diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 9383fca37..82ea5c615 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -254,7 +254,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv pip install -e ".[dev,semantic]"
+          uv pip install -e ".[dev]"
 
       - name: Run tests (Semantic)
         run: |
@@ -296,7 +296,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv pip install -e ".[dev,semantic]"
+          uv pip install -e ".[dev]"
 
       - name: Run combined coverage (SQLite + Postgres)
         run: |
diff --git a/docs/post-v0.18.0-test-plan.md b/docs/post-v0.18.0-test-plan.md
index b1a18c938..f8972c0a4 100644
--- a/docs/post-v0.18.0-test-plan.md
+++ b/docs/post-v0.18.0-test-plan.md
@@ -79,7 +79,7 @@ These are the most important post-`v0.18.0` feature modules currently under-cove
 ### Acceptance criteria
 
 - `search_type=text|vector|hybrid` returns expected ranked results on canonical semantic corpus.
-- Missing semantic extras fail fast with actionable install guidance.
+- Missing semantic dependencies fail fast with actionable install guidance.
 - Reindex and provider/model changes produce valid vectors without dimension mismatch.
 - SQLite and Postgres produce equivalent behavior for semantic modes on the same dataset.
 - Generated-column migration path is valid on SQLite environments in use.
diff --git a/docs/semantic-search.md b/docs/semantic-search.md
index be77776e0..92ed027a5 100644
--- a/docs/semantic-search.md
+++ b/docs/semantic-search.md
@@ -1,26 +1,26 @@
 # Semantic Search
 
-This guide covers Basic Memory's optional semantic (vector) search feature, which adds meaning-based retrieval alongside the existing full-text search.
+This guide covers Basic Memory's semantic (vector) search feature, which adds meaning-based retrieval alongside the existing full-text search.
 
 ## Overview
 
-Basic Memory's default search uses full-text search (FTS) — keyword matching with boolean operators. Semantic search adds vector embeddings that capture the *meaning* of your content, enabling:
+Basic Memory's search supports both full-text search (FTS) and semantic retrieval. Semantic search adds vector embeddings that capture the *meaning* of your content, enabling:
 
 - **Paraphrase matching**: Find "authentication flow" when searching for "login process"
 - **Conceptual queries**: Search for "ways to improve performance" and find notes about caching, indexing, and optimization
 - **Hybrid retrieval**: Combine the precision of keyword search with the recall of semantic similarity
 
-Semantic search is **opt-in** — existing behavior is completely unchanged unless you enable it. It works on both SQLite (local) and Postgres (cloud) backends.
+Semantic search is enabled by default when semantic dependencies are available at runtime. It works on both SQLite (local) and Postgres (cloud) backends.
 
 ## Installation
 
-Semantic search dependencies (fastembed, sqlite-vec, openai) are **optional extras** — they are not installed with the base `basic-memory` package. Install them with:
+Semantic search dependencies (fastembed, sqlite-vec, openai) are included in the default `basic-memory` install.
 
 ```bash
-pip install 'basic-memory[semantic]'
+pip install basic-memory
 ```
 
-This keeps the base install lightweight and avoids platform-specific issues with ONNX Runtime wheels.
+You can always override with `BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED=true|false`.
 
 ### Platform Compatibility
 
@@ -34,36 +34,40 @@ This keeps the base install lightweight and avoids platform-specific issues with
 
 #### Intel Mac Workaround
 
-The default FastEmbed provider uses ONNX Runtime, which dropped Intel Mac (x86_64) wheels starting in v1.24. Intel Mac users have two options:
+The default install includes FastEmbed, which depends on ONNX Runtime. ONNX Runtime dropped Intel Mac (x86_64) wheels starting in v1.24, so install with a compatible ONNX Runtime pin first:
 
-**Option 1: Use OpenAI embeddings (recommended)**
+```bash
+pip install basic-memory 'onnxruntime<1.24'
+```
 
-Install only the OpenAI dependency manually — no ONNX Runtime or FastEmbed needed:
+After installation, Intel Mac users have two runtime options:
+
+**Option 1: Use OpenAI embeddings (recommended)**
 
 ```bash
-pip install openai sqlite-vec
 export BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED=true
 export BASIC_MEMORY_SEMANTIC_EMBEDDING_PROVIDER=openai
 export OPENAI_API_KEY=sk-...
 ```
 
-**Option 2: Pin an older ONNX Runtime**
+**Option 2: Use FastEmbed locally**
 
-FastEmbed's ONNX Runtime dependency is unpinned, so you can constrain it to an older version that still ships Intel Mac wheels by passing both requirements in the same install command:
+Keep the same pinned installation and use FastEmbed (default provider):
 
 ```bash
-pip install 'basic-memory[semantic]' 'onnxruntime<1.24'
+export BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED=true
+export BASIC_MEMORY_SEMANTIC_EMBEDDING_PROVIDER=fastembed
 ```
 
 ## Quick Start
 
-1. Install semantic extras:
+1. Install Basic Memory:
 
 ```bash
-pip install 'basic-memory[semantic]'
+pip install basic-memory
 ```
 
-2. Enable semantic search:
+2. (Optional) Explicitly enable semantic search:
 
 ```bash
 export BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED=true
@@ -84,7 +88,7 @@ search_notes("login process", search_type="vector")
 # Hybrid: combines FTS precision with vector recall (recommended)
 search_notes("login process", search_type="hybrid")
 
-# Traditional full-text search (still the default)
+# Explicit full-text search
 search_notes("login process", search_type="text")
 ```
 
@@ -94,7 +98,7 @@ All settings are fields on `BasicMemoryConfig` and can be set via environment va
 
 | Config Field | Env Var | Default | Description |
 |---|---|---|---|
-| `semantic_search_enabled` | `BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED` | `false` | Enable semantic search. Required before vector/hybrid modes work. |
+| `semantic_search_enabled` | `BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED` | Auto (`true` when semantic deps are available) | Enable semantic search. Required before vector/hybrid modes work. |
 | `semantic_embedding_provider` | `BASIC_MEMORY_SEMANTIC_EMBEDDING_PROVIDER` | `"fastembed"` | Embedding provider: `"fastembed"` (local) or `"openai"` (API). |
 | `semantic_embedding_model` | `BASIC_MEMORY_SEMANTIC_EMBEDDING_MODEL` | `"bge-small-en-v1.5"` | Model identifier. Auto-adjusted per provider if left at default. |
 | `semantic_embedding_dimensions` | `BASIC_MEMORY_SEMANTIC_EMBEDDING_DIMENSIONS` | Auto-detected | Vector dimensions. 384 for FastEmbed, 1536 for OpenAI. Override only if using a non-default model. |
@@ -112,8 +116,8 @@ FastEmbed runs entirely locally using ONNX models — no API key, no network cal
 - **Tradeoff**: Smaller model, fast inference, good quality for most use cases
 
 ```bash
-# Install semantic extras and enable
-pip install 'basic-memory[semantic]'
+# Install basic-memory and enable semantic search
+pip install basic-memory
 export BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED=true
 ```
 
@@ -197,7 +201,8 @@ bm reindex -p my-project
 
 ### When You Need to Reindex
 
-- **First enable**: After turning on `semantic_search_enabled` for the first time
+- **Upgrade note**: Migration now performs a one-time automatic embedding backfill on upgrade.
+- **Manual enable case**: If you explicitly had `semantic_search_enabled=false` and then turn it on
 - **Provider change**: After switching between `fastembed` and `openai`
 - **Model change**: After changing `semantic_embedding_model`
 - **Dimension change**: After changing `semantic_embedding_dimensions`
diff --git a/justfile b/justfile
index 148ff2bea..229c74be0 100644
--- a/justfile
+++ b/justfile
@@ -2,7 +2,7 @@
 
 # Install dependencies
 install:
-    uv sync --extra semantic
+    uv sync
     @echo ""
     @echo "💡 Remember to activate the virtual environment by running: source .venv/bin/activate"
 
diff --git a/pyproject.toml b/pyproject.toml
index d44c061bf..bfbd5de73 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -44,10 +44,6 @@ dependencies = [
     "sniffio>=1.3.1",
     "anyio>=4.10.0",
     "httpx>=0.28.0",
-]
-
-[project.optional-dependencies]
-semantic = [
     "fastembed>=0.7.4",
     "sqlite-vec>=0.1.6",
     "openai>=1.100.2",
@@ -78,7 +74,7 @@ markers = [
     "postgres: Tests that run against Postgres backend (deselect with '-m \"not postgres\"')",
     "windows: Windows-specific tests (deselect with '-m \"not windows\"')",
     "smoke: Fast end-to-end smoke tests for MCP flows",
-    "semantic: Tests requiring [semantic] extras (fastembed, sqlite-vec, openai)",
+    "semantic: Tests requiring semantic dependencies (fastembed, sqlite-vec, openai)",
 ]
 
 [tool.ruff]
diff --git a/src/basic_memory/alembic/versions/i2c3d4e5f6g7_auto_backfill_semantic_embeddings.py b/src/basic_memory/alembic/versions/i2c3d4e5f6g7_auto_backfill_semantic_embeddings.py
new file mode 100644
index 000000000..75c8694ff
--- /dev/null
+++ b/src/basic_memory/alembic/versions/i2c3d4e5f6g7_auto_backfill_semantic_embeddings.py
@@ -0,0 +1,29 @@
+"""Trigger automatic semantic embedding backfill during migration.
+
+Revision ID: i2c3d4e5f6g7
+Revises: h1b2c3d4e5f6
+Create Date: 2026-02-19 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+# revision identifiers, used by Alembic.
+revision: str = "i2c3d4e5f6g7"
+down_revision: Union[str, None] = "h1b2c3d4e5f6"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """No schema change.
+
+    Trigger: this revision is newly applied.
+    Why: db.run_migrations() detects this revision transition and runs the existing
+    sync_entity_vectors() pipeline to backfill semantic embeddings automatically.
+    Outcome: users no longer need to run `bm reindex --embeddings` after upgrading.
+    """
+
+
+def downgrade() -> None:
+    """No-op downgrade."""
diff --git a/src/basic_memory/cli/commands/tool.py b/src/basic_memory/cli/commands/tool.py
index 7ef289f42..875bd0d92 100644
--- a/src/basic_memory/cli/commands/tool.py
+++ b/src/basic_memory/cli/commands/tool.py
@@ -847,8 +847,8 @@ def search_notes(
         if not metadata_filters:
             metadata_filters = None
 
-        # set search type
-        search_type = "text"
+        # set search type (None delegates to MCP tool default selection)
+        search_type: str | None = None
         if permalink:
             search_type = "permalink"
             if query and "*" in query:
diff --git a/src/basic_memory/config.py b/src/basic_memory/config.py
index d48c9b055..d5f849815 100644
--- a/src/basic_memory/config.py
+++ b/src/basic_memory/config.py
@@ -40,8 +40,9 @@ class DatabaseBackend(str, Enum):
 
 
 def _default_semantic_search_enabled() -> bool:
-    """Enable semantic search by default when semantic extras are installed."""
-    return importlib.util.find_spec("fastembed") is not None
+    """Enable semantic search by default when required local semantic dependencies exist."""
+    required_modules = ("fastembed", "sqlite_vec")
+    return all(importlib.util.find_spec(module_name) is not None for module_name in required_modules)
 
 
 @dataclass
@@ -145,7 +146,7 @@ class BasicMemoryConfig(BaseSettings):
     # Semantic search configuration
     semantic_search_enabled: bool = Field(
         default_factory=_default_semantic_search_enabled,
-        description="Enable semantic search (vector/hybrid retrieval). Works on both SQLite and Postgres backends. Requires semantic extras.",
+        description="Enable semantic search (vector/hybrid retrieval). Works on both SQLite and Postgres backends. Requires semantic dependencies (included by default).",
     )
     semantic_embedding_provider: str = Field(
         default="fastembed",
diff --git a/src/basic_memory/db.py b/src/basic_memory/db.py
index 8247345c5..e12b8a76b 100644
--- a/src/basic_memory/db.py
+++ b/src/basic_memory/db.py
@@ -43,6 +43,99 @@
 _engine: Optional[AsyncEngine] = None
 _session_maker: Optional[async_sessionmaker[AsyncSession]] = None
 
+# Alembic revision that enables one-time automatic embedding backfill.
+SEMANTIC_EMBEDDING_BACKFILL_REVISION = "i2c3d4e5f6g7"
+
+
+async def _load_applied_alembic_revisions(
+    session_maker: async_sessionmaker[AsyncSession],
+) -> set[str]:
+    """Load applied Alembic revisions from alembic_version.
+
+    Returns an empty set when the version table does not exist yet
+    (fresh database before first migration).
+    """
+    try:
+        async with scoped_session(session_maker) as session:
+            result = await session.execute(text("SELECT version_num FROM alembic_version"))
+            return {str(row[0]) for row in result.fetchall() if row[0]}
+    except Exception as exc:
+        error_message = str(exc).lower()
+        if "alembic_version" in error_message and (
+            "no such table" in error_message or "does not exist" in error_message
+        ):
+            return set()
+        raise
+
+
+def _should_run_semantic_embedding_backfill(
+    revisions_before_upgrade: set[str],
+    revisions_after_upgrade: set[str],
+) -> bool:
+    """Check if this migration run newly applied the backfill-trigger revision."""
+    return (
+        SEMANTIC_EMBEDDING_BACKFILL_REVISION in revisions_after_upgrade
+        and SEMANTIC_EMBEDDING_BACKFILL_REVISION not in revisions_before_upgrade
+    )
+
+
+async def _run_semantic_embedding_backfill(
+    app_config: BasicMemoryConfig,
+    session_maker: async_sessionmaker[AsyncSession],
+) -> None:
+    """Backfill semantic embeddings for all active projects/entities."""
+    if not app_config.semantic_search_enabled:
+        logger.info("Skipping automatic semantic embedding backfill: semantic search is disabled.")
+        return
+
+    async with scoped_session(session_maker) as session:
+        project_result = await session.execute(
+            text("SELECT id, name FROM project WHERE is_active = :is_active ORDER BY id"),
+            {"is_active": True},
+        )
+        projects = [(int(row[0]), str(row[1])) for row in project_result.fetchall()]
+
+    if not projects:
+        logger.info("Skipping automatic semantic embedding backfill: no active projects found.")
+        return
+
+    repository_class = (
+        PostgresSearchRepository
+        if app_config.database_backend == DatabaseBackend.POSTGRES
+        else SQLiteSearchRepository
+    )
+
+    total_entities = 0
+    for project_id, project_name in projects:
+        async with scoped_session(session_maker) as session:
+            entity_result = await session.execute(
+                text("SELECT id FROM entity WHERE project_id = :project_id ORDER BY id"),
+                {"project_id": project_id},
+            )
+            entity_ids = [int(row[0]) for row in entity_result.fetchall()]
+
+        if not entity_ids:
+            continue
+
+        total_entities += len(entity_ids)
+        logger.info(
+            "Automatic semantic embedding backfill: "
+            f"project={project_name}, entities={len(entity_ids)}"
+        )
+
+        search_repository = repository_class(
+            session_maker,
+            project_id=project_id,
+            app_config=app_config,
+        )
+        for entity_id in entity_ids:
+            await search_repository.sync_entity_vectors(entity_id)
+
+    logger.info(
+        "Automatic semantic embedding backfill complete: "
+        f"projects={len(projects)}, entities={total_entities}"
+    )
+
 
 class DatabaseType(Enum):
     """Types of supported databases."""
@@ -384,6 +477,23 @@ async def run_migrations(
     """
     logger.info("Running database migrations...")
     try:
+        revisions_before_upgrade: set[str] = set()
+        # Trigger: run_migrations() can be invoked before module-level session maker is set.
+        # Why: we still need reliable before/after revision detection for one-time backfill.
+        # Outcome: create a short-lived session maker when needed, then dispose it immediately.
+        if _session_maker is None:
+            temp_engine, temp_session_maker = _create_engine_and_session(
+                app_config.database_path,
+                database_type,
+                app_config,
+            )
+            try:
+                revisions_before_upgrade = await _load_applied_alembic_revisions(temp_session_maker)
+            finally:
+                await temp_engine.dispose()
+        else:
+            revisions_before_upgrade = await _load_applied_alembic_revisions(_session_maker)
+
         # Get the absolute path to the alembic directory relative to this file
         alembic_dir = Path(__file__).parent / "alembic"
         config = Config()
@@ -422,6 +532,13 @@ async def run_migrations(
             await PostgresSearchRepository(session_maker, 1).init_search_index()
         else:
             await SQLiteSearchRepository(session_maker, 1).init_search_index()
+
+        revisions_after_upgrade = await _load_applied_alembic_revisions(session_maker)
+        if _should_run_semantic_embedding_backfill(
+            revisions_before_upgrade,
+            revisions_after_upgrade,
+        ):
+            await _run_semantic_embedding_backfill(app_config, session_maker)
     except Exception as e:  # pragma: no cover
         logger.error(f"Error running migrations: {e}")
         raise
diff --git a/src/basic_memory/mcp/tools/chatgpt_tools.py b/src/basic_memory/mcp/tools/chatgpt_tools.py
index baad43047..f9040153b 100644
--- a/src/basic_memory/mcp/tools/chatgpt_tools.py
+++ b/src/basic_memory/mcp/tools/chatgpt_tools.py
@@ -120,7 +120,6 @@ async def search(
             project=default_project,  # Use default project for ChatGPT
             page=1,
             page_size=10,  # Reasonable default for ChatGPT consumption
-            search_type="text",  # Default to full-text search
             output_format="json",
             context=context,
         )
diff --git a/src/basic_memory/mcp/tools/search.py b/src/basic_memory/mcp/tools/search.py
index 1c3e5e841..cfae2f3b2 100644
--- a/src/basic_memory/mcp/tools/search.py
+++ b/src/basic_memory/mcp/tools/search.py
@@ -29,6 +29,11 @@ def _semantic_search_enabled_for_text_search() -> bool:
         return ConfigManager().config.semantic_search_enabled
 
 
+def _default_search_type() -> str:
+    """Pick default search mode from semantic-search config."""
+    return "hybrid" if _semantic_search_enabled_for_text_search() else "text"
+
+
 def _format_search_error_response(
     project: str, error_message: str, query: str, search_type: str = "text"
 ) -> str:
@@ -57,7 +62,7 @@ def _format_search_error_response(
             Semantic retrieval is enabled but required packages are not installed.
 
             ## Fix
-            1. Install semantic extras: `pip install 'basic-memory[semantic]'`
+            1. Install/update Basic Memory: `pip install -U basic-memory`
             2. Restart Basic Memory
             3. Retry your query:
                `search_notes("{project}", "{query}", search_type="{search_type}")`
@@ -252,7 +257,7 @@ async def search_notes(
     workspace: Optional[str] = None,
     page: int = 1,
     page_size: int = 10,
-    search_type: str = "text",
+    search_type: str | None = None,
     output_format: Literal["text", "json"] = "text",
     types: List[str] | None = None,
     entity_types: List[str] | None = None,
@@ -295,8 +300,8 @@ async def search_notes(
     ### Search Type Examples
     - `search_notes("my-project", "Meeting", search_type="title")` - Search only in titles
     - `search_notes("work-docs", "docs/meeting-*", search_type="permalink")` - Pattern match permalinks
-    - `search_notes("research", "keyword", search_type="text")` - Text search (default; auto-upgrades
-      to hybrid when semantic search is enabled)
+    - `search_notes("research", "keyword")` - Default search (hybrid when semantic is enabled,
+      text when disabled)
 
     ### Filtering Options
     - `search_notes("my-project", "query", types=["entity"])` - Search only entities
@@ -339,8 +344,8 @@ async def search_notes(
         page: The page number of results to return (default 1)
         page_size: The number of results to return per page (default 10)
         search_type: Type of search to perform, one of:
-                    "text", "title", "permalink", "vector", "semantic", "hybrid" (default: "text";
-                    text mode auto-upgrades to hybrid when semantic search is enabled)
+                    "text", "title", "permalink", "vector", "semantic", "hybrid".
+                    Default is dynamic: "hybrid" when semantic search is enabled, otherwise "text".
         output_format: "text" preserves existing structured search response behavior.
             "json" returns a machine-readable dictionary payload.
         types: Optional list of note types to search (e.g., ["note", "person"])
@@ -426,9 +431,10 @@ async def search_notes(
         _, resolved_query, is_memory_url = await resolve_project_and_path(
             client, query, project, context
         )
+        effective_search_type = search_type or _default_search_type()
         if is_memory_url:
             query = resolved_query
-            search_type = "permalink"
+            effective_search_type = "permalink"
 
         try:
             # Create a SearchQuery object based on the parameters
@@ -436,27 +442,24 @@ async def search_notes(
 
             # Map search_type to the appropriate query field and retrieval mode
             valid_search_types = {"text", "title", "permalink", "vector", "semantic", "hybrid"}
-            if search_type == "text":
+            if effective_search_type == "text":
                 search_query.text = query
-                # Upgrade to hybrid when semantic search is available —
-                # combines FTS keyword matching with vector similarity for better results
-                if _semantic_search_enabled_for_text_search():
-                    search_query.retrieval_mode = SearchRetrievalMode.HYBRID
-            elif search_type in ("vector", "semantic"):
+                search_query.retrieval_mode = SearchRetrievalMode.FTS
+            elif effective_search_type in ("vector", "semantic"):
                 search_query.text = query
                 search_query.retrieval_mode = SearchRetrievalMode.VECTOR
-            elif search_type == "hybrid":
+            elif effective_search_type == "hybrid":
                 search_query.text = query
                 search_query.retrieval_mode = SearchRetrievalMode.HYBRID
-            elif search_type == "title":
+            elif effective_search_type == "title":
                 search_query.title = query
-            elif search_type == "permalink" and "*" in query:
+            elif effective_search_type == "permalink" and "*" in query:
                 search_query.permalink_match = query
-            elif search_type == "permalink":
+            elif effective_search_type == "permalink":
                 search_query.permalink = query
             else:
                 raise ValueError(
-                    f"Invalid search_type '{search_type}'. "
+                    f"Invalid search_type '{effective_search_type}'. "
                     f"Valid options: {', '.join(sorted(valid_search_types))}"
                 )
 
@@ -504,7 +507,9 @@ async def search_notes(
         except Exception as e:
             logger.error(f"Search failed for query '{query}': {e}, project: {active_project.name}")
             # Return formatted error message as string for better user experience
-            return _format_search_error_response(active_project.name, str(e), query, search_type)
+            return _format_search_error_response(
+                active_project.name, str(e), query, effective_search_type
+            )
 
 
 @mcp.tool(
diff --git a/src/basic_memory/mcp/tools/ui_sdk.py b/src/basic_memory/mcp/tools/ui_sdk.py
index 985a84a4d..6c4da5d04 100644
--- a/src/basic_memory/mcp/tools/ui_sdk.py
+++ b/src/basic_memory/mcp/tools/ui_sdk.py
@@ -26,7 +26,7 @@ async def search_notes_ui(
     project: Optional[str] = None,
     page: int = 1,
     page_size: int = 10,
-    search_type: str = "text",
+    search_type: Optional[str] = None,
     types: List[str] | None = None,
     entity_types: List[str] | None = None,
     after_date: Optional[str] = None,
diff --git a/src/basic_memory/repository/fastembed_provider.py b/src/basic_memory/repository/fastembed_provider.py
index b59673b54..b8c2bde39 100644
--- a/src/basic_memory/repository/fastembed_provider.py
+++ b/src/basic_memory/repository/fastembed_provider.py
@@ -48,7 +48,8 @@ def _create_model() -> "TextEmbedding":
                 ) as exc:  # pragma: no cover - exercised via tests with monkeypatch
                     raise SemanticDependenciesMissingError(
                         "fastembed package is missing. "
-                        "Install semantic extras: pip install 'basic-memory[semantic]'"
+                        "Install/update basic-memory to include semantic dependencies: "
+                        "pip install -U basic-memory"
                     ) from exc
                 resolved_model_name = self._MODEL_ALIASES.get(self.model_name, self.model_name)
                 return TextEmbedding(model_name=resolved_model_name)
diff --git a/src/basic_memory/repository/openai_provider.py b/src/basic_memory/repository/openai_provider.py
index 65a6021bc..69c4acfa6 100644
--- a/src/basic_memory/repository/openai_provider.py
+++ b/src/basic_memory/repository/openai_provider.py
@@ -45,7 +45,8 @@ async def _get_client(self) -> Any:
             except ImportError as exc:  # pragma: no cover - covered via monkeypatch tests
                 raise SemanticDependenciesMissingError(
                     "OpenAI dependency is missing. "
-                    "Install semantic extras: pip install 'basic-memory[semantic]'"
+                    "Install/update basic-memory to include semantic dependencies: "
+                    "pip install -U basic-memory"
                 ) from exc
 
             api_key = self._api_key or os.getenv("OPENAI_API_KEY")
diff --git a/src/basic_memory/repository/search_repository_base.py b/src/basic_memory/repository/search_repository_base.py
index 4919a68b5..0f573a04d 100644
--- a/src/basic_memory/repository/search_repository_base.py
+++ b/src/basic_memory/repository/search_repository_base.py
@@ -355,7 +355,8 @@ def _assert_semantic_available(self) -> None:
         if self._embedding_provider is None:
             raise SemanticDependenciesMissingError(
                 "No embedding provider configured. "
-                "Install semantic extras: pip install 'basic-memory[semantic]' "
+                "Install/update basic-memory to include semantic dependencies "
+                "(pip install -U basic-memory) "
                 "and set semantic_search_enabled=true."
             )
 
diff --git a/src/basic_memory/repository/sqlite_search_repository.py b/src/basic_memory/repository/sqlite_search_repository.py
index ecb540524..a0bdb20d7 100644
--- a/src/basic_memory/repository/sqlite_search_repository.py
+++ b/src/basic_memory/repository/sqlite_search_repository.py
@@ -347,7 +347,8 @@ async def _ensure_sqlite_vec_loaded(self, session) -> None:
         except ImportError as exc:
             raise SemanticDependenciesMissingError(
                 "sqlite-vec package is missing. "
-                "Install semantic extras: pip install 'basic-memory[semantic]'"
+                "Install/update basic-memory to include semantic dependencies: "
+                "pip install -U basic-memory"
             ) from exc
 
         async with self._sqlite_vec_lock:
diff --git a/test-int/semantic/conftest.py b/test-int/semantic/conftest.py
index 75709dbb4..4369906b0 100644
--- a/test-int/semantic/conftest.py
+++ b/test-int/semantic/conftest.py
@@ -95,11 +95,11 @@ def skip_if_needed(combo: SearchCombo) -> None:
         pytest.skip("Docker not available for Postgres testcontainer")
 
     if combo.provider_name == "fastembed" and not _fastembed_available():
-        pytest.skip("fastembed not installed (install basic-memory[semantic])")
+        pytest.skip("fastembed not installed (install/update basic-memory)")
 
     if combo.provider_name == "openai":
         if not _fastembed_available():
-            pytest.skip("semantic extras not installed")
+            pytest.skip("semantic dependencies not installed")
         if not _openai_key_available():
             pytest.skip("OPENAI_API_KEY not set")
 
diff --git a/tests/mcp/test_tool_search.py b/tests/mcp/test_tool_search.py
index cf20b4df0..e0261cf5a 100644
--- a/tests/mcp/test_tool_search.py
+++ b/tests/mcp/test_tool_search.py
@@ -6,7 +6,7 @@
 
 from basic_memory.mcp.tools import write_note
 from basic_memory.mcp.tools.search import search_notes, _format_search_error_response
-from basic_memory.schemas.search import SearchResponse
+from basic_memory.schemas.search import SearchItemType, SearchResponse
 
 
 @pytest.mark.asyncio
@@ -331,13 +331,13 @@ def test_format_search_error_semantic_dependencies_missing(self):
         """Test formatting for missing semantic dependencies."""
         result = _format_search_error_response(
             "test-project",
-            "fastembed package is missing. Install semantic extras: pip install 'basic-memory[semantic]'",
+            "fastembed package is missing. Install/update basic-memory to include semantic dependencies: pip install -U basic-memory",
             "semantic query",
             "hybrid",
         )
 
         assert "# Search Failed - Semantic Dependencies Missing" in result
-        assert "pip install 'basic-memory[semantic]'" in result
+        assert "pip install -U basic-memory" in result
 
     def test_format_search_error_generic(self):
         """Test formatting for generic errors."""
@@ -615,7 +615,7 @@ async def fake_get_project_client(*args, **kwargs):
             title=f"Item {i}",
             permalink=f"item-{i}",
             file_path=f"item-{i}.md",
-            type="entity",
+            type=SearchItemType.ENTITY,
             score=1.0 - i * 0.1,
         )
         for i in range(5)
@@ -775,8 +775,8 @@ async def search(self, payload, page, page_size):
 
 
 @pytest.mark.asyncio
-async def test_search_notes_text_upgrades_to_hybrid_when_semantic_enabled(monkeypatch):
-    """Default text search should auto-upgrade to hybrid when semantic search is enabled."""
+async def test_search_notes_defaults_to_hybrid_when_semantic_enabled(monkeypatch):
+    """When search_type is omitted, semantic-enabled configs should default to hybrid."""
     import importlib
     from dataclasses import dataclass
 
@@ -817,7 +817,7 @@ class StubConfig:
 
     @dataclass
     class StubContainer:
-        config: StubConfig = None
+        config: StubConfig | None = None
 
         def __post_init__(self):
             if self.config is None:
@@ -828,17 +828,16 @@ def __post_init__(self):
     await search_mod.search_notes.fn(
         project="test-project",
         query="test query",
-        search_type="text",
     )
 
-    # Default text search should have been upgraded to hybrid
+    # Default mode should be hybrid when semantic search is enabled
     assert captured_payload["retrieval_mode"] == "hybrid"
     assert captured_payload["text"] == "test query"
 
 
 @pytest.mark.asyncio
-async def test_search_notes_text_stays_fts_when_semantic_disabled(monkeypatch):
-    """Default text search should stay FTS when semantic search is disabled."""
+async def test_search_notes_defaults_to_fts_when_semantic_disabled(monkeypatch):
+    """When search_type is omitted, semantic-disabled configs should default to FTS."""
     import importlib
     from dataclasses import dataclass
 
@@ -879,7 +878,67 @@ class StubConfig:
 
     @dataclass
     class StubContainer:
-        config: StubConfig = None
+        config: StubConfig | None = None
+
+        def __post_init__(self):
+            if self.config is None:
+                self.config = StubConfig()
+
+    monkeypatch.setattr(search_mod, "get_container", lambda: StubContainer())
+
+    await search_mod.search_notes.fn(
+        project="test-project",
+        query="test query",
+    )
+
+    # Default mode should be FTS when semantic search is disabled
+    assert captured_payload["retrieval_mode"] == "fts"
+    assert captured_payload["text"] == "test query"
+
+
+@pytest.mark.asyncio
+async def test_search_notes_explicit_text_stays_fts_when_semantic_enabled(monkeypatch):
+    """Explicit text mode should preserve FTS behavior even when semantic is enabled."""
+    import importlib
+    from dataclasses import dataclass
+
+    search_mod = importlib.import_module("basic_memory.mcp.tools.search")
+    clients_mod = importlib.import_module("basic_memory.mcp.clients")
+
+    class StubProject:
+        name = "test-project"
+        external_id = "test-external-id"
+
+    @asynccontextmanager
+    async def fake_get_project_client(*args, **kwargs):
+        yield (object(), StubProject())
+
+    async def fake_resolve_project_and_path(
+        client, identifier, project=None, context=None, headers=None
+    ):
+        return StubProject(), identifier, False
+
+    captured_payload: dict = {}
+
+    class MockSearchClient:
+        def __init__(self, *args, **kwargs):
+            pass
+
+        async def search(self, payload, page, page_size):
+            captured_payload.update(payload)
+            return SearchResponse(results=[], current_page=page, page_size=page_size)
+
+    monkeypatch.setattr(search_mod, "get_project_client", fake_get_project_client)
+    monkeypatch.setattr(search_mod, "resolve_project_and_path", fake_resolve_project_and_path)
+    monkeypatch.setattr(clients_mod, "SearchClient", MockSearchClient)
+
+    @dataclass
+    class StubConfig:
+        semantic_search_enabled: bool = True
+
+    @dataclass
+    class StubContainer:
+        config: StubConfig | None = None
 
         def __post_init__(self):
             if self.config is None:
@@ -893,14 +952,13 @@ def __post_init__(self):
         search_type="text",
     )
 
-    # Should stay as default FTS (no retrieval_mode override)
     assert captured_payload["retrieval_mode"] == "fts"
     assert captured_payload["text"] == "test query"
 
 
 @pytest.mark.asyncio
-async def test_search_notes_text_upgrades_to_hybrid_when_container_not_initialized(monkeypatch):
-    """Default text search should upgrade to hybrid in CLI contexts when semantic is enabled."""
+async def test_search_notes_defaults_to_hybrid_when_container_not_initialized(monkeypatch):
+    """CLI fallback config should still default omitted search_type to hybrid."""
     import importlib
 
     search_mod = importlib.import_module("basic_memory.mcp.tools.search")
@@ -951,7 +1009,6 @@ def raise_runtime_error():
     await search_mod.search_notes.fn(
         project="test-project",
         query="test query",
-        search_type="text",
     )
 
     # Should upgrade using ConfigManager fallback
@@ -960,10 +1017,10 @@ def raise_runtime_error():
 
 
 @pytest.mark.asyncio
-async def test_search_notes_text_stays_fts_when_container_not_initialized_and_semantic_disabled(
+async def test_search_notes_defaults_to_fts_when_container_not_initialized_and_semantic_disabled(
     monkeypatch,
 ):
-    """Default text search should remain FTS in CLI contexts when semantic is disabled."""
+    """CLI fallback config should default omitted search_type to FTS when semantic is disabled."""
     import importlib
 
     search_mod = importlib.import_module("basic_memory.mcp.tools.search")
@@ -1013,7 +1070,6 @@ def raise_runtime_error():
     await search_mod.search_notes.fn(
         project="test-project",
         query="test query",
-        search_type="text",
     )
 
     assert captured_payload["retrieval_mode"] == "fts"
diff --git a/tests/mcp/tools/test_chatgpt_tools.py b/tests/mcp/tools/test_chatgpt_tools.py
index d3f952696..15c9edbe5 100644
--- a/tests/mcp/tools/test_chatgpt_tools.py
+++ b/tests/mcp/tools/test_chatgpt_tools.py
@@ -66,6 +66,25 @@ async def fake_search_notes_fn(*args, **kwargs):
     assert "error_details" in content
 
 
+@pytest.mark.asyncio
+async def test_search_uses_dynamic_default_search_type(monkeypatch, client, test_project):
+    """ChatGPT adapter should not hardcode search_type so search_notes can pick defaults."""
+    import basic_memory.mcp.tools.chatgpt_tools as chatgpt_tools
+
+    captured_kwargs: dict = {}
+
+    async def fake_search_notes_fn(*args, **kwargs):
+        captured_kwargs.update(kwargs)
+        return {"results": []}
+
+    monkeypatch.setattr(chatgpt_tools.search_notes, "fn", fake_search_notes_fn)
+
+    result = await chatgpt_tools.search.fn("default search mode query")
+
+    assert isinstance(result, list)
+    assert "search_type" not in captured_kwargs
+
+
 @pytest.mark.asyncio
 async def test_fetch_successful_document(client, test_project):
     """Test fetch with successful document retrieval."""
diff --git a/tests/repository/test_fastembed_provider.py b/tests/repository/test_fastembed_provider.py
index a10c5aa71..79762c72b 100644
--- a/tests/repository/test_fastembed_provider.py
+++ b/tests/repository/test_fastembed_provider.py
@@ -84,4 +84,4 @@ def _raising_import(name, globals=None, locals=None, fromlist=(), level=0):
     with pytest.raises(SemanticDependenciesMissingError) as error:
         await provider.embed_query("test")
 
-    assert "pip install 'basic-memory[semantic]'" in str(error.value)
+    assert "pip install -U basic-memory" in str(error.value)
diff --git a/tests/repository/test_openai_provider.py b/tests/repository/test_openai_provider.py
index 8fb8dafb3..50a3d52b6 100644
--- a/tests/repository/test_openai_provider.py
+++ b/tests/repository/test_openai_provider.py
@@ -92,7 +92,7 @@ def _raising_import(name, globals=None, locals=None, fromlist=(), level=0):
     with pytest.raises(SemanticDependenciesMissingError) as error:
         await provider.embed_query("test")
 
-    assert "pip install 'basic-memory[semantic]'" in str(error.value)
+    assert "pip install -U basic-memory" in str(error.value)
 
 
 @pytest.mark.asyncio
diff --git a/tests/services/test_initialization.py b/tests/services/test_initialization.py
index 0ebfc84ed..469c6970e 100644
--- a/tests/services/test_initialization.py
+++ b/tests/services/test_initialization.py
@@ -6,6 +6,7 @@
 
 from __future__ import annotations
 
+from datetime import datetime
 from unittest.mock import AsyncMock
 
 import pytest
@@ -196,3 +197,162 @@ def capture_warning(message: str) -> None:
         "ensure_frontmatter_on_sync=True overrides disable_permalinks=True" in message
         for message in warnings
     )
+
+
+@pytest.mark.asyncio
+async def test_run_migrations_triggers_embedding_backfill_on_new_revision(
+    monkeypatch, app_config: BasicMemoryConfig
+):
+    """When the trigger revision is newly applied, run automatic embedding backfill once."""
+
+    class StubSearchRepository:
+        def __init__(self, *args, **kwargs):
+            pass
+
+        async def init_search_index(self):
+            return None
+
+    original_session_maker = db._session_maker  # pyright: ignore [reportPrivateUsage]
+    try:
+        session_marker = object()
+        db._session_maker = session_marker  # pyright: ignore [reportPrivateUsage]
+
+        monkeypatch.setattr(
+            "basic_memory.db.command.upgrade",
+            lambda *args, **kwargs: None,
+        )
+        monkeypatch.setattr("basic_memory.db.SQLiteSearchRepository", StubSearchRepository)
+        monkeypatch.setattr("basic_memory.db.PostgresSearchRepository", StubSearchRepository)
+
+        load_revisions_mock = AsyncMock(
+            side_effect=[
+                set(),
+                {db.SEMANTIC_EMBEDDING_BACKFILL_REVISION},
+            ]
+        )
+        backfill_mock = AsyncMock()
+        monkeypatch.setattr("basic_memory.db._load_applied_alembic_revisions", load_revisions_mock)
+        monkeypatch.setattr("basic_memory.db._run_semantic_embedding_backfill", backfill_mock)
+
+        await db.run_migrations(app_config)
+
+        assert load_revisions_mock.await_count == 2
+        backfill_mock.assert_awaited_once_with(app_config, session_marker)
+    finally:
+        db._session_maker = original_session_maker  # pyright: ignore [reportPrivateUsage]
+
+
+@pytest.mark.asyncio
+async def test_run_migrations_skips_embedding_backfill_when_revision_already_applied(
+    monkeypatch, app_config: BasicMemoryConfig
+):
+    """If the trigger revision was already present before upgrade, skip backfill."""
+
+    class StubSearchRepository:
+        def __init__(self, *args, **kwargs):
+            pass
+
+        async def init_search_index(self):
+            return None
+
+    original_session_maker = db._session_maker  # pyright: ignore [reportPrivateUsage]
+    try:
+        session_marker = object()
+        db._session_maker = session_marker  # pyright: ignore [reportPrivateUsage]
+
+        monkeypatch.setattr(
+            "basic_memory.db.command.upgrade",
+            lambda *args, **kwargs: None,
+        )
+        monkeypatch.setattr("basic_memory.db.SQLiteSearchRepository", StubSearchRepository)
+        monkeypatch.setattr("basic_memory.db.PostgresSearchRepository", StubSearchRepository)
+
+        load_revisions_mock = AsyncMock(
+            side_effect=[
+                {db.SEMANTIC_EMBEDDING_BACKFILL_REVISION},
+                {db.SEMANTIC_EMBEDDING_BACKFILL_REVISION},
+            ]
+        )
+        backfill_mock = AsyncMock()
+        monkeypatch.setattr("basic_memory.db._load_applied_alembic_revisions", load_revisions_mock)
+        monkeypatch.setattr("basic_memory.db._run_semantic_embedding_backfill", backfill_mock)
+
+        await db.run_migrations(app_config)
+
+        assert load_revisions_mock.await_count == 2
+        assert backfill_mock.await_count == 0
+    finally:
+        db._session_maker = original_session_maker  # pyright: ignore [reportPrivateUsage]
+
+
+@pytest.mark.asyncio
+async def test_semantic_embedding_backfill_syncs_each_entity(
+    monkeypatch,
+    app_config: BasicMemoryConfig,
+    session_maker,
+    test_project,
+):
+    """Automatic backfill should run sync_entity_vectors for every entity in active projects."""
+    from basic_memory.repository.entity_repository import EntityRepository
+
+    entity_repository = EntityRepository(session_maker, project_id=test_project.id)
+    created_entity_ids: list[int] = []
+    for i in range(3):
+        entity = await entity_repository.create(
+            {
+                "title": f"Backfill Entity {i}",
+                "entity_type": "note",
+                "entity_metadata": {},
+                "content_type": "text/markdown",
+                "file_path": f"test/backfill-{i}.md",
+                "permalink": f"test/backfill-{i}",
+                "project_id": test_project.id,
+                "created_at": datetime.now(),
+                "updated_at": datetime.now(),
+            }
+        )
+        created_entity_ids.append(entity.id)
+
+    synced_pairs: list[tuple[int, int]] = []
+
+    class StubSearchRepository:
+        def __init__(self, _session_maker, project_id: int, app_config=None):
+            self.project_id = project_id
+
+        async def sync_entity_vectors(self, entity_id: int) -> None:
+            synced_pairs.append((self.project_id, entity_id))
+
+    monkeypatch.setattr("basic_memory.db.SQLiteSearchRepository", StubSearchRepository)
+    monkeypatch.setattr("basic_memory.db.PostgresSearchRepository", StubSearchRepository)
+
+    app_config.semantic_search_enabled = True
+
+    await db._run_semantic_embedding_backfill(app_config, session_maker)  # pyright: ignore [reportPrivateUsage]
+
+    expected_pairs = {(test_project.id, entity_id) for entity_id in created_entity_ids}
+    assert expected_pairs.issubset(set(synced_pairs))
+
+
+@pytest.mark.asyncio
+async def test_semantic_embedding_backfill_skips_when_semantic_disabled(
+    monkeypatch,
+    app_config: BasicMemoryConfig,
+    session_maker,
+):
+    """Automatic backfill should no-op when semantic search is disabled."""
+    called = False
+
+    class StubSearchRepository:
+        def __init__(self, *args, **kwargs):
+            nonlocal called
+            called = True
+
+        async def sync_entity_vectors(self, entity_id: int) -> None:  # pragma: no cover
+            return None
+
+    monkeypatch.setattr("basic_memory.db.SQLiteSearchRepository", StubSearchRepository)
+    monkeypatch.setattr("basic_memory.db.PostgresSearchRepository", StubSearchRepository)
+
+    app_config.semantic_search_enabled = False
+    await db._run_semantic_embedding_backfill(app_config, session_maker)  # pyright: ignore [reportPrivateUsage]
+    assert called is False
diff --git a/tests/test_config.py b/tests/test_config.py
index a8ea430bc..63961b5ef 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -603,29 +603,33 @@ def test_model_post_init_uses_platform_native_separators(self, config_home, monk
 class TestSemanticSearchConfig:
     """Test semantic search configuration options."""
 
-    def test_semantic_search_enabled_defaults_to_true_when_fastembed_is_available(
+    def test_semantic_search_enabled_defaults_to_true_when_semantic_modules_are_available(
         self, monkeypatch
     ):
-        """Semantic search defaults on when fastembed is importable."""
+        """Semantic search defaults on when fastembed and sqlite_vec are importable."""
         import basic_memory.config as config_module
 
         monkeypatch.delenv("BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED", raising=False)
         monkeypatch.setattr(
             config_module.importlib.util,
             "find_spec",
-            lambda name: object() if name == "fastembed" else None,
+            lambda name: object() if name in {"fastembed", "sqlite_vec"} else None,
         )
         config = BasicMemoryConfig()
         assert config.semantic_search_enabled is True
 
-    def test_semantic_search_enabled_defaults_to_false_when_fastembed_is_unavailable(
+    def test_semantic_search_enabled_defaults_to_false_when_any_semantic_module_is_unavailable(
         self, monkeypatch
     ):
-        """Semantic search defaults off when fastembed is not importable."""
+        """Semantic search defaults off when required semantic modules are missing."""
         import basic_memory.config as config_module
 
         monkeypatch.delenv("BASIC_MEMORY_SEMANTIC_SEARCH_ENABLED", raising=False)
-        monkeypatch.setattr(config_module.importlib.util, "find_spec", lambda name: None)
+        monkeypatch.setattr(
+            config_module.importlib.util,
+            "find_spec",
+            lambda name: object() if name == "fastembed" else None,
+        )
         config = BasicMemoryConfig()
         assert config.semantic_search_enabled is False
 
diff --git a/uv.lock b/uv.lock
index db1eef26b..44e8d1467 100644
--- a/uv.lock
+++ b/uv.lock
@@ -151,6 +151,7 @@ dependencies = [
     { name = "asyncpg" },
     { name = "dateparser" },
     { name = "fastapi", extra = ["standard"] },
+    { name = "fastembed" },
     { name = "fastmcp" },
     { name = "greenlet" },
     { name = "httpx" },
@@ -161,6 +162,7 @@ dependencies = [
     { name = "mdformat-frontmatter" },
     { name = "mdformat-gfm" },
     { name = "nest-asyncio" },
+    { name = "openai" },
     { name = "pillow" },
     { name = "psycopg" },
     { name = "pybars3" },
@@ -176,18 +178,12 @@ dependencies = [
     { name = "rich" },
     { name = "sniffio" },
     { name = "sqlalchemy" },
+    { name = "sqlite-vec" },
     { name = "typer" },
     { name = "unidecode" },
     { name = "watchfiles" },
 ]
 
-[package.optional-dependencies]
-semantic = [
-    { name = "fastembed" },
-    { name = "openai" },
-    { name = "sqlite-vec" },
-]
-
 [package.dev-dependencies]
 dev = [
     { name = "freezegun" },
@@ -214,7 +210,7 @@ requires-dist = [
     { name = "asyncpg", specifier = ">=0.30.0" },
     { name = "dateparser", specifier = ">=1.2.0" },
     { name = "fastapi", extras = ["standard"], specifier = ">=0.115.8" },
-    { name = "fastembed", marker = "extra == 'semantic'", specifier = ">=0.7.4" },
+    { name = "fastembed", specifier = ">=0.7.4" },
     { name = "fastmcp", specifier = "==2.12.3" },
     { name = "greenlet", specifier = ">=3.1.1" },
     { name = "httpx", specifier = ">=0.28.0" },
@@ -225,7 +221,7 @@ requires-dist = [
     { name = "mdformat-frontmatter", specifier = ">=2.0.8" },
     { name = "mdformat-gfm", specifier = ">=0.3.7" },
     { name = "nest-asyncio", specifier = ">=1.6.0" },
-    { name = "openai", marker = "extra == 'semantic'", specifier = ">=1.100.2" },
+    { name = "openai", specifier = ">=1.100.2" },
     { name = "pillow", specifier = ">=11.1.0" },
     { name = "psycopg", specifier = "==3.3.1" },
     { name = "pybars3", specifier = ">=0.9.7" },
@@ -241,12 +237,11 @@ requires-dist = [
     { name = "rich", specifier = ">=13.9.4" },
     { name = "sniffio", specifier = ">=1.3.1" },
     { name = "sqlalchemy", specifier = ">=2.0.0" },
-    { name = "sqlite-vec", marker = "extra == 'semantic'", specifier = ">=0.1.6" },
+    { name = "sqlite-vec", specifier = ">=0.1.6" },
     { name = "typer", specifier = ">=0.9.0" },
     { name = "unidecode", specifier = ">=1.3.8" },
     { name = "watchfiles", specifier = ">=1.0.4" },
 ]
-provides-extras = ["semantic"]
 
 [package.metadata.requires-dev]
 dev = [