Added support for RemoteModel with image scope (#14)

Author: david-yz-liu

ai_feedback/__main__.py

@@ -198,7 +198,7 @@ def main() -> int:
 
     if args.scope == "image":
         prompt["prompt_content"] = prompt_content
-        request, response = image_processing.process_image(args, prompt)
+        request, response = image_processing.process_image(args, prompt, system_instructions)
     elif args.scope == "text":
         request, response = text_processing.process_text(args, prompt_content, system_instructions)
     else:

ai_feedback/image_processing.py

@@ -11,6 +11,7 @@
 from .helpers.image_extractor import extract_images
 from .helpers.image_reader import *
 from .helpers.template_utils import render_prompt_template
+from .models.RemoteModel import RemoteModel
 
 
 def encode_image(image_path: os.PathLike) -> bytes:
@@ -86,7 +87,7 @@ def anthropic_call(message: Message, model: str) -> str | None:
     return message.content[0].text
 
 
-def process_image(args, prompt: dict) -> tuple[str, str]:
+def process_image(args, prompt: dict, system_instructions: str) -> tuple[str, str]:
     """Generates feedback for an image submission.
     Returns the LLM prompt delivered and the returned response."""
     OUTPUT_DIRECTORY = "output_images"
@@ -152,6 +153,20 @@ def process_image(args, prompt: dict) -> tuple[str, str]:
             responses.append(openai_call(message, model="gpt-4o"))
         elif args.model == Models.CLAUDE.value:
             responses.append(anthropic_call(message, model="claude-3-7-sonnet-20250219"))
+        elif args.model == Models.REMOTE.value:
+            if args.remote_model:
+                model = RemoteModel(model_name=args.remote_model)
+            else:
+                model = RemoteModel()
+
+            _request, response = model.generate_response(
+                rendered_prompt,
+                args.submission,
+                system_instructions=system_instructions,
+                question_num=question,
+                submission_image=args.submission_image,
+            )
+            responses.append(str(response))
         else:
             responses.append(chat(model=args.model, messages=[message], options={"temperature": 0.33}).message.content)
 

ai_feedback/models/RemoteModel.py

@@ -1,11 +1,10 @@
-import json
 import os
 import re
 import sys
-import urllib.request
 from pathlib import Path
-from typing import List, Optional, Tuple
+from typing import Optional, Tuple
 
+import requests
 from dotenv import load_dotenv
 
 from .Model import Model
@@ -39,6 +38,7 @@ def generate_response(
         test_output: Optional[Path] = None,
         scope: Optional[str] = None,
         llama_mode: Optional[str] = None,
+        submission_image: Optional[str] = None,
     ) -> Optional[Tuple[str, str]]:
         """
         Generate a model response using the prompt and assignment files.
@@ -52,24 +52,21 @@ def generate_response(
             scope (Optional[str]): The scope to use for generating the response.
             system_instructions (str): instructions for the model
             llama_mode (Optional[str]): Optional mode to invoke llama.cpp in.
+            submission_image (Optional[str]): An optional path to a submission image file.
 
         Returns:
             Optional[Tuple[str, str]]: A tuple containing the prompt and the model's response,
                                        or None if the response was invalid.
         """
         load_dotenv()
 
-        headers = {"X-API-KEY": os.getenv("REMOTE_API_KEY"), "Content-Type": "application/json"}
+        headers = {"X-API-KEY": os.getenv("REMOTE_API_KEY")}
         data = {"content": prompt, "model": self.model_name, "system_instructions": system_instructions}
+        files = {}
+        if submission_image:
+            filename = os.path.basename(submission_image)
+            files[filename] = (filename, open(submission_image, 'rb'))
 
-        # Convert the data to JSON format
-        json_data = json.dumps(data).encode("utf-8")
+        response = requests.post(self.remote_url, data=data, headers=headers, files=files)
 
-        # Create the request
-        request = urllib.request.Request(self.remote_url, data=json_data, headers=headers, method="POST")
-
-        # Send the request and get the response
-        with urllib.request.urlopen(request) as response:
-            response = json.loads(response.read().decode())
-
-        return request, response
+        return prompt, response.json()