feat: process pdfs synthetically im model does not support file natively (#2263)

* feat: process pdfs synthetically im model does not support file natively

* fix: small code optimisations

application/core/model_configs.py

@@ -8,8 +8,8 @@ from application.core.model_settings import (
     ModelProvider,
 )
 
-OPENAI_ATTACHMENTS = [
-    "application/pdf",
+# Base image attachment types supported by most vision-capable LLMs
+IMAGE_ATTACHMENTS = [
     "image/png",
     "image/jpeg",
     "image/jpg",
@@ -17,14 +17,15 @@ OPENAI_ATTACHMENTS = [
     "image/gif",
 ]
 
-GOOGLE_ATTACHMENTS = [
-    "application/pdf",
-    "image/png",
-    "image/jpeg",
-    "image/jpg",
-    "image/webp",
-    "image/gif",
-]
+# PDF excluded: most OpenAI-compatible endpoints don't support native PDF uploads.
+# When excluded, PDFs are synthetically processed by converting pages to images.
+OPENAI_ATTACHMENTS = IMAGE_ATTACHMENTS
+
+GOOGLE_ATTACHMENTS = ["application/pdf"] + IMAGE_ATTACHMENTS
+
+ANTHROPIC_ATTACHMENTS = IMAGE_ATTACHMENTS
+
+OPENROUTER_ATTACHMENTS = IMAGE_ATTACHMENTS
 
 
 OPENAI_MODELS = [
@@ -63,6 +64,7 @@ ANTHROPIC_MODELS = [
         description="Latest Claude 3.5 Sonnet with enhanced capabilities",
         capabilities=ModelCapabilities(
             supports_tools=True,
+            supported_attachment_types=ANTHROPIC_ATTACHMENTS,
             context_window=200000,
         ),
     ),
@@ -73,6 +75,7 @@ ANTHROPIC_MODELS = [
         description="Balanced performance and capability",
         capabilities=ModelCapabilities(
             supports_tools=True,
+            supported_attachment_types=ANTHROPIC_ATTACHMENTS,
             context_window=200000,
         ),
     ),
@@ -83,6 +86,7 @@ ANTHROPIC_MODELS = [
         description="Most capable Claude model",
         capabilities=ModelCapabilities(
             supports_tools=True,
+            supported_attachment_types=ANTHROPIC_ATTACHMENTS,
             context_window=200000,
         ),
     ),
@@ -93,6 +97,7 @@ ANTHROPIC_MODELS = [
         description="Fastest Claude model",
         capabilities=ModelCapabilities(
             supports_tools=True,
+            supported_attachment_types=ANTHROPIC_ATTACHMENTS,
             context_window=200000,
         ),
     ),
@@ -151,28 +156,43 @@ GROQ_MODELS = [
         ),
     ),
     AvailableModel(
-        id="llama-3.1-8b-instant",
+        id="openai/gpt-oss-120b",
         provider=ModelProvider.GROQ,
-        display_name="Llama 3.1 8B",
-        description="Ultra-fast inference",
+        display_name="GPT-OSS 120B",
+        description="Open-source GPT model optimized for speed",
         capabilities=ModelCapabilities(
             supports_tools=True,
             context_window=128000,
         ),
     ),
+]
+
+
+OPENROUTER_MODELS = [
     AvailableModel(
-        id="mixtral-8x7b-32768",
-        provider=ModelProvider.GROQ,
-        display_name="Mixtral 8x7B",
-        description="High-speed inference with tools",
+        id="qwen/qwen3-coder:free",
+        provider=ModelProvider.OPENROUTER,
+        display_name="Qwen 3 Coder",
+        description="Latest Qwen model with high-speed inference",
         capabilities=ModelCapabilities(
             supports_tools=True,
-            context_window=32768,
+            context_window=128000,
+            supported_attachment_types=OPENROUTER_ATTACHMENTS
+        ),
+    ),
+    AvailableModel(
+        id="google/gemma-3-27b-it:free",
+        provider=ModelProvider.OPENROUTER,
+        display_name="Gemma 3 27B",
+        description="Latest Gemma model with high-speed inference",
+        capabilities=ModelCapabilities(
+            supports_tools=True,
+            context_window=128000,
+            supported_attachment_types=OPENROUTER_ATTACHMENTS
         ),
     ),
 ]
 
-
 AZURE_OPENAI_MODELS = [
     AvailableModel(
         id="azure-gpt-4",

application/core/model_settings.py

@@ -8,6 +8,7 @@ logger = logging.getLogger(__name__)
 
 class ModelProvider(str, Enum):
     OPENAI = "openai"
+    OPENROUTER = "openrouter"
     AZURE_OPENAI = "azure_openai"
     ANTHROPIC = "anthropic"
     GROQ = "groq"
@@ -107,6 +108,10 @@ class ModelRegistry:
             settings.LLM_PROVIDER == "groq" and settings.API_KEY
         ):
             self._add_groq_models(settings)
+        if settings.OPEN_ROUTER_API_KEY or (
+            settings.LLM_PROVIDER == "openrouter" and settings.API_KEY
+        ):
+            self._add_openrouter_models(settings)
         if settings.HUGGINGFACE_API_KEY or (
             settings.LLM_PROVIDER == "huggingface" and settings.API_KEY
         ):
@@ -211,6 +216,21 @@ class ModelRegistry:
                     return
         for model in GROQ_MODELS:
             self.models[model.id] = model
+    
+    def _add_openrouter_models(self, settings):
+        from application.core.model_configs import OPENROUTER_MODELS
+
+        if settings.OPEN_ROUTER_API_KEY:
+            for model in OPENROUTER_MODELS:
+                self.models[model.id] = model
+            return
+        if settings.LLM_PROVIDER == "openrouter" and settings.LLM_NAME:
+            for model in OPENROUTER_MODELS:
+                if model.id == settings.LLM_NAME:
+                    self.models[model.id] = model
+                    return
+        for model in OPENROUTER_MODELS:
+            self.models[model.id] = model
 
     def _add_docsgpt_models(self, settings):
         model_id = "docsgpt-local"

application/core/model_utils.py

@@ -9,6 +9,7 @@ def get_api_key_for_provider(provider: str) -> Optional[str]:
 
     provider_key_map = {
         "openai": settings.OPENAI_API_KEY,
+        "openrouter": settings.OPEN_ROUTER_API_KEY,
         "anthropic": settings.ANTHROPIC_API_KEY,
         "google": settings.GOOGLE_API_KEY,
         "groq": settings.GROQ_API_KEY,

application/core/settings.py

@@ -81,6 +81,7 @@ class Settings(BaseSettings):
     GOOGLE_API_KEY: Optional[str] = None
     GROQ_API_KEY: Optional[str] = None
     HUGGINGFACE_API_KEY: Optional[str] = None
+    OPEN_ROUTER_API_KEY: Optional[str] = None
 
     OPENAI_API_BASE: Optional[str] = None  # azure openai api base url
     OPENAI_API_VERSION: Optional[str] = None  # azure openai api version