cat-llm 0.0.26__tar.gz → 0.0.28__tar.gz

{cat_llm-0.0.26 → cat_llm-0.0.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cat-llm
-Version: 0.0.26
+Version: 0.0.28
 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-0.0.26 → cat_llm-0.0.28}/src/catllm/__about__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2025-present Christopher Soria <chrissoria@berkeley.edu>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.26"
+__version__ = "0.0.28"
 __author__ = "Chris Soria"
 __email__ = "chrissoria@berkeley.edu"
 __title__ = "cat-llm"

{cat_llm-0.0.26 → cat_llm-0.0.28}/src/catllm/image_functions.py

@@ -1,5 +1,5 @@
 # image multi-class (binary) function
-def extract_image_multi_class(
+def image_multi_class(
     image_description, 
     image_input,
     categories,
@@ -72,29 +72,56 @@ def extract_image_multi_class(
     
     # 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":
+            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"},
+                },
+            ]
+            
+        elif model_source == "Anthropic":
+            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",
+                    "source": {
+                        "type": "base64",
+                        "media_type": "image/jpeg",
+                        "data": encoded
+                    }
+                }
+            ]
         if model_source == "OpenAI":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
@@ -111,32 +138,8 @@ def extract_image_multi_class(
                 link1.append(f"Error processing input: {e}")
 
         elif model_source == "Anthropic":
-            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",
-                "source": {
-                    "type": "base64",
-                    "media_type": "image/jpeg",
-                    "data": encoded_image
-                }
-            }
-            ]
-
             import anthropic
+            reply = None
             client = anthropic.Anthropic(api_key=api_key)
             try:
                 message = client.messages.create(
@@ -168,7 +171,7 @@ def extract_image_multi_class(
                 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")
+            raise ValueError("Unknown source! Choose from OpenAI, Anthropic, or Mistral")
             # in situation that no JSON is found
         if reply is not None:
             extracted_json = regex.findall(r'\{(?:[^{}]|(?R))*\}', reply, regex.DOTALL)
@@ -237,7 +240,7 @@ def extract_image_multi_class(
     return categorized_data
 
 #image score function
-def extract_image_score(
+def image_score(
     reference_image_description,
     image_input,
     reference_image,
@@ -285,7 +288,8 @@ def extract_image_score(
         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')}"
+        reference = base64.b64encode(f.read()).decode('utf-8')
+        reference_image = f"data:image/{reference_image.split('.')[-1]};base64,{reference}"
     
     link1 = []
     extracted_jsons = []
@@ -305,40 +309,87 @@ def extract_image_score(
         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":
+            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"}
+                }
+            ]
+
+        elif model_source == "Anthropic":  # Changed to elif
+            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",  # Added missing type
+                    "source": {
+                        "type": "base64",
+                        "media_type": "image/png",
+                        "data": reference
+                    }
+                },
+                {
+                    "type": "image",  # Added missing type
+                    "source": {
+                        "type": "base64",
+                        "media_type": "image/jpeg", 
+                        "data": encoded
+                    }
+                }
+            ]
+
+            
         if model_source == "OpenAI":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)
@@ -354,20 +405,6 @@ def extract_image_score(
                 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)
@@ -383,6 +420,7 @@ def extract_image_score(
             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)
@@ -465,7 +503,7 @@ def extract_image_score(
     return categorized_data
 
 # image features function
-def extract_image_features(
+def image_features(
     image_description, 
     image_input,
     features_to_extract,
@@ -527,41 +565,80 @@ def extract_image_features(
 
     for i, img_path in enumerate(
         tqdm(image_files, desc="Categorising images"), start=0):
+        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
     # 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":
+            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"},
+                            },
+            ]
+        elif model_source == "Anthropic":
+            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",
+                    "source": {
+                        "type": "base64",
+                        "media_type": "image/jpeg",
+                        "data": encoded
+                    }
+                }
+            ]
         if model_source == "OpenAI":
             from openai import OpenAI
             client = OpenAI(api_key=api_key)