Method handle_get_models

backend/server.py:746–782

Get available models from both Ollama and HuggingFace, grouped by capability

(self)

        }, status_code=410) # 410 Gone

    def handle_get_models(self):
        """Get available models from both Ollama and HuggingFace, grouped by capability"""
        try:
            generation_models = []
            embedding_models = []
            
            # Get Ollama models if available
            if self.ollama_client.is_ollama_running():
                all_ollama_models = self.ollama_client.list_models()
                
                # Very naive classification - same logic as RAG API server
                ollama_embedding_models = [m for m in all_ollama_models if any(k in m for k in ['embed','bge','embedding','text'])]
                ollama_generation_models = [m for m in all_ollama_models if m not in ollama_embedding_models]
                
                generation_models.extend(ollama_generation_models)
                embedding_models.extend(ollama_embedding_models)
            
            # Add supported HuggingFace embedding models
            huggingface_embedding_models = [
                "Qwen/Qwen3-Embedding-0.6B",
                "Qwen/Qwen3-Embedding-4B", 
                "Qwen/Qwen3-Embedding-8B"
            ]
            embedding_models.extend(huggingface_embedding_models)
            
            # Sort models for consistent ordering
            generation_models.sort()
            embedding_models.sort()
            
            self.send_json_response({
                "generation_models": generation_models,
                "embedding_models": embedding_models
            })
        except Exception as e:
            self.send_json_response({
                "error": f"Could not list models: {str(e)}"
            }, status_code=500)

    def handle_get_indexes(self):
        try: