description": "\n\n# catllm\n\n[](https://pypi.org/project/cat-llm)\n[](https://pypi.org/project/cat-llm)\n\n-----\n\n## Table of Contents\n\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Configuration](#configuration)\n- [Supported Models](#supported-models)\n- [API Reference](#api-reference)\n - [explore_corpus()](#explore_corpus)\n - [explore_common_categories()](#explore_common_categories)\n - [multi_class()](#multi_class)\n - [image_score()](#image_score)\n - [image_features()](#image_features)\n - [cerad_drawn_score()](#cerad_drawn_score)\n- [Academic Research](#academic-research)\n- [License](#license)\n\n## Installation\n\n```console\npip install cat-llm\n```\n\n## Quick Start\n\nCatLLM helps social scientists and demographers automatically categorize open-ended survey responses using AI models like GPT-4 and Claude.\n\nSimply provide your survey responses and category list - the package handles the rest and outputs clean data ready for statistical analysis. It works with single or multiple categories per response and automatically skips missing data to save API costs.\n\nPerfect for turning messy text data into structured categories you can actually analyze.\n\n## Configuration\n\n### Get Your OpenAI API Key\n\n1. **Create an OpenAI Developer Account**:\n - Go to [platform.openai.com](https://platform.openai.com) (separate from regular ChatGPT)\n - Sign up with email, Google, Microsoft, or Apple\n\n2. **Generate an API Key**:\n - Log into your account and click your name in the top right corner\n - Click \"View API keys\" or navigate to the \"API keys\" section\n - Click \"Create new secret key\"\n - Give your key a descriptive name\n - Set permissions (choose \"All\" for full access)\n\n3. **Add Payment Details**:\n - Add a payment method to your OpenAI account\n - Purchase credits (start with $5 - it lasts a long time for most research use)\n - **Important**: Your API key won't work without credits\n\n4. **Save Your Key Securely**:\n - Copy the key immediately (you won't be able to see it again)\n - Store it safely and never share it publicly\n\n5. Copy and paste your key into catllm in the api_key parameter\n\n## Supported Models\n\n- **OpenAI**: GPT-4o, GPT-4, GPT-3.5-turbo, etc.\n- **Anthropic**: Claude Sonnet 3.7, Claude Haiku, etc.\n- **Perplexity**: Sonnar Large, Sonnar Small, etc.\n- **Mistral**: Mistral Large, Mistral Small, etc.\n\n## API Reference\n\n### `explore_corpus()`\n\nExtracts categories from a corpus of text responses and returns frequency counts.\n\n**Methodology:**\nThe function divides the corpus into random chunks to address the probabilistic nature of LLM outputs. By processing multiple chunks and averaging results across many API calls rather than relying on a single call, this approach significantly improves reproducibility and provides more stable categorical frequency estimates.\n\n**Parameters:**\n- `survey_question` (str): The survey question being analyzed\n- `survey_input` (list): List of text responses to categorize\n- `api_key` (str): API key for the LLM service\n- `cat_num` (int, default=10): Number of categories to extract in each iteration\n- `divisions` (int, default=5): Number of chunks to divide the data into (larger corpora might require larger divisions)\n- `specificity` (str, default=\"broad\"): Category precision level (e.g., \"broad\", \"narrow\")\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n- `user_model` (str, default=\"got-4o\"): Specific model (e.g., \"gpt-4o\", \"claude-opus-4-20250514\")\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `filename` (str, optional): Output file path for saving results\n\n**Returns:**\n- `pandas.DataFrame`: Two-column dataset with category names and frequencies\n\n**Example:***\n\n```\nimport catllm as cat\n\ncategories = cat.explore_corpus(\nsurvey_question=\"What motivates you most at work?\",\nsurvey_input=[\"flexible schedule\", \"good pay\", \"interesting projects\"],\napi_key=\"OPENAI_API_KEY\",\ncat_num=5,\ndivisions=10\n)\n```\n\n### `explore_common_categories()`\n\nIdentifies the most frequently occurring categories across a text corpus and returns the top N categories by frequency count.\n\n**Methodology:**\nDivides the corpus into random chunks and averages results across multiple API calls to improve reproducibility and provide stable frequency estimates for the most prevalent categories, addressing the probabilistic nature of LLM outputs.\n\n**Parameters:**\n- `survey_question` (str): Survey question being analyzed\n- `survey_input` (list): Text responses to categorize\n- `api_key` (str): API key for the LLM service\n- `top_n` (int, default=10): Number of top categories to return by frequency\n- `cat_num` (int, default=10): Number of categories to extract per iteration\n- `divisions` (int, default=5): Number of data chunks (increase for larger corpora)\n- `user_model` (str, default=\"gpt-4o\"): Specific model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `specificity` (str, default=\"broad\"): Category precision level (\"broad\", \"narrow\")\n- `research_question` (str, optional): Contextual research question to guide categorization\n- `filename` (str, optional): File path to save output dataset\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: Dataset with category names and frequencies, limited to top N most common categories\n\n**Example:**\n\n```\nimport catllm as cat\n\ntop_10_categories = cat.explore_common_categories(\nsurvey_question=\"What motivates you most at work?\",\nsurvey_input=[\"flexible schedule\", \"good pay\", \"interesting projects\"],\napi_key=\"OPENAI_API_KEY\",\ntop_n=10,\ncat_num=5,\ndivisions=10\n)\nprint(categories)\n```\n### `multi_class()`\n\nPerforms multi-label classification of text responses into user-defined categories, returning structured results with optional CSV export.\n\n**Methodology:**\nProcesses each text response individually, assigning one or more categories from the provided list. Supports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows.\n\n**Parameters:**\n- `survey_question` (str): The survey question being analyzed\n- `survey_input` (list): List of text responses to classify\n- `categories` (list): List of predefined categories for classification\n- `api_key` (str): API key for the LLM service\n- `user_model` (str, default=\"gpt-4o\"): Specific model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `safety` (bool, default=False): Enable safety checks on responses and saves to CSV at each API call step\n- `filename` (str, default=\"categorized_data.csv\"): Filename for CSV output\n- `save_directory` (str, optional): Directory path to save the CSV file\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: DataFrame with classification results, columns formatted as specified\n\n**Example:**\n\n```\nimport catllm as cat\n\nuser_categories = [\"to start living with or to stay with partner/spouse\",\n \"relationship change (divorce, breakup, etc)\",\n \"the person had a job or school or career change, including transferred and retired\",\n \"the person's partner's job or school or career change, including transferred and retired\",\n \"financial reasons (rent is too expensive, pay raise, etc)\",\n \"related specifically features of the home, such as a bigger or smaller yard\"]\n\nquestion = \"Why did you move?\" \n\nmove_reasons = cat.multi_class(\n survey_question=question, \n survey_input= df[column1], \n user_model=\"gpt-4o\",\n creativity=0,\n categories=user_categories,\n safety =TRUE,\n api_key=\"OPENAI_API_KEY\")\n```\n\n### `image_multi_class()`\n\nPerforms multi-label image classification into user-defined categories, returning structured results with optional CSV export.\n\n**Methodology:**\nProcesses each image individually, assigning one or more categories from the provided list. Supports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows.\n\n**Parameters:**\n- `image_description` (str): A description of what the model should expect to see\n- `image_input` (list): List of file paths or a folder to pull file paths from\n- `categories` (list): List of predefined categories for classification\n- `api_key` (str): API key for the LLM service\n- `user_model` (str, default=\"gpt-4o\"): Specific model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `safety` (bool, default=False): Enable safety checks on responses and saves to CSV at each API call step\n- `filename` (str, default=\"categorized_data.csv\"): Filename for CSV output\n- `save_directory` (str, optional): Directory path to save the CSV file\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: DataFrame with classification results, columns formatted as specified\n\n**Example:**\n\n```\nimport catllm as cat\n\nuser_categories = [\"has a cat somewhere in it\",\n \"looks cartoonish\",\n \"Adrian Brody is in it\"]\n\ndescription = \"Should be an image of a child's drawing\" \n\nimage_categories = cat.image_multi_class(\n image_description=description, \n image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'], \n user_model=\"gpt-4o\",\n creativity=0,\n categories=user_categories,\n safety =TRUE,\n api_key=\"OPENAI_API_KEY\")\n```\n\n### `image_score_drawing()`\n\nPerforms quality scoring of images against a reference description and optional reference image, returning structured results with optional CSV export.\n\n**Methodology:**\nProcesses each image individually, assigning a drawing quality score on a 5-point scale based on similarity to the expected description:\n\n- **1**: No meaningful similarity (fundamentally different)\n- **2**: Barely recognizable similarity (25% match) \n- **3**: Partial match (50% key features)\n- **4**: Strong alignment (75% features)\n- **5**: Near-perfect match (90%+ similarity)\n\nSupports flexible output formatting and optional saving of results to CSV for easy integration with data analysis workflows[5].\n\n**Parameters:**\n- `reference_image_description` (str): A description of what the model should expect to see\n- `image_input` (list): List of image file paths or folder path containing images\n- `reference_image` (str): A file path to the reference image\n- `api_key` (str): API key for the LLM service\n- `user_model` (str, default=\"gpt-4o\"): Specific vision model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `safety` (bool, default=False): Enable safety checks and save results at each API call step\n- `filename` (str, default=\"image_scores.csv\"): Filename for CSV output\n- `save_directory` (str, optional): Directory path to save the CSV file\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: DataFrame with image paths, quality scores, and analysis details\n\n**Example:**\n\n```\nimport catllm as cat \n\nimage_scores = cat.image_score(\n reference_image_description='Adrien Brody sitting in a lawn chair, \n image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'], \n user_model=\"gpt-4o\",\n creativity=0,\n safety =TRUE,\n api_key=\"OPENAI_API_KEY\")\n```\n\n### `image_features()`\n\nExtracts specific features and attributes from images, returning exact answers to user-defined questions (e.g., counts, colors, presence of objects).\n\n**Methodology:**\nProcesses each image individually using vision models to extract precise information about specified features. Unlike scoring and multi-class functions, this returns factual data such as object counts, color identification, or presence/absence of specific elements. Supports flexible output formatting and optional CSV export for quantitative analysis workflows.\n\n**Parameters:**\n- `image_description` (str): A description of what the model should expect to see\n- `image_input` (list): List of image file paths or folder path containing images\n- `features_to_extract` (list): List of specific features to extract (e.g., [\"number of people\", \"primary color\", \"contains text\"])\n- `api_key` (str): API key for the LLM service\n- `user_model` (str, default=\"gpt-4o\"): Specific vision model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `to_csv` (bool, default=False): Whether to save the output to a CSV file\n- `safety` (bool, default=False): Enable safety checks and save results at each API call step\n- `filename` (str, default=\"categorized_data.csv\"): Filename for CSV output\n- `save_directory` (str, optional): Directory path to save the CSV file\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Perplexity\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: DataFrame with image paths and extracted feature values for each specified attribute[1][4]\n\n**Example:**\n\n```\nimport catllm as cat \n\nimage_scores = cat.image_features(\n image_description='An AI generated image of Spongebob dancing with Patrick', \n features_to_extract=['Spongebob is yellow','Both are smiling','Patrick is chunky']\n image_input= ['desktop/image1.jpg','desktop/image2.jpg', desktop/image3.jpg'], \n model_source= 'OpenAI',\n user_model=\"gpt-4o\",\n creativity=0,\n safety =TRUE,\n api_key=\"OPENAI_API_KEY\")\n```\n\n### `cerad_drawn_score()`\n\nAutomatically scores drawings of circles, diamonds, overlapping rectangles, and cubes according to the official Consortium to Establish a Registry for Alzheimer's Disease (CERAD) scoring system, returning structured results with optional CSV export. Works even with images that contain other drawings or writing.\n\n**Methodology:**\nProcesses each image individually, evaluating the drawn shapes based on CERAD criteria. Supports optional inclusion of reference shapes within images and can provide reference examples if requested. The function outputs standardized scores facilitating reproducible analysis and integrates optional safety checks and CSV export for research workflows.\n\n**Parameters:**\n- `shape` (str): The type of shape to score (e.g., \"circle\", \"diamond\", \"overlapping rectangles\", \"cube\")\n- `image_input` (list): List of image file paths or folder path containing images\n- `api_key` (str): API key for the LLM service\n- `user_model` (str, default=\"gpt-4o\"): Specific model to use\n- `creativity` (float, default=0): Temperature/randomness setting (0.0-1.0)\n- `reference_in_image` (bool, default=False): Whether a reference shape is present in the image for comparison\n- `provide_reference` (bool, default=False): Whether to provide a reference example image (built in reference image)\n- `safety` (bool, default=False): Enable safety checks and save results at each API call step\n- `filename` (str, default=\"categorized_data.csv\"): Filename for CSV output\n- `model_source` (str, default=\"OpenAI\"): Model provider (\"OpenAI\", \"Anthropic\", \"Mistral\")\n\n**Returns:**\n- `pandas.DataFrame`: DataFrame with image paths, CERAD scores, and analysis details\n\n**Example:**\n\n```\nimport catllm as cat \n\ndiamond_scores = cat.cerad_score(\n shape=\"diamond\",\n image_input=df['diamond_pic_path'],\n api_key=open_ai_key,\n safety=True,\n filename=\"diamond_gpt_score.csv\",\n)\n```\n\n\n## Academic Research\n\nThis package implements methodology from research on LLM performance in social science applications, including the UC Berkeley Social Networks Study. The package addresses reproducibility challenges in LLM-assisted research by providing standardized interfaces and consistent output formatting.\n\nIf you use this package for research, please cite:\n\nSoria, C. (2025). CatLLM (0.0.8). Zenodo. https://doi.org/10.5281/zenodo.15532317\n\n## License\n\n`cat-llm` is distributed under the terms of the [GNU](https://www.gnu.org/licenses/gpl-3.0.en.html) license.\n",
"bugtrack_url": null,
"license": null,
"summary": "A tool for categorizing text data and images using LLMs and vision models",
"version": "0.0.39",
"project_urls": {
"Documentation": "https://github.com/chrissoria/cat-llm#readme",
"Issues": "https://github.com/chrissoria/cat-llm/issues",
"Source": "https://github.com/chrissoria/cat-llm"
},
"split_keywords": [
"categorizer",
" image classification",
" llm",
" structured output",
" survey data",
" text classification"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "9dcc7b7a9645db4ea51ba98b33d6ad9fc1386ca57a0debf4168e174760237032",
"md5": "879192cf2fb4ccd27f78fe0440518dde",
"sha256": "1472a27c95fff0bd8701b496f392354405c2683016e809f1c3ca4993651c39c6"
},
"downloads": -1,
"filename": "cat_llm-0.0.39-py3-none-any.whl",
"has_sig": false,
"md5_digest": "879192cf2fb4ccd27f78fe0440518dde",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 333368,
"upload_time": "2025-07-23T23:16:25",
"upload_time_iso_8601": "2025-07-23T23:16:25.051173Z",
"url": "https://files.pythonhosted.org/packages/9d/cc/7b7a9645db4ea51ba98b33d6ad9fc1386ca57a0debf4168e174760237032/cat_llm-0.0.39-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "4a914a2d091d428d21a8633a0af28ea23c2ff183380ba4ee8a02b84dcf64724b",
"md5": "4681d80c12dacd9d383e968b669a9cdc",
"sha256": "e06948f7c7f0209bf3592d2d085a414066cc60638d1960dacb7dcdd6bc97cbb9"
},
"downloads": -1,
"filename": "cat_llm-0.0.39.tar.gz",
"has_sig": false,
"md5_digest": "4681d80c12dacd9d383e968b669a9cdc",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 330530,
"upload_time": "2025-07-23T23:16:26",
"upload_time_iso_8601": "2025-07-23T23:16:26.462951Z",
"url": "https://files.pythonhosted.org/packages/4a/91/4a2d091d428d21a8633a0af28ea23c2ff183380ba4ee8a02b84dcf64724b/cat_llm-0.0.39.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-23 23:16:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "chrissoria",
"github_project": "cat-llm#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "cat-llm"
}
JSON
