Merge pull request #374 from tseaver/feat-cli-search_type

feat: add '--search-type' option to CLI 'search'

docs/cli.md

@@ -133,6 +133,18 @@ With options:
 haiku-rag search "python programming" --limit 10  # or -l 10
 ```
 
+With search type:
+```bash
+# Hybrid search (the default)
+haiku-rag search "python programming" --search-type hybrid  # or -s hybrid
+
+# Full-text search only
+haiku-rag search "python programming" --search-type fts  # or -s fts
+
+# Vector search only
+haiku-rag search "python programming" --search-type vector  # or -s vector
+```
+
 With filters (filter by document properties, use `--filter` or `-f`):
 ```bash
 # Filter by URI pattern

haiku_rag_slim/haiku/rag/app.py

@@ -22,6 +22,7 @@ from haiku.rag.client import HaikuRAG, RebuildMode
 from haiku.rag.config import AppConfig, Config
 from haiku.rag.mcp import create_mcp_server
 from haiku.rag.monitor import FileWatcher, S3Watcher
+from haiku.rag.store.models.chunk import SearchType
 from haiku.rag.store.models.document import Document
 
 if TYPE_CHECKING:
@@ -361,6 +362,7 @@ class HaikuRAGApp:  # pragma: no cover
         query: str | None = None,
         limit: int | None = None,
         filter: str | None = None,
+        search_type: SearchType | None = None,
         image: Path | None = None,
     ):
         if query is None and image is None:
@@ -372,6 +374,10 @@ class HaikuRAGApp:  # pragma: no cover
             self.console.print("[red]Pass either a query or --image, not both.[/red]")
             return
 
+        if query is None and search_type is not None:
+            self.console.print("[red]Pass --search-type only for text queries[/red]")
+            return
+
         search_input: str | bytes
         if image is not None:
             search_input = image.read_bytes()
@@ -385,7 +391,12 @@ class HaikuRAGApp:  # pragma: no cover
             read_only=self.read_only,
             before=self.before,
         ) as self.client:
-            results = await self.client.search(search_input, limit=limit, filter=filter)
+            results = await self.client.search(
+                search_input,
+                limit=limit,
+                filter=filter,
+                search_type=search_type,
+            )
             if not results:
                 self.console.print("[yellow]No results found.[/yellow]")
                 return

haiku_rag_slim/haiku/rag/cli.py

@@ -27,6 +27,7 @@ from haiku.rag.store.exceptions import (  # noqa: E402
     MigrationRequiredError,
     ReadOnlyError,
 )
+from haiku.rag.store.models.chunk import SearchType  # noqa: E402
 from haiku.rag.utils import is_up_to_date  # noqa: E402
 
 _cli = typer.Typer(
@@ -314,6 +315,12 @@ def search(  # pragma: no cover
         "-f",
         help="SQL WHERE clause to filter documents (e.g., \"uri LIKE '%arxiv%'\")",
     ),
+    search_type: SearchType | None = typer.Option(
+        None,
+        "--search-type",
+        "-s",
+        help="Type of search to perform (text searches only)",
+    ),
     image: Path | None = typer.Option(
         None,
         "--image",
@@ -326,7 +333,15 @@ def search(  # pragma: no cover
     ),
 ):
     app = create_app(db)
-    asyncio.run(app.search(query=query, limit=limit, filter=filter, image=image))
+    asyncio.run(
+        app.search(
+            query=query,
+            limit=limit,
+            filter=filter,
+            search_type=search_type,
+            image=image,
+        )
+    )
 
 
 @_cli.command("visualize", help="Show visual grounding for a chunk")

haiku_rag_slim/haiku/rag/client/__init__.py

@@ -17,7 +17,7 @@ from haiku.rag.config import AppConfig, Config
 from haiku.rag.converters import get_converter
 from haiku.rag.reranking import get_reranker
 from haiku.rag.store.engine import Store
-from haiku.rag.store.models.chunk import Chunk, SearchResult
+from haiku.rag.store.models.chunk import Chunk, SearchResult, SearchType
 from haiku.rag.store.models.document import Document
 from haiku.rag.store.models.document_item import extract_items
 from haiku.rag.store.repositories.chunk import ChunkRepository
@@ -349,7 +349,7 @@ class HaikuRAG:
         self,
         query: "str | bytes | PILImage.Image",
         limit: int | None = None,
-        search_type: str = "hybrid",
+        search_type: SearchType | None = None,
         filter: str | None = None,
         include_images: bool = True,
     ) -> list[SearchResult]:

haiku_rag_slim/haiku/rag/client/search.py

@@ -2,7 +2,7 @@ import base64
 from typing import TYPE_CHECKING
 
 from haiku.rag.reranking import get_reranker
-from haiku.rag.store.models.chunk import Chunk, SearchResult
+from haiku.rag.store.models.chunk import Chunk, SearchResult, SearchType
 
 if TYPE_CHECKING:
     from PIL import Image as PILImage
@@ -14,7 +14,7 @@ async def search(
     client: "HaikuRAG",
     query: "str | bytes | PILImage.Image",
     limit: int | None = None,
-    search_type: str = "hybrid",
+    search_type: SearchType | None = None,
     filter: str | None = None,
     include_images: bool = True,
 ) -> list[SearchResult]:
@@ -25,7 +25,8 @@ async def search(
         query: Text (``str``) or image (``bytes`` / ``PIL.Image.Image``).
             Image queries require a multimodal embedder and run vector-only.
         limit: Maximum number of results to return. Defaults to config.search.limit.
-        search_type: "vector", "fts", or "hybrid" (default). Text queries only.
+        search_type: "vector", "fts", or "hybrid".
+            Applicable only for text queries, where the default is "hybrid".
         filter: Optional SQL WHERE clause to filter documents before searching chunks.
         include_images: When True, populate ``SearchResult.image_data`` with
             base64 picture bytes for picture-labeled chunks.
@@ -37,6 +38,9 @@ async def search(
         limit = client._config.search.limit
 
     if isinstance(query, str):
+        if search_type is None:
+            search_type = "hybrid"
+
         reranker = get_reranker(config=client._config)
 
         if reranker is None:

haiku_rag_slim/haiku/rag/store/models/chunk.py

@@ -1,4 +1,4 @@
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Literal
 
 from pydantic import BaseModel, PrivateAttr
 
@@ -113,6 +113,9 @@ class Chunk(BaseModel):
         return ChunkMetadata.model_validate(self.metadata)
 
 
+SearchType = Literal["vector", "fts", "hybrid"]
+
+
 class SearchResult(BaseModel):
     """Search result with optional provenance information for citations.
 

haiku_rag_slim/haiku/rag/store/repositories/chunk.py

@@ -11,7 +11,7 @@ from lancedb.index import FTS
 from lancedb.rerankers import RRFReranker
 
 from haiku.rag.store.engine import Store, query_to_pydantic
-from haiku.rag.store.models.chunk import Chunk
+from haiku.rag.store.models.chunk import Chunk, SearchType
 
 logger = logging.getLogger(__name__)
 
@@ -220,7 +220,7 @@ class ChunkRepository:
         self,
         query: str = "",
         limit: int = 5,
-        search_type: str = "hybrid",
+        search_type: SearchType = "hybrid",
         filter: str | None = None,
         query_vector: list[float] | None = None,
     ) -> list[tuple[Chunk, float]]: