cat-llm 0.0.17__tar.gz → 0.0.19__tar.gz

{cat_llm-0.0.17 → cat_llm-0.0.19}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.17
+Version: 0.0.19
 Summary: A tool for categorizing text data and images using LLMs and vision models
-Project-URL: Documentation, https://github.com/Christopher Soria/cat-llm#readme
+Project-URL: Documentation, https://github.com/chrissoria/cat-llm#readme
 Project-URL: Issues, https://github.com/chrissoria/cat-llm/issues
 Project-URL: Source, https://github.com/chrissoria/cat-llm
 Author-email: Christopher Soria <chrissoria@berkeley.edu>

{cat_llm-0.0.17 → cat_llm-0.0.19}/pyproject.toml

@@ -30,7 +30,7 @@ dependencies = [
 ]
 
 [project.urls]
-Documentation = "https://github.com/Christopher Soria/cat-llm#readme"
+Documentation = "https://github.com/chrissoria/cat-llm#readme"
 Issues = "https://github.com/chrissoria/cat-llm/issues"
 Source = "https://github.com/chrissoria/cat-llm"
 
@@ -45,13 +45,15 @@ extra-dependencies = [
 check = "mypy --install-types --non-interactive {args:src/catllm tests}"
 
 [tool.hatch.build.targets.wheel]
-packages = ["src/catllm"]
+packages = ["src/catllm"]  # Keep the src/ prefix for wheel
 include = [
+    "src/catllm/**/*.py",
     "src/catllm/images/*",
 ]
 
 [tool.hatch.build.targets.sdist]
 include = [
+    "src/catllm/**/*.py",
     "src/catllm/images/*",
 ]
 

cat_llm-0.0.19/src/catllm/__about__.py

@@ -0,0 +1,10 @@
+# SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
+#
+# SPDX-License-Identifier: MIT
+__version__ = "0.0.19"
+__author__ = "Chris Soria"
+__email__ = "chrissoria@berkeley.edu"
+__title__ = "cat-llm"
+__description__ = "A tool for categorizing and exploring text data and images using LLMs and vision models"
+__url__ = "https://github.com/chrissoria/cat-llm" 
+__license__ = "MIT"

cat_llm-0.0.19/src/catllm/__init__.py

@@ -0,0 +1,14 @@
+# SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
+#
+# SPDX-License-Identifier: MIT
+
+from .__about__ import (
+    __version__,
+    __author__,
+    __description__,
+    __title__,
+    __url__,
+    __license__,
+)
+
+from .cat_llm import *

cat_llm-0.0.19/src/catllm/cat_llm.py

@@ -0,0 +1,1075 @@
+#multi-class text classification
+def extract_multi_class(
+    survey_question, 
+    survey_input,
+    categories,
+    api_key,
+    columns="numbered",
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    to_csv=False,
+    safety=False,
+    filename="categorized_data.csv",
+    save_directory=None,
+    model_source="OpenAI"
+):
+    import os
+    import json
+    import pandas as pd
+    import regex
+    from tqdm import tqdm
+    
+    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("\nThe categories you entered:")
+    for i, cat in enumerate(categories, 1):
+        print(f"{i}. {cat}")
+    
+    link1 = []
+    extracted_jsons = []
+
+    for idx, response in enumerate(tqdm(survey_input, desc="Categorizing responses")):
+        reply = None  
+
+        if pd.isna(response): 
+            link1.append("Skipped NaN input")
+            default_json = example_JSON 
+            extracted_jsons.append(default_json)
+            #print(f"Skipped NaN input.")
+        else:
+            prompt = f"""A respondent was asked: {survey_question}. \
+Categorize this survey response "{response}" into the following categories that apply: \
+{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"):
+                from openai import OpenAI
+                client = OpenAI(api_key=api_key)
+                try:
+                    response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                    reply = response_obj.choices[0].message.content
+                    link1.append(reply)
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+            elif model_source == "Perplexity":
+                from openai import OpenAI
+                client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
+                try:
+                    response_obj = client.chat.completions.create(
+                        model=user_model,
+                        messages=[{'role': 'user', 'content': prompt}],
+                        temperature=creativity
+                    )
+                    reply = response_obj.choices[0].message.content
+                    link1.append(reply)
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+            elif model_source == "Anthropic":
+                import anthropic
+                client = anthropic.Anthropic(api_key=api_key)
+                try:
+                    message = client.messages.create(
+                    model=user_model,
+                    max_tokens=1024,
+                    temperature=creativity,
+                    messages=[{"role": "user", "content": prompt}]
+                )
+                    reply = message.content[0].text  # Anthropic returns content as list
+                    link1.append(reply)
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+            elif model_source == "Mistral":
+                from mistralai import Mistral
+                client = Mistral(api_key=api_key)
+                try:
+                    response = client.chat.complete(
+                    model=user_model,
+                    messages=[
+                        {'role': 'user', 'content': prompt}
+                    ],
+                    temperature=creativity
+                )
+                    reply = response.choices[0].message.content
+                    link1.append(reply)
+                except Exception as e:
+                    print(f"An error occurred: {e}")
+                    link1.append(f"Error processing input: {e}")
+            else:
+                raise ValueError("Unknown source! Choose from OpenAI, Anthropic, Perplexity, or Mistral")
+            # in situation that no JSON is found
+            if reply is not None:
+                extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
+                if extracted_json:
+                    cleaned_json = extracted_json[0].replace('[', '').replace(']', '').replace('\n', '').replace(" ", '').replace("  ", '')
+                    extracted_jsons.append(cleaned_json)
+                    #print(cleaned_json)
+                else:
+                    error_message = """{"1":"e"}"""
+                    extracted_jsons.append(error_message)
+                    print(error_message)
+            else:
+                error_message = """{"1":"e"}"""
+                extracted_jsons.append(error_message)
+                #print(error_message)
+
+        # --- Safety Save ---
+        if safety:
+            # Save progress so far
+            temp_df = pd.DataFrame({
+                'survey_response': survey_input[:idx+1],
+                'link1': link1,
+                'json': extracted_jsons
+            })
+            # Normalize processed jsons so far
+            normalized_data_list = []
+            for json_str in extracted_jsons:
+                try:
+                    parsed_obj = json.loads(json_str)
+                    normalized_data_list.append(pd.json_normalize(parsed_obj))
+                except json.JSONDecodeError:
+                    normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+            normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+            temp_df = pd.concat([temp_df, normalized_data], axis=1)
+            # Save to CSV
+            if save_directory is None:
+                save_directory = os.getcwd()
+            temp_df.to_csv(os.path.join(save_directory, filename), index=False)
+
+    # --- Final DataFrame ---
+    normalized_data_list = []
+    for json_str in extracted_jsons:
+        try:
+            parsed_obj = json.loads(json_str)
+            normalized_data_list.append(pd.json_normalize(parsed_obj))
+        except json.JSONDecodeError:
+            normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+    normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+
+    categorized_data = pd.DataFrame({
+        'survey_response': survey_input.reset_index(drop=True),
+        'link1': pd.Series(link1).reset_index(drop=True),
+        'json': pd.Series(extracted_jsons).reset_index(drop=True)
+    })
+    categorized_data = pd.concat([categorized_data, normalized_data], axis=1)
+    
+    if columns != "numbered": #if user wants text columns
+        categorized_data.columns = list(categorized_data.columns[:3]) + categories[:len(categorized_data.columns) - 3]
+
+    if to_csv:
+        if save_directory is None:
+            save_directory = os.getcwd()
+        categorized_data.to_csv(os.path.join(save_directory, filename), index=False)
+    
+    return categorized_data
+
+# image multi-class (binary) function
+def extract_image_multi_class(
+    image_description, 
+    image_input,
+    categories,
+    api_key,
+    columns="numbered",
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    to_csv=False,
+    safety=False,
+    filename="categorized_data.csv",
+    save_directory=None,
+    model_source="OpenAI"
+):
+    import os
+    import json
+    import pandas as pd
+    import regex
+    from tqdm import tqdm
+    import glob
+    import base64
+    from pathlib import Path
+
+    if save_directory is not None and not os.path.isdir(save_directory):
+    # Directory doesn't exist - raise an exception to halt execution
+        raise FileNotFoundError(f"Directory {save_directory} doesn't exist")
+
+    image_extensions = [
+    '*.png', '*.jpg', '*.jpeg',
+    '*.gif', '*.webp', '*.svg', '*.svgz', '*.avif', '*.apng',
+    '*.tif', '*.tiff', '*.bmp',
+    '*.heif', '*.heic', '*.ico',
+    '*.psd'
+    ]
+
+    if not isinstance(image_input, list):
+        # If image_input is a filepath (string)
+        image_files = []
+        for ext in image_extensions:
+            image_files.extend(glob.glob(os.path.join(image_input, ext)))
+    
+        print(f"Found {len(image_files)} images.")
+    else:
+        # If image_files is already a list
+        image_files = image_input
+        print(f"Provided a list of {len(image_input)} images.")
+    
+    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("Categories to classify:")
+    for i, cat in enumerate(categories, 1):
+        print(f"{i}. {cat}")
+    
+    link1 = []
+    extracted_jsons = []
+
+    for i, img_path in enumerate(tqdm(image_files, desc="Categorising images"), start=0):
+    # Check validity first
+        if img_path is None or not os.path.exists(img_path):
+            link1.append("Skipped NaN input or invalid path")
+            extracted_jsons.append("""{"no_valid_image": 1}""")
+            continue  # Skip the rest of the loop iteration
+        
+    # Only open the file if path is valid
+        with open(img_path, "rb") as f:
+            encoded = base64.b64encode(f.read()).decode("utf-8")
+    
+    # Handle extension safely
+        ext = Path(img_path).suffix.lstrip(".").lower()
+        encoded_image = f"data:image/{ext};base64,{encoded}"
+    
+        prompt = [
+            {
+                "type": "text",
+                "text": (
+                    f"You are an image-tagging assistant.\n"
+                    f"Task ► Examine the attached image and decide, **for each category below**, "
+                    f"whether it is PRESENT (1) or NOT PRESENT (0).\n\n"
+                    f"Image is expected to show: {image_description}\n\n"
+                    f"Categories:\n{categories_str}\n\n"
+                    f"Output format ► Respond with **only** a JSON object whose keys are the "
+                    f"quoted category numbers ('1', '2', …) and whose values are 1 or 0. "
+                    f"No additional keys, comments, or text.\n\n"
+                    f"Example (three categories):\n"
+                    f"{example_JSON}"
+                ),
+            },
+            {
+                "type": "image_url",
+                "image_url": {"url": encoded_image, "detail": "high"},
+            },
+        ]
+        if model_source == "OpenAI":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key)
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+
+        elif model_source == "Perplexity":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Anthropic":
+            import anthropic
+            client = anthropic.Anthropic(api_key=api_key)
+            try:
+                message = client.messages.create(
+                    model=user_model,
+                    max_tokens=1024,
+                    temperature=creativity,
+                    messages=[{"role": "user", "content": prompt}]
+                )
+                reply = message.content[0].text  # Anthropic returns content as list
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Mistral":
+            from mistralai import Mistral
+            client = Mistral(api_key=api_key)
+            try:
+                response = client.chat.complete(
+                    model=user_model,
+                    messages=[
+                    {'role': 'user', 'content': prompt}
+                ],
+                temperature=creativity
+                )
+                reply = response.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        else:
+            raise ValueError("Unknown source! Choose from OpenAI, Anthropic, Perplexity, or Mistral")
+            # in situation that no JSON is found
+        if reply is not None:
+            extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
+            if extracted_json:
+                cleaned_json = extracted_json[0].replace('[', '').replace(']', '').replace('\n', '').replace(" ", '').replace("  ", '')
+                extracted_jsons.append(cleaned_json)
+                #print(cleaned_json)
+            else:
+                error_message = """{"1":"e"}"""
+                extracted_jsons.append(error_message)
+                print(error_message)
+        else:
+            error_message = """{"1":"e"}"""
+            extracted_jsons.append(error_message)
+            #print(error_message)
+
+        # --- Safety Save ---
+        if safety:
+            #print(f"Saving CSV to: {save_directory}")
+            # Save progress so far
+            temp_df = pd.DataFrame({
+                'image_input': image_files[:i+1],
+                'link1': link1,
+                'json': extracted_jsons
+            })
+            # Normalize processed jsons so far
+            normalized_data_list = []
+            for json_str in extracted_jsons:
+                try:
+                    parsed_obj = json.loads(json_str)
+                    normalized_data_list.append(pd.json_normalize(parsed_obj))
+                except json.JSONDecodeError:
+                    normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+            normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+            temp_df = pd.concat([temp_df, normalized_data], axis=1)
+            # Save to CSV
+            if save_directory is None:
+                save_directory = os.getcwd()
+            temp_df.to_csv(os.path.join(save_directory, filename), index=False)
+
+    # --- Final DataFrame ---
+    normalized_data_list = []
+    for json_str in extracted_jsons:
+        try:
+            parsed_obj = json.loads(json_str)
+            normalized_data_list.append(pd.json_normalize(parsed_obj))
+        except json.JSONDecodeError:
+            normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+    normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+
+    categorized_data = pd.DataFrame({
+        'image_input': image_files,
+        'link1': pd.Series(link1).reset_index(drop=True),
+        'json': pd.Series(extracted_jsons).reset_index(drop=True)
+    })
+    categorized_data = pd.concat([categorized_data, normalized_data], axis=1)
+    
+    if columns != "numbered": #if user wants text columns
+        categorized_data.columns = list(categorized_data.columns[:3]) + categories[:len(categorized_data.columns) - 3]
+
+    if to_csv:
+        if save_directory is None:
+            save_directory = os.getcwd()
+        categorized_data.to_csv(os.path.join(save_directory, filename), index=False)
+    
+    return categorized_data
+
+#image score function
+def extract_image_score(
+    reference_image_description,
+    image_input,
+    reference_image,
+    api_key,
+    columns="numbered",
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    to_csv=False,
+    safety=False,
+    filename="categorized_data.csv",
+    save_directory=None,
+    model_source="OpenAI"
+):
+    import os
+    import json
+    import pandas as pd
+    import regex
+    from tqdm import tqdm
+    import glob
+    import base64
+    from pathlib import Path
+
+    if save_directory is not None and not os.path.isdir(save_directory):
+    # Directory doesn't exist - raise an exception to halt execution
+        raise FileNotFoundError(f"Directory {save_directory} doesn't exist")
+
+    image_extensions = [
+    '*.png', '*.jpg', '*.jpeg',
+    '*.gif', '*.webp', '*.svg', '*.svgz', '*.avif', '*.apng',
+    '*.tif', '*.tiff', '*.bmp',
+    '*.heif', '*.heic', '*.ico',
+    '*.psd'
+    ]
+
+    if not isinstance(image_input, list):
+        # If image_input is a filepath (string)
+        image_files = []
+        for ext in image_extensions:
+            image_files.extend(glob.glob(os.path.join(image_input, ext)))
+    
+        print(f"Found {len(image_files)} images.")
+    else:
+        # If image_files is already a list
+        image_files = image_input
+        print(f"Provided a list of {len(image_input)} images.")
+    
+    with open(reference_image, 'rb') as f:
+        reference_image = f"data:image/{reference_image.split('.')[-1]};base64,{base64.b64encode(f.read()).decode('utf-8')}"
+    
+    link1 = []
+    extracted_jsons = []
+
+    for i, img_path in enumerate(tqdm(image_files, desc="Categorising images"), start=0):
+    # Check validity first
+        if img_path is None or not os.path.exists(img_path):
+            link1.append("Skipped NaN input or invalid path")
+            extracted_jsons.append("""{"no_valid_image": 1}""")
+            continue  # Skip the rest of the loop iteration
+        
+    # Only open the file if path is valid
+        with open(img_path, "rb") as f:
+            encoded = base64.b64encode(f.read()).decode("utf-8")
+    
+    # Handle extension safely
+        ext = Path(img_path).suffix.lstrip(".").lower()
+        encoded_image = f"data:image/{ext};base64,{encoded}"
+
+        prompt = [
+            {
+                "type": "text",
+                "text": (
+                    f"You are a visual similarity assessment system.\n"
+            f"Task ► Compare these two images:\n"
+            f"1. REFERENCE (left): {reference_image_description}\n"
+            f"2. INPUT (right): User-provided drawing\n\n"
+            f"Rating criteria:\n"
+            f"1: No meaningful similarity (fundamentally different)\n"
+            f"2: Barely recognizable similarity (25% match)\n" 
+            f"3: Partial match (50% key features)\n"
+            f"4: Strong alignment (75% features)\n"
+            f"5: Near-perfect match (90%+ similarity)\n\n"
+            f"Output format ► Return ONLY:\n"
+            "{\n"
+            '  "score": [1-5],\n'
+            '  "summary": "reason you scored"\n'
+            "}\n\n"
+            f"Critical rules:\n"
+            f"- Score must reflect shape, proportions, and key details\n"
+            f"- List only concrete matching elements from reference\n"
+            f"- No markdown or additional text"
+                ),
+            },
+            {"type": "image_url", 
+             "image_url": {"url": reference_image, "detail": "high"}
+             },
+            {
+                "type": "image_url",
+                
+                "image_url": {"url": encoded_image, "detail": "high"},
+            },
+        ]
+        if model_source == "OpenAI":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key)
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+
+        elif model_source == "Perplexity":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Anthropic":
+            import anthropic
+            client = anthropic.Anthropic(api_key=api_key)
+            try:
+                message = client.messages.create(
+                    model=user_model,
+                    max_tokens=1024,
+                    temperature=creativity,
+                    messages=[{"role": "user", "content": prompt}]
+                )
+                reply = message.content[0].text  # Anthropic returns content as list
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Mistral":
+            from mistralai import Mistral
+            client = Mistral(api_key=api_key)
+            try:
+                response = client.chat.complete(
+                    model=user_model,
+                    messages=[
+                    {'role': 'user', 'content': prompt}
+                ],
+                temperature=creativity
+                )
+                reply = response.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        else:
+            raise ValueError("Unknown source! Choose from OpenAI, Anthropic, Perplexity, or Mistral")
+            # in situation that no JSON is found
+        if reply is not None:
+            extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
+            if extracted_json:
+                cleaned_json = extracted_json[0].replace('[', '').replace(']', '').replace('\n', '').replace(" ", '').replace("  ", '')
+                extracted_jsons.append(cleaned_json)
+                #print(cleaned_json)
+            else:
+                error_message = """{"1":"e"}"""
+                extracted_jsons.append(error_message)
+                print(error_message)
+        else:
+            error_message = """{"1":"e"}"""
+            extracted_jsons.append(error_message)
+            #print(error_message)
+
+        # --- Safety Save ---
+        if safety:
+            # Save progress so far
+            temp_df = pd.DataFrame({
+                'image_input': image_files[:i+1],
+                'link1': link1,
+                'json': extracted_jsons
+            })
+            # Normalize processed jsons so far
+            normalized_data_list = []
+            for json_str in extracted_jsons:
+                try:
+                    parsed_obj = json.loads(json_str)
+                    normalized_data_list.append(pd.json_normalize(parsed_obj))
+                except json.JSONDecodeError:
+                    normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+            normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+            temp_df = pd.concat([temp_df, normalized_data], axis=1)
+            # Save to CSV
+            if save_directory is None:
+                save_directory = os.getcwd()
+            temp_df.to_csv(os.path.join(save_directory, filename), index=False)
+
+    # --- Final DataFrame ---
+    normalized_data_list = []
+    for json_str in extracted_jsons:
+        try:
+            parsed_obj = json.loads(json_str)
+            normalized_data_list.append(pd.json_normalize(parsed_obj))
+        except json.JSONDecodeError:
+            normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+    normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+
+    categorized_data = pd.DataFrame({
+        'image_input': image_files,
+        'link1': pd.Series(link1).reset_index(drop=True),
+        'json': pd.Series(extracted_jsons).reset_index(drop=True)
+    })
+    categorized_data = pd.concat([categorized_data, normalized_data], axis=1)
+
+    if to_csv:
+        if save_directory is None:
+            save_directory = os.getcwd()
+        categorized_data.to_csv(os.path.join(save_directory, filename), index=False)
+    
+    return categorized_data
+
+# image features function
+def extract_image_features(
+    image_description, 
+    image_input,
+    features_to_extract,
+    api_key,
+    columns="numbered",
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    to_csv=False,
+    safety=False,
+    filename="categorized_data.csv",
+    save_directory=None,
+    model_source="OpenAI"
+):
+    import os
+    import json
+    import pandas as pd
+    import regex
+    from tqdm import tqdm
+    import glob
+    import base64
+    from pathlib import Path
+
+    if save_directory is not None and not os.path.isdir(save_directory):
+    # Directory doesn't exist - raise an exception to halt execution
+        raise FileNotFoundError(f"Directory {save_directory} doesn't exist")
+
+    image_extensions = [
+    '*.png', '*.jpg', '*.jpeg',
+    '*.gif', '*.webp', '*.svg', '*.svgz', '*.avif', '*.apng',
+    '*.tif', '*.tiff', '*.bmp',
+    '*.heif', '*.heic', '*.ico',
+    '*.psd'
+    ]
+
+    if not isinstance(image_input, list):
+        # If image_input is a filepath (string)
+        image_files = []
+        for ext in image_extensions:
+            image_files.extend(glob.glob(os.path.join(image_input, ext)))
+    
+        print(f"Found {len(image_files)} images.")
+    else:
+        # If image_files is already a list
+        image_files = image_input
+        print(f"Provided a list of {len(image_input)} images.")
+    
+    categories_str = "\n".join(f"{i + 1}. {cat}" for i, cat in enumerate(features_to_extract))
+    cat_num = len(features_to_extract)
+    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("\nThe image features to be extracted are:")
+    for i, cat in enumerate(features_to_extract, 1):
+        print(f"{i}. {cat}")
+    
+    link1 = []
+    extracted_jsons = []
+
+    for i, img_path in enumerate(
+        tqdm(image_files, desc="Categorising images"), start=0):
+    # encode this specific image once
+        with open(img_path, "rb") as f:
+            encoded = base64.b64encode(f.read()).decode("utf-8")
+        ext = Path(img_path).suffix.lstrip(".").lower()
+        encoded_image = f"data:image/{ext};base64,{encoded}"
+
+        prompt = [
+            {
+                "type": "text",
+                "text": (
+                    f"You are a visual question answering assistant.\n"
+            f"Task ► Analyze the attached image and answer these specific questions:\n\n"
+            f"Image context: {image_description}\n\n"
+            f"Questions to answer:\n{categories_str}\n\n"
+            f"Output format ► Return **only** a JSON object where:\n"
+            f"- Keys are question numbers ('1', '2', ...)\n"
+            f"- Values are concise answers (numbers, short phrases)\n\n"
+            f"Example for 3 questions:\n"
+            "{\n"
+            '  "1": "4",\n'
+            '  "2": "blue",\n'
+            '  "3": "yes"\n'
+            "}\n\n"
+            f"Important rules:\n"
+            f"1. Answer directly - no explanations\n"
+            f"2. Use exact numerical values when possible\n"
+            f"3. For yes/no questions, use 'yes' or 'no'\n"
+            f"4. Never add extra keys or formatting"
+                ),
+            },
+            {
+                "type": "image_url",
+                "image_url": {"url": encoded_image, "detail": "high"},
+            },
+        ]
+        if model_source == "OpenAI":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key)
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+
+        elif model_source == "Perplexity":
+            from openai import OpenAI
+            client = OpenAI(api_key=api_key, base_url="https://api.perplexity.ai")
+            try:
+                response_obj = client.chat.completions.create(
+                    model=user_model,
+                    messages=[{'role': 'user', 'content': prompt}],
+                    temperature=creativity
+                )
+                reply = response_obj.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Anthropic":
+            import anthropic
+            client = anthropic.Anthropic(api_key=api_key)
+            try:
+                message = client.messages.create(
+                    model=user_model,
+                    max_tokens=1024,
+                    temperature=creativity,
+                    messages=[{"role": "user", "content": prompt}]
+                )
+                reply = message.content[0].text  # Anthropic returns content as list
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        elif model_source == "Mistral":
+            from mistralai import Mistral
+            client = Mistral(api_key=api_key)
+            try:
+                response = client.chat.complete(
+                    model=user_model,
+                    messages=[
+                    {'role': 'user', 'content': prompt}
+                ],
+                temperature=creativity
+                )
+                reply = response.choices[0].message.content
+                link1.append(reply)
+            except Exception as e:
+                print(f"An error occurred: {e}")
+                link1.append(f"Error processing input: {e}")
+        else:
+            raise ValueError("Unknown source! Choose from OpenAI, Anthropic, Perplexity, or Mistral")
+            # in situation that no JSON is found
+        if reply is not None:
+            extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
+            if extracted_json:
+                cleaned_json = extracted_json[0].replace('[', '').replace(']', '').replace('\n', '').replace(" ", '').replace("  ", '')
+                extracted_jsons.append(cleaned_json)
+                #print(cleaned_json)
+            else:
+                error_message = """{"1":"e"}"""
+                extracted_jsons.append(error_message)
+                print(error_message)
+        else:
+            error_message = """{"1":"e"}"""
+            extracted_jsons.append(error_message)
+            #print(error_message)
+
+        # --- Safety Save ---
+        if safety:
+            #print(f"Saving CSV to: {save_directory}")
+            # Save progress so far
+            temp_df = pd.DataFrame({
+                'image_input': image_files[:i+1],
+                'link1': link1,
+                'json': extracted_jsons
+            })
+            # Normalize processed jsons so far
+            normalized_data_list = []
+            for json_str in extracted_jsons:
+                try:
+                    parsed_obj = json.loads(json_str)
+                    normalized_data_list.append(pd.json_normalize(parsed_obj))
+                except json.JSONDecodeError:
+                    normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+            normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+            temp_df = pd.concat([temp_df, normalized_data], axis=1)
+            # Save to CSV
+            if save_directory is None:
+                save_directory = os.getcwd()
+            temp_df.to_csv(os.path.join(save_directory, filename), index=False)
+
+    # --- Final DataFrame ---
+    normalized_data_list = []
+    for json_str in extracted_jsons:
+        try:
+            parsed_obj = json.loads(json_str)
+            normalized_data_list.append(pd.json_normalize(parsed_obj))
+        except json.JSONDecodeError:
+            normalized_data_list.append(pd.DataFrame({"1": ["e"]}))
+    normalized_data = pd.concat(normalized_data_list, ignore_index=True)
+
+    categorized_data = pd.DataFrame({
+        'image_input': image_files,
+        'link1': pd.Series(link1).reset_index(drop=True),
+        'json': pd.Series(extracted_jsons).reset_index(drop=True)
+    })
+    categorized_data = pd.concat([categorized_data, normalized_data], axis=1)
+    
+    if columns != "numbered": #if user wants text columns
+        categorized_data.columns = list(categorized_data.columns[:3]) + categories[:len(categorized_data.columns) - 3]
+
+    if to_csv:
+        if save_directory is None:
+            save_directory = os.getcwd()
+        categorized_data.to_csv(os.path.join(save_directory, filename), index=False)
+    
+    return categorized_data
+
+#extract categories from corpus
+def explore_corpus(
+    survey_question, 
+    survey_input,
+    api_key,
+    research_question=None,
+    specificity="broad",
+    cat_num=10,
+    divisions=5,
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    filename="corpus_exploration.csv",
+    model_source="OpenAI"
+):
+    import os
+    import pandas as pd
+    import random
+    from openai import OpenAI
+    from openai import OpenAI, BadRequestError
+    from tqdm import tqdm
+
+    print(f"Exploring class for question: '{survey_question}'.\n          {cat_num * divisions} unique categories to be extracted.")
+    print()
+
+    chunk_size = round(max(1, len(survey_input) / divisions),0)
+    chunk_size = int(chunk_size)
+
+    if chunk_size < (cat_num/2):
+        raise ValueError(f"Cannot extract {cat_num} {specificity} categories from chunks of only {chunk_size} responses. \n" 
+                    f"Choose one solution: \n"
+                    f"(1) Reduce 'divisions' parameter (currently {divisions}) to create larger chunks, or \n"
+                    f"(2) Reduce 'cat_num' parameter (currently {cat_num}) to extract fewer categories per chunk.")
+
+    random_chunks = []
+    for i in range(divisions):
+        chunk = survey_input.sample(n=chunk_size).tolist()
+        random_chunks.append(chunk)
+    
+    responses = []
+    responses_list = []
+    
+    for i in tqdm(range(divisions), desc="Processing chunks"):
+        survey_participant_chunks = '; '.join(random_chunks[i])
+        prompt = f"""Identify {cat_num} {specificity} categories of responses to the question "{survey_question}" in the following list of responses. \
+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":
+            client = OpenAI(api_key=api_key)
+            try:
+                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
+                )
+                reply = response_obj.choices[0].message.content
+                responses.append(reply)
+            except BadRequestError as e:
+                if "context_length_exceeded" in str(e) or "maximum context length" in str(e):
+                    error_msg = (f"Token limit exceeded for model {user_model}. "
+                        f"Try increasing the 'iterations' parameter to create smaller chunks.")
+                    raise ValueError(error_msg)
+                else:
+                    print(f"OpenAI API error: {e}")
+            except Exception as e:
+                print(f"An error occurred: {e}")
+        else:
+            raise ValueError(f"Unsupported model_source: {model_source}")
+        
+        # Extract just the text as a list
+        items = []
+        for line in responses[i].split('\n'):
+            if '. ' in line:
+                try:
+                    items.append(line.split('. ', 1)[1])
+                except IndexError:
+                    pass
+
+        responses_list.append(items)
+
+    flat_list = [item.lower() for sublist in responses_list for item in sublist]
+
+    #convert flat_list to a df
+    df = pd.DataFrame(flat_list, columns=['Category'])
+    counts = pd.Series(flat_list).value_counts()  # Use original list before conversion
+    df['counts'] = df['Category'].map(counts)
+    df = df.sort_values(by='counts', ascending=False).reset_index(drop=True)
+    df = df.drop_duplicates(subset='Category', keep='first').reset_index(drop=True)
+
+    if filename is not None:
+        df.to_csv(filename, index=False)
+    
+    return df
+
+#extract top categories from corpus
+def explore_common_categories(
+    survey_question, 
+    survey_input,
+    api_key,
+    top_n=10,
+    cat_num=10,
+    divisions=5,
+    user_model="gpt-4o-2024-11-20",
+    creativity=0,
+    specificity="broad",
+    research_question=None,
+    filename=None,
+    model_source="OpenAI"
+):
+    import os
+    import pandas as pd
+    import random
+    from openai import OpenAI
+    from openai import OpenAI, BadRequestError
+    from tqdm import tqdm
+
+    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()
+
+    chunk_size = round(max(1, len(survey_input) / divisions),0)
+    chunk_size = int(chunk_size)
+
+    if chunk_size < (cat_num/2):
+        raise ValueError(f"Cannot extract {cat_num} categories from chunks of only {chunk_size} responses. \n" 
+                    f"Choose one solution: \n"
+                    f"(1) Reduce 'divisions' parameter (currently {divisions}) to create larger chunks, or \n"
+                    f"(2) Reduce 'cat_num' parameter (currently {cat_num}) to extract fewer categories per chunk.")
+
+    random_chunks = []
+    for i in range(divisions):
+        chunk = survey_input.sample(n=chunk_size).tolist()
+        random_chunks.append(chunk)
+    
+    responses = []
+    responses_list = []
+    
+    for i in tqdm(range(divisions), desc="Processing chunks"):
+        survey_participant_chunks = '; '.join(random_chunks[i])
+        prompt = f"""Identify {cat_num} {specificity} categories of responses to the question "{survey_question}" in the following list of responses. \
+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":
+            client = OpenAI(api_key=api_key)
+            try:
+                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
+                )
+                reply = response_obj.choices[0].message.content
+                responses.append(reply)
+            except BadRequestError as e:
+                if "context_length_exceeded" in str(e) or "maximum context length" in str(e):
+                    error_msg = (f"Token limit exceeded for model {user_model}. "
+                        f"Try increasing the 'iterations' parameter to create smaller chunks.")
+                    raise ValueError(error_msg)
+                else:
+                    print(f"OpenAI API error: {e}")
+            except Exception as e:
+                print(f"An error occurred: {e}")
+        else:
+            raise ValueError(f"Unsupported model_source: {model_source}")
+        
+        # Extract just the text as a list
+        items = []
+        for line in responses[i].split('\n'):
+            if '. ' in line:
+                try:
+                    items.append(line.split('. ', 1)[1])
+                except IndexError:
+                    pass
+
+        responses_list.append(items)
+
+    flat_list = [item.lower() for sublist in responses_list for item in sublist]
+
+    #convert flat_list to a df
+    df = pd.DataFrame(flat_list, columns=['Category'])
+    counts = pd.Series(flat_list).value_counts()  # Use original list before conversion
+    df['counts'] = df['Category'].map(counts)
+    df = df.sort_values(by='counts', ascending=False).reset_index(drop=True)
+    df = df.drop_duplicates(subset='Category', keep='first').reset_index(drop=True)
+
+    second_prompt = f"""From this list of categories, extract the top {top_n} most common categories. \
+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":
+        client = OpenAI(api_key=api_key)
+        response_obj = client.chat.completions.create(
+            model=user_model,
+            messages=[{'role': 'user', 'content': second_prompt}],
+            temperature=creativity
+        )
+    top_categories = response_obj.choices[0].message.content
+    print(top_categories)
+
+    top_categories_final = []
+    for line in top_categories.split('\n'):
+        if '. ' in line:
+            try:
+                top_categories_final.append(line.split('. ', 1)[1])
+            except IndexError:
+                pass
+
+    return top_categories_final