chore: Update default embedding model to `sentence-transformers/all-mpnet-base-v2` in settings and deployment documentation.

config/settings.py

@@ -42,7 +42,7 @@ class Settings(BaseSettings):
         description="Request timeout for Ollama API in seconds",
     )
     embedding_model: str = Field(
-        default="nomic-embed-text",
+        default="sentence-transformers/all-mpnet-base-v2",
         description="Ollama embedding model name",
     )
     llm_model: str = Field(

deployment_readme.md

@@ -100,7 +100,7 @@ Once the Space is running:
 | `QDRANT_API_KEY`          | No       | -                          | Qdrant Cloud API key                                |
 | `QDRANT_PATH`             | No       | `./data/vectorstore`       | Local Qdrant path (if not using cloud)              |
 | `QDRANT_COLLECTION_NAME`  | No       | `eyewiki_rag`              | Qdrant collection name                              |
-| `EMBEDDING_MODEL`         | No       | `nomic-embed-text`         | Sentence-transformer embedding model                |
+| `EMBEDDING_MODEL`         | No       | `sentence-transformers/all-mpnet-base-v2` | Sentence-transformer embedding model                |
 | `API_PORT`                | No       | `8000`                     | API server port                                     |
 
 ---