Merge pull request #129 from ggozad/feat/filter-list

Add filtering to document listing in CLI/client

docs/cli.md

@@ -22,6 +22,18 @@ The `haiku-rag` CLI provides complete document management functionality.
 haiku-rag list
 ```
 
+Filter documents by properties:
+```bash
+# Filter by URI pattern
+haiku-rag list --filter "uri LIKE '%arxiv%'"
+
+# Filter by exact title
+haiku-rag list --filter "title = 'My Document'"
+
+# Combine multiple conditions
+haiku-rag list --filter "uri LIKE '%.pdf' AND title LIKE '%paper%'"
+```
+
 ### Add Documents
 
 From text:

docs/mcp.md

@@ -10,7 +10,7 @@ The MCP server exposes `haiku.rag` as MCP tools for compatible MCP clients.
 - `add_document_from_url` - Add documents from URLs
 - `add_document_from_text` - Add documents from raw text content
 - `get_document` - Retrieve specific documents by ID
-- `list_documents` - List all documents with pagination
+- `list_documents` - List all documents with pagination and optional filtering
 - `delete_document` - Delete documents by ID
 
 ### Search

docs/python.md

@@ -84,6 +84,21 @@ List all documents:
 docs = await client.list_documents(limit=10, offset=0)
 ```
 
+Filter documents by properties:
+```python
+# Filter by URI pattern
+docs = await client.list_documents(filter="uri LIKE '%arxiv%'")
+
+# Filter by exact title
+docs = await client.list_documents(filter="title = 'My Document'")
+
+# Combine multiple conditions
+docs = await client.list_documents(
+    limit=10,
+    filter="uri LIKE '%.pdf' AND title LIKE '%paper%'"
+)
+```
+
 ### Updating Documents
 
 ```python

src/haiku/rag/app.py

@@ -139,9 +139,9 @@ class HaikuRAGApp:
             f"  [repr.attrib_name]docling[/repr.attrib_name]: {docling_version}"
         )
 
-    async def list_documents(self):
+    async def list_documents(self, filter: str | None = None):
         async with HaikuRAG(db_path=self.db_path) as self.client:
-            documents = await self.client.list_documents()
+            documents = await self.client.list_documents(filter=filter)
             for doc in documents:
                 self._rich_print_document(doc, truncate=True)
 

src/haiku/rag/cli.py

@@ -92,11 +92,17 @@ def list_documents(
         "--db",
         help="Path to the LanceDB database file",
     ),
+    filter: str | None = typer.Option(
+        None,
+        "--filter",
+        "-f",
+        help="SQL WHERE clause to filter documents (e.g., \"uri LIKE '%arxiv%'\")",
+    ),
 ):
     from haiku.rag.app import HaikuRAGApp
 
     app = HaikuRAGApp(db_path=db)
-    asyncio.run(app.list_documents())
+    asyncio.run(app.list_documents(filter=filter))
 
 
 def _parse_meta_options(meta: list[str] | None) -> dict[str, Any]:

src/haiku/rag/client.py

@@ -409,18 +409,24 @@ class HaikuRAG:
         return await self.document_repository.delete(document_id)
 
     async def list_documents(
-        self, limit: int | None = None, offset: int | None = None
+        self,
+        limit: int | None = None,
+        offset: int | None = None,
+        filter: str | None = None,
     ) -> list[Document]:
-        """List all documents with optional pagination.
+        """List all documents with optional pagination and filtering.
 
         Args:
             limit: Maximum number of documents to return.
             offset: Number of documents to skip.
+            filter: Optional SQL WHERE clause to filter documents.
 
         Returns:
-            List of Document instances.
+            List of Document instances matching the criteria.
         """
-        return await self.document_repository.list_all(limit=limit, offset=offset)
+        return await self.document_repository.list_all(
+            limit=limit, offset=offset, filter=filter
+        )
 
     async def search(
         self,

src/haiku/rag/mcp.py

@@ -130,12 +130,23 @@ def create_mcp_server(db_path: Path) -> FastMCP:
 
     @mcp.tool()
     async def list_documents(
-        limit: int | None = None, offset: int | None = None
+        limit: int | None = None,
+        offset: int | None = None,
+        filter: str | None = None,
     ) -> list[DocumentResult]:
-        """List all documents with optional pagination."""
+        """List all documents with optional pagination and filtering.
+
+        Args:
+            limit: Maximum number of documents to return.
+            offset: Number of documents to skip.
+            filter: Optional SQL WHERE clause to filter documents.
+
+        Returns:
+            List of DocumentResult instances matching the criteria.
+        """
         try:
             async with HaikuRAG(db_path) as rag:
-                documents = await rag.list_documents(limit, offset)
+                documents = await rag.list_documents(limit, offset, filter)
 
                 return [
                     DocumentResult(

src/haiku/rag/store/repositories/document.py

@@ -123,11 +123,25 @@ class DocumentRepository:
         return True
 
     async def list_all(
-        self, limit: int | None = None, offset: int | None = None
+        self,
+        limit: int | None = None,
+        offset: int | None = None,
+        filter: str | None = None,
     ) -> list[Document]:
-        """List all documents with optional pagination."""
+        """List all documents with optional pagination and filtering.
+
+        Args:
+            limit: Maximum number of documents to return.
+            offset: Number of documents to skip.
+            filter: Optional SQL WHERE clause to filter documents.
+
+        Returns:
+            List of Document instances matching the criteria.
+        """
         query = self.store.documents_table.search()
 
+        if filter is not None:
+            query = query.where(filter)
         if offset is not None:
             query = query.offset(offset)
         if limit is not None:

tests/test_document.py

@@ -105,3 +105,46 @@ async def test_document_repository_crud(qa_corpus: Dataset, temp_db_path):
     assert retrieved_document is None
 
     store.close()
+
+
+@pytest.mark.asyncio
+async def test_document_list_with_filter(qa_corpus: Dataset, temp_db_path):
+    """Test listing documents with filter clause."""
+    store = Store(temp_db_path)
+    doc_repo = DocumentRepository(store)
+
+    first_doc = qa_corpus[0]
+    document_text = first_doc["document_extracted"]
+
+    doc1 = Document(
+        content=document_text,
+        uri="https://example.com/doc1.txt",
+        metadata={"source": "test", "category": "A"},
+    )
+    doc2 = Document(
+        content=document_text,
+        uri="https://arxiv.org/paper.pdf",
+        metadata={"source": "test", "category": "B"},
+    )
+    doc3 = Document(
+        content=document_text,
+        uri="https://example.com/doc3.txt",
+        metadata={"source": "test", "category": "A"},
+    )
+
+    created_doc1 = await doc_repo.create(doc1)
+    created_doc2 = await doc_repo.create(doc2)
+    created_doc3 = await doc_repo.create(doc3)
+
+    all_documents = await doc_repo.list_all()
+    assert len(all_documents) == 3
+
+    arxiv_documents = await doc_repo.list_all(filter="uri LIKE '%arxiv%'")
+    assert len(arxiv_documents) == 1
+    assert arxiv_documents[0].id == created_doc2.id
+
+    example_documents = await doc_repo.list_all(filter="uri LIKE '%example.com%'")
+    assert len(example_documents) == 2
+    assert {doc.id for doc in example_documents} == {created_doc1.id, created_doc3.id}
+
+    store.close()

tests/test_mcp.py

@@ -215,7 +215,7 @@ async def test_mcp_list_documents():
             assert len(result) == 2
             assert result[0].id == "doc1"
             assert result[1].id == "doc2"
-            mock_rag.list_documents.assert_called_once_with(10, 0)
+            mock_rag.list_documents.assert_called_once_with(10, 0, None)
 
 
 @pytest.mark.asyncio