Method handle_models

rag_system/api_server.py:692–732

Return a list of locally installed Ollama models and supported HuggingFace models, grouped by capability.

(self)

            self.send_json_response({"error": f"Failed to start indexing: {str(e)}"}, status_code=500)

    def handle_models(self):
        """Return a list of locally installed Ollama models and supported HuggingFace models, grouped by capability."""
        try:
            generation_models = []
            embedding_models = []
            
            # Get Ollama models if available
            try:
                resp = requests.get(f"{RAG_AGENT.ollama_config['host']}/api/tags", timeout=5)
                resp.raise_for_status()
                data = resp.json()

                all_ollama_models = [m.get('name') for m in data.get('models', [])]

                # Very naive classification
                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)
            except Exception as e:
                print(f"⚠️ Could not get Ollama models: {e}")
            
            # 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: {e}"}, status_code=500)

    def send_json_response(self, data, status_code=200):
        """Utility to send a JSON response with CORS headers."""