Chore(deps): Bump the ai-group (#11798)

* Chore(deps): Bump llama-index-core from 0.12.33.post1 to 0.13.0

Bumps [llama-index-core](https://github.com/run-llama/llama_index) from 0.12.33.post1 to 0.13.0.
- [Release notes](https://github.com/run-llama/llama_index/releases)
- [Changelog](https://github.com/run-llama/llama_index/blob/main/CHANGELOG.md)
- [Commits](https://github.com/run-llama/llama_index/commits/v0.13.0)

---
updated-dependencies:
- dependency-name: llama-index-core
  dependency-version: 0.13.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>

* Update llama-index to latest versions

* Fix embedding mock

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>

src/paperless_ai/tests/test_chat.py

@@ -11,14 +11,12 @@ from paperless_ai.chat import stream_chat_with_documents
 @pytest.fixture(autouse=True)
 def patch_embed_model():
     from llama_index.core import settings as llama_settings
+    from llama_index.core.embeddings.mock_embed_model import MockEmbedding
 
-    mock_embed_model = MagicMock()
-    mock_embed_model._get_text_embedding_batch.return_value = [
-        [0.1] * 1536,
-    ]  # 1 vector per input
-    llama_settings.Settings._embed_model = mock_embed_model
+    # Use a real BaseEmbedding subclass to satisfy llama-index 0.14 validation
+    llama_settings.Settings.embed_model = MockEmbedding(embed_dim=1536)
     yield
-    llama_settings.Settings._embed_model = None
+    llama_settings.Settings.embed_model = None
 
 
 @pytest.fixture(autouse=True)