Merge branch 'main' into docs-windows-and-tui-restart

README.md

@@ -13,7 +13,7 @@
 
 OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with [Starlette](https://github.com/Kludex/starlette) and [Next.js](https://github.com/vercel/next.js). Powered by [OpenSearch](https://github.com/opensearch-project/OpenSearch), [Langflow](https://github.com/langflow-ai/langflow), and [Docling](https://github.com/docling-project/docling).
 
-<a href="https://deepwiki.com/phact/openrag"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
+<a href="https://deepwiki.com/langflow-ai/openrag"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 
 </div>
 <div align="center">

src/services/models_service.py

@@ -1,5 +1,6 @@
 import httpx
 from typing import Dict, List
+from api.provider_validation import test_embedding
 from utils.container_utils import transform_localhost_url
 from utils.logging_config import get_logger
 
@@ -9,18 +10,6 @@ logger = get_logger(__name__)
 class ModelsService:
     """Service for fetching available models from different AI providers"""
 
-    OLLAMA_EMBEDDING_MODELS = [
-        "nomic-embed-text",
-        "mxbai-embed-large",
-        "snowflake-arctic-embed",
-        "all-minilm",
-        "bge-m3",
-        "bge-large",
-        "paraphrase-multilingual",
-        "granite-embedding",
-        "jina-embeddings-v2-base-en",
-    ]
-
     OPENAI_TOOL_CALLING_MODELS = [
         "gpt-5",
         "gpt-5-mini",
@@ -171,10 +160,12 @@ class ModelsService:
                         has_tools = TOOL_CALLING_CAPABILITY in capabilities
 
                         # Check if it's an embedding model
-                        is_embedding = any(
-                            embed_model in model_name.lower()
-                            for embed_model in self.OLLAMA_EMBEDDING_MODELS
-                        )
+                        try:
+                            await test_embedding("ollama", endpoint=endpoint, embedding_model=model_name)
+                            is_embedding = True
+                        except Exception as e:
+                            logger.warning(f"Failed to test embedding for model {model_name}: {str(e)}")
+                            is_embedding = False
 
                         if is_embedding:
                             # Embedding models only need completion capability