Show index stats in cli info command

CHANGELOG.md

@@ -10,6 +10,10 @@
   - New `search.vector_refine_factor` config option (default: 10) for accuracy/speed tradeoff
   - Indexes not created automatically during ingestion to avoid performance degradation
   - Manual rebuilding required after adding significant new data
+- **Enhanced Info Command**: `haiku-rag info` now shows storage sizes and vector index statistics
+  - Displays storage size for documents and chunks tables in human-readable format
+  - Shows vector index status (exists/not created)
+  - Shows indexed and unindexed chunk counts for monitoring index staleness
 
 ### Changed
 

haiku_rag_slim/haiku/rag/app.py

@@ -18,6 +18,7 @@ from haiku.rag.mcp import create_mcp_server
 from haiku.rag.monitor import FileWatcher
 from haiku.rag.store.models.chunk import Chunk
 from haiku.rag.store.models.document import Document
+from haiku.rag.utils import format_bytes
 
 logger = logging.getLogger(__name__)
 
@@ -83,10 +84,22 @@ class HaikuRAGApp:
                 embed_model = embeddings.get("model")
                 vector_dim = embeddings.get("vector_dim")
 
-        num_docs = 0
-        if "documents" in table_names:
-            docs_tbl = db.open_table("documents")
-            num_docs = int(docs_tbl.count_rows())  # type: ignore[attr-defined]
+        # Get comprehensive table statistics
+        from haiku.rag.store.engine import Store
+
+        store = Store(self.db_path, config=self.config)
+        table_stats = store.get_stats()
+        store.close()
+
+        num_docs = table_stats["documents"].get("num_rows", 0)
+        doc_bytes = table_stats["documents"].get("total_bytes", 0)
+
+        num_chunks = table_stats["chunks"].get("num_rows", 0)
+        chunk_bytes = table_stats["chunks"].get("total_bytes", 0)
+
+        has_vector_index = table_stats["chunks"].get("has_vector_index", False)
+        num_indexed_rows = table_stats["chunks"].get("num_indexed_rows", 0)
+        num_unindexed_rows = table_stats["chunks"].get("num_unindexed_rows", 0)
 
         # Table versions per table (direct API)
         doc_versions = (
@@ -116,8 +129,43 @@ class HaikuRAGApp:
                 "  [repr.attrib_name]embeddings[/repr.attrib_name]: unknown"
             )
         self.console.print(
-            f"  [repr.attrib_name]documents[/repr.attrib_name]: {num_docs}"
+            f"  [repr.attrib_name]documents[/repr.attrib_name]: {num_docs} "
+            f"({format_bytes(doc_bytes)})"
         )
+        self.console.print(
+            f"  [repr.attrib_name]chunks[/repr.attrib_name]: {num_chunks} "
+            f"({format_bytes(chunk_bytes)})"
+        )
+
+        # Vector index information
+        if has_vector_index:
+            self.console.print(
+                "  [repr.attrib_name]vector index[/repr.attrib_name]: ✓ exists"
+            )
+            self.console.print(
+                f"  [repr.attrib_name]indexed chunks[/repr.attrib_name]: {num_indexed_rows}"
+            )
+            if num_unindexed_rows > 0:
+                self.console.print(
+                    f"  [repr.attrib_name]unindexed chunks[/repr.attrib_name]: [yellow]{num_unindexed_rows}[/yellow] "
+                    "(consider running: haiku-rag create-index)"
+                )
+            else:
+                self.console.print(
+                    f"  [repr.attrib_name]unindexed chunks[/repr.attrib_name]: {num_unindexed_rows}"
+                )
+        else:
+            if num_chunks >= 256:
+                self.console.print(
+                    "  [repr.attrib_name]vector index[/repr.attrib_name]: [yellow]✗ not created[/yellow] "
+                    "(run: haiku-rag create-index)"
+                )
+            else:
+                self.console.print(
+                    f"  [repr.attrib_name]vector index[/repr.attrib_name]: ✗ not created "
+                    f"(need {256 - num_chunks} more chunks)"
+                )
+
         self.console.print(
             f"  [repr.attrib_name]versions (documents)[/repr.attrib_name]: {doc_versions}"
         )

haiku_rag_slim/haiku/rag/store/engine.py

@@ -145,6 +145,51 @@ class Store:
             and self._config.lancedb.region
         )
 
+    def get_stats(self) -> dict:
+        """Get comprehensive table statistics.
+
+        Returns:
+            Dictionary with statistics for documents and chunks tables including:
+            - Row counts
+            - Storage sizes
+            - Vector index status and statistics
+        """
+        stats_dict: dict = {
+            "documents": {"exists": False},
+            "chunks": {"exists": False},
+        }
+
+        # Documents table stats
+        doc_stats: dict = self.documents_table.stats()  # type: ignore[assignment]
+        stats_dict["documents"] = {
+            "exists": True,
+            "num_rows": doc_stats.get("num_rows", 0),
+            "total_bytes": doc_stats.get("total_bytes", 0),
+        }
+
+        # Chunks table stats
+        chunk_stats: dict = self.chunks_table.stats()  # type: ignore[assignment]
+        stats_dict["chunks"] = {
+            "exists": True,
+            "num_rows": chunk_stats.get("num_rows", 0),
+            "total_bytes": chunk_stats.get("total_bytes", 0),
+        }
+
+        # Vector index stats
+        indices = self.chunks_table.list_indices()
+        has_vector_index = any("vector" in str(idx).lower() for idx in indices)
+        stats_dict["chunks"]["has_vector_index"] = has_vector_index
+
+        if has_vector_index:
+            index_stats = self.chunks_table.index_stats("vector_idx")
+            if index_stats is not None:
+                stats_dict["chunks"]["num_indexed_rows"] = index_stats.num_indexed_rows
+                stats_dict["chunks"]["num_unindexed_rows"] = (
+                    index_stats.num_unindexed_rows
+                )
+
+        return stats_dict
+
     def _ensure_vector_index(self) -> None:
         """Create or rebuild vector index on chunks table.
 

haiku_rag_slim/haiku/rag/utils.py

@@ -8,6 +8,16 @@ from types import ModuleType
 from packaging.version import Version, parse
 
 
+def format_bytes(num_bytes: int) -> str:
+    """Format bytes as human-readable string."""
+    size = float(num_bytes)
+    for unit in ["B", "KB", "MB", "GB", "TB"]:
+        if size < 1024.0:
+            return f"{size:.1f} {unit}"
+        size /= 1024.0
+    return f"{size:.1f} PB"
+
+
 def get_default_data_dir() -> Path:
     """Get the user data directory for the current system platform.