Merge pull request #53 from Red5d/main

Add image support to the OpenAI provider

simplemind/providers/openai.py

@@ -182,13 +182,32 @@ class OpenAI(BaseProvider):
         response_model: Type[T],
         *,
         llm_model: str | None = None,
+        image_url: str | None = None,
         **kwargs,
     ) -> T:
         """Get a structured response from the OpenAI API."""
         # Ensure messages are provided in kwargs
         messages = [
-            {"role": "user", "content": prompt},
+            {
+                "role": "user", 
+                "content": [
+                    {
+                        "type": "text", 
+                        "text": prompt
+                    }
+                ]
+            },
         ]
+
+        """Add an image (url or base64-encoded) to the message if provided."""
+        if image_url:
+            messages[0]['content'].append({
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url
+                }
+            })
+
         response = self.structured_client.chat.completions.create(
             messages=messages,
             model=llm_model or self.DEFAULT_MODEL,
@@ -199,12 +218,30 @@ class OpenAI(BaseProvider):
 
     @logger
     def generate_text(
-        self, prompt: str, *, llm_model: str | None = None, **kwargs
+        self, prompt: str, *, llm_model: str | None = None, image_url: str | None = None, **kwargs
     ):
         """Generate text using the OpenAI API."""
         messages = [
-            {"role": "user", "content": prompt},
+            {
+                "role": "user", 
+                "content": [
+                    {
+                        "type": "text", 
+                        "text": prompt
+                    }
+                ]
+            },
         ]
+
+        """Add an image (url or base64-encoded) to the message if provided."""
+        if image_url:
+            messages[0]['content'].append({
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url
+                }
+            })
+
         response = self.client.chat.completions.create(
             messages=messages,
             model=llm_model or self.DEFAULT_MODEL,
@@ -214,15 +251,33 @@ class OpenAI(BaseProvider):
 
     @logger
     def generate_stream_text(
-        self, prompt: str, *, llm_model: str | None = None, **kwargs
+        self, prompt: str, *, llm_model: str | None = None, image_url: str | None = None, **kwargs
     ) -> Iterator[str]:
         """Generate streaming text using the OpenAI API.
 
         Yields chunks of text as they are generated by the model.
         """
         messages = [
-            {"role": "user", "content": prompt},
+            {
+                "role": "user", 
+                "content": [
+                    {
+                        "type": "text", 
+                        "text": prompt
+                    }
+                ]
+            },
         ]
+
+        """Add an image (url or base64-encoded) to the message if provided."""
+        if image_url:
+            messages[0]['content'].append({
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url
+                }
+            })
+
         response = self.client.chat.completions.create(
             messages=messages,
             model=llm_model or self.DEFAULT_MODEL,