Merge pull request #15 from ggozad/feat/settings

Store settings to db & check for incompatibilities.
This commit is contained in:
Yiorgis Gozadinos 2025-07-16 18:46:07 +03:00 committed by GitHub
commit 96945e2c98
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 614 additions and 423 deletions

View file

@ -2,6 +2,9 @@
Configuration is done through the use of environment variables. Configuration is done through the use of environment variables.
!!! note
If you create a db with certain settings and later change them, `haiku.rag` will detect incompatibilities (for example, if you change embedding provider) and will exit. You can **rebuild** the database to apply the new settings, see [Rebuild Database](./cli.md#rebuild-database).
## File Monitoring ## File Monitoring
Set directories to monitor for automatic indexing: Set directories to monitor for automatic indexing:

View file

@ -56,7 +56,7 @@ dev = [
"mkdocs>=1.6.1", "mkdocs>=1.6.1",
"mkdocs-material>=9.6.14", "mkdocs-material>=9.6.14",
"pre-commit>=4.2.0", "pre-commit>=4.2.0",
"pyright>=1.1.402", "pyright>=1.1.403",
"pytest>=8.4.0", "pytest>=8.4.0",
"pytest-asyncio>=1.0.0", "pytest-asyncio>=1.0.0",
"pytest-cov>=6.2.1", "pytest-cov>=6.2.1",

View file

@ -74,7 +74,7 @@ class HaikuRAGApp:
self.console.print(f"[red]Error: {e}[/red]") self.console.print(f"[red]Error: {e}[/red]")
async def rebuild(self): async def rebuild(self):
async with HaikuRAG(db_path=self.db_path) as client: async with HaikuRAG(db_path=self.db_path, skip_validation=True) as client:
try: try:
documents = await client.list_documents() documents = await client.list_documents()
total_docs = len(documents) total_docs = len(documents)

View file

@ -5,7 +5,7 @@ import typer
from rich.console import Console from rich.console import Console
from haiku.rag.app import HaikuRAGApp from haiku.rag.app import HaikuRAGApp
from haiku.rag.utils import get_default_data_dir from haiku.rag.utils import get_default_data_dir, is_up_to_date
cli = typer.Typer( cli = typer.Typer(
context_settings={"help_option_names": ["-h", "--help"]}, no_args_is_help=True context_settings={"help_option_names": ["-h", "--help"]}, no_args_is_help=True
@ -15,6 +15,23 @@ console = Console()
event_loop = asyncio.get_event_loop() event_loop = asyncio.get_event_loop()
async def check_version():
"""Check if haiku.rag is up to date and show warning if not."""
up_to_date, current_version, latest_version = await is_up_to_date()
if not up_to_date:
console.print(
f"[yellow]Warning: haiku.rag is outdated. Current: {current_version}, Latest: {latest_version}[/yellow]"
)
console.print("[yellow]Please update.[/yellow]")
@cli.callback()
def main():
"""haiku.rag CLI - SQLite-based RAG system"""
# Run version check before any command
event_loop.run_until_complete(check_version())
@cli.command("list", help="List all stored documents") @cli.command("list", help="List all stored documents")
def list_documents( def list_documents(
db: Path = typer.Option( db: Path = typer.Option(

View file

@ -24,12 +24,13 @@ class HaikuRAG:
self, self,
db_path: Path | Literal[":memory:"] = Config.DEFAULT_DATA_DIR db_path: Path | Literal[":memory:"] = Config.DEFAULT_DATA_DIR
/ "haiku.rag.sqlite", / "haiku.rag.sqlite",
skip_validation: bool = False,
): ):
"""Initialize the RAG client with a database path.""" """Initialize the RAG client with a database path."""
if isinstance(db_path, Path): if isinstance(db_path, Path):
if not db_path.parent.exists(): if not db_path.parent.exists():
Path.mkdir(db_path.parent, parents=True) Path.mkdir(db_path.parent, parents=True)
self.store = Store(db_path) self.store = Store(db_path, skip_validation=skip_validation)
self.document_repository = DocumentRepository(self.store) self.document_repository = DocumentRepository(self.store)
self.chunk_repository = ChunkRepository(self.store) self.chunk_repository = ChunkRepository(self.store)
@ -165,29 +166,26 @@ class HaikuRAG:
# Create a temporary file with the appropriate extension # Create a temporary file with the appropriate extension
with tempfile.NamedTemporaryFile( with tempfile.NamedTemporaryFile(
mode="wb", suffix=file_extension, delete=False mode="wb", suffix=file_extension
) as temp_file: ) as temp_file:
temp_file.write(response.content) temp_file.write(response.content)
temp_file.flush() # Ensure content is written to disk
temp_path = Path(temp_file.name) temp_path = Path(temp_file.name)
try:
# Parse the content using FileReader # Parse the content using FileReader
content = FileReader.parse_file(temp_path) content = FileReader.parse_file(temp_path)
# Merge metadata with contentType and md5 # Merge metadata with contentType and md5
metadata.update({"contentType": content_type, "md5": md5_hash}) metadata.update({"contentType": content_type, "md5": md5_hash})
if existing_doc: if existing_doc:
existing_doc.content = content existing_doc.content = content
existing_doc.metadata = metadata existing_doc.metadata = metadata
return await self.update_document(existing_doc) return await self.update_document(existing_doc)
else: else:
return await self.create_document( return await self.create_document(
content=content, uri=url, metadata=metadata content=content, uri=url, metadata=metadata
) )
finally:
# Clean up temporary file
temp_path.unlink(missing_ok=True)
def _get_extension_from_content_type_or_url( def _get_extension_from_content_type_or_url(
self, url: str, content_type: str self, url: str, content_type: str
@ -277,12 +275,16 @@ class HaikuRAG:
Yields: Yields:
int: The ID of the document currently being processed int: The ID of the document currently being processed
""" """
documents = await self.list_documents()
if not documents:
return
await self.chunk_repository.delete_all() await self.chunk_repository.delete_all()
self.store.recreate_embeddings_table()
# Update settings to current config
from haiku.rag.store.repositories.settings import SettingsRepository
settings_repo = SettingsRepository(self.store)
settings_repo.save()
documents = await self.list_documents()
for doc in documents: for doc in documents:
if doc.id is not None: if doc.id is not None:

View file

@ -9,10 +9,19 @@ from haiku.rag.embeddings import get_embedder
class Store: class Store:
def __init__(self, db_path: Path | Literal[":memory:"]): def __init__(
self, db_path: Path | Literal[":memory:"], skip_validation: bool = False
):
self.db_path: Path | Literal[":memory:"] = db_path self.db_path: Path | Literal[":memory:"] = db_path
self._connection = self.create_db() self._connection = self.create_db()
# Validate config compatibility after connection is established
if not skip_validation:
from haiku.rag.store.repositories.settings import SettingsRepository
settings_repo = SettingsRepository(self)
settings_repo.validate_config_compatibility()
def create_db(self) -> sqlite3.Connection: def create_db(self) -> sqlite3.Connection:
"""Create the database and tables with sqlite-vec support for embeddings.""" """Create the database and tables with sqlite-vec support for embeddings."""
db = sqlite3.connect(self.db_path) db = sqlite3.connect(self.db_path)
@ -60,14 +69,50 @@ class Store:
) )
""") """)
# Create settings table for storing current configuration
db.execute("""
CREATE TABLE IF NOT EXISTS settings (
id INTEGER PRIMARY KEY DEFAULT 1,
settings TEXT NOT NULL DEFAULT '{}'
)
""")
# Create indexes for better performance # Create indexes for better performance
db.execute( db.execute(
"CREATE INDEX IF NOT EXISTS idx_chunks_document_id ON chunks(document_id)" "CREATE INDEX IF NOT EXISTS idx_chunks_document_id ON chunks(document_id)"
) )
# Save current settings to the new database
from haiku.rag.config import Config
settings_json = Config.model_dump_json()
db.execute(
"INSERT OR IGNORE INTO settings (id, settings) VALUES (1, ?)",
(settings_json,),
)
db.commit() db.commit()
return db return db
def recreate_embeddings_table(self) -> None:
"""Recreate the embeddings table with current vector dimensions."""
if self._connection is None:
raise ValueError("Store connection is not available")
# Drop existing embeddings table
self._connection.execute("DROP TABLE IF EXISTS chunk_embeddings")
# Recreate with current dimensions
embedder = get_embedder()
self._connection.execute(f"""
CREATE VIRTUAL TABLE chunk_embeddings USING vec0(
chunk_id INTEGER PRIMARY KEY,
embedding FLOAT[{embedder._vector_dim}]
)
""")
self._connection.commit()
@staticmethod @staticmethod
def serialize_embedding(embedding: list[float]) -> bytes: def serialize_embedding(embedding: list[float]) -> bytes:
"""Serialize a list of floats to bytes for sqlite-vec storage.""" """Serialize a list of floats to bytes for sqlite-vec storage."""

View file

@ -0,0 +1,78 @@
import json
from typing import Any
from haiku.rag.store.engine import Store
class ConfigMismatchError(Exception):
"""Raised when current config doesn't match stored settings."""
pass
class SettingsRepository:
def __init__(self, store: Store):
self.store = store
def get(self) -> dict[str, Any]:
"""Get all settings from the database."""
if self.store._connection is None:
raise ValueError("Store connection is not available")
cursor = self.store._connection.execute("SELECT settings FROM settings LIMIT 1")
row = cursor.fetchone()
if row:
return json.loads(row[0])
return {}
def save(self) -> None:
"""Sync settings from the current AppConfig to database."""
if self.store._connection is None:
raise ValueError("Store connection is not available")
from haiku.rag.config import Config
settings_json = Config.model_dump_json()
self.store._connection.execute(
"INSERT INTO settings (id, settings) VALUES (1, ?) ON CONFLICT(id) DO UPDATE SET settings = excluded.settings",
(settings_json,),
)
self.store._connection.commit()
def validate_config_compatibility(self) -> None:
"""Check if current config is compatible with stored settings.
Raises ConfigMismatchError if there are incompatible differences.
If no settings exist, saves current config.
"""
db_settings = self.get()
if not db_settings:
# No settings in DB, save current config
self.save()
return
from haiku.rag.config import Config
current_config = Config.model_dump(mode="json")
# Critical settings that must match
critical_settings = [
"EMBEDDINGS_PROVIDER",
"EMBEDDINGS_MODEL",
"EMBEDDINGS_VECTOR_DIM",
"CHUNK_SIZE",
"CHUNK_OVERLAP",
]
errors = []
for setting in critical_settings:
if db_settings.get(setting) != current_config.get(setting):
errors.append(
f"{setting}: current={current_config.get(setting)}, stored={db_settings.get(setting)}"
)
if errors:
error_msg = f"Config mismatch detected: {'; '.join(errors)}. Consider rebuilding the database with the current configuration."
raise ConfigMismatchError(error_msg)

View file

@ -1,6 +1,10 @@
import sys import sys
from importlib import metadata
from pathlib import Path from pathlib import Path
import httpx
from packaging.version import Version, parse
def get_default_data_dir() -> Path: def get_default_data_dir() -> Path:
""" """
@ -23,3 +27,23 @@ def get_default_data_dir() -> Path:
data_path = system_paths[sys.platform] data_path = system_paths[sys.platform]
return data_path return data_path
async def is_up_to_date() -> tuple[bool, Version, Version]:
"""
Checks whether haiku.rag is current.
:return: A tuple containing a boolean indicating whether haiku.rag is current, the running version and the latest version
:rtype: tuple[bool, Version, Version]
"""
async with httpx.AsyncClient() as client:
running_version = parse(metadata.version("haiku.rag"))
try:
response = await client.get("https://pypi.org/pypi/haiku.rag/json")
data = response.json()
pypi_version = parse(data["info"]["version"])
except Exception:
# If no network connection, do not raise alarms.
pypi_version = running_version
return running_version >= pypi_version, running_version, pypi_version

View file

@ -12,300 +12,270 @@ from haiku.rag.client import HaikuRAG
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_document_crud(qa_corpus: Dataset): async def test_client_document_crud(qa_corpus: Dataset):
"""Test HaikuRAG CRUD operations for documents.""" """Test HaikuRAG CRUD operations for documents."""
# Create client with in-memory database async with HaikuRAG(":memory:") as client:
client = HaikuRAG(":memory:") # Get test data
first_doc = qa_corpus[0]
document_text = first_doc["document_extracted"]
test_uri = "file:///path/to/test.txt"
test_metadata = {"source": "test", "topic": "testing"}
# Get test data # Test create_document
first_doc = qa_corpus[0] created_doc = await client.create_document(
document_text = first_doc["document_extracted"] content=document_text, uri=test_uri, metadata=test_metadata
test_uri = "file:///path/to/test.txt" )
test_metadata = {"source": "test", "topic": "testing"}
# Test create_document assert created_doc.id is not None
created_doc = await client.create_document( assert created_doc.content == document_text
content=document_text, uri=test_uri, metadata=test_metadata assert created_doc.uri == test_uri
) assert created_doc.metadata == test_metadata
assert created_doc.id is not None # Test get_document_by_id
assert created_doc.content == document_text retrieved_doc = await client.get_document_by_id(created_doc.id)
assert created_doc.uri == test_uri assert retrieved_doc is not None
assert created_doc.metadata == test_metadata assert retrieved_doc.id == created_doc.id
assert retrieved_doc.content == document_text
assert retrieved_doc.uri == test_uri
# Test get_document_by_id # Test get_document_by_uri
retrieved_doc = await client.get_document_by_id(created_doc.id) retrieved_by_uri = await client.get_document_by_uri(test_uri)
assert retrieved_doc is not None assert retrieved_by_uri is not None
assert retrieved_doc.id == created_doc.id assert retrieved_by_uri.id == created_doc.id
assert retrieved_doc.content == document_text assert retrieved_by_uri.content == document_text
assert retrieved_doc.uri == test_uri
# Test get_document_by_uri # Test get_document_by_uri with non-existent URI
retrieved_by_uri = await client.get_document_by_uri(test_uri) non_existent = await client.get_document_by_uri("file:///non/existent.txt")
assert retrieved_by_uri is not None assert non_existent is None
assert retrieved_by_uri.id == created_doc.id
assert retrieved_by_uri.content == document_text
# Test get_document_by_uri with non-existent URI # Test update_document
non_existent = await client.get_document_by_uri("file:///non/existent.txt") retrieved_doc.content = "Updated content"
assert non_existent is None retrieved_doc.uri = "file:///updated/path.txt"
updated_doc = await client.update_document(retrieved_doc)
assert updated_doc.content == "Updated content"
assert updated_doc.uri == "file:///updated/path.txt"
# Test update_document # Test list_documents
retrieved_doc.content = "Updated content" all_docs = await client.list_documents()
retrieved_doc.uri = "file:///updated/path.txt" assert len(all_docs) == 1
updated_doc = await client.update_document(retrieved_doc) assert all_docs[0].id == created_doc.id
assert updated_doc.content == "Updated content"
assert updated_doc.uri == "file:///updated/path.txt"
# Test list_documents # Test list_documents with pagination
all_docs = await client.list_documents() limited_docs = await client.list_documents(limit=10, offset=0)
assert len(all_docs) == 1 assert len(limited_docs) == 1
assert all_docs[0].id == created_doc.id
# Test list_documents with pagination # Test delete_document
limited_docs = await client.list_documents(limit=10, offset=0) deleted = await client.delete_document(created_doc.id)
assert len(limited_docs) == 1 assert deleted is True
# Test delete_document # Verify document is gone
deleted = await client.delete_document(created_doc.id) retrieved_doc = await client.get_document_by_id(created_doc.id)
assert deleted is True assert retrieved_doc is None
# Verify document is gone # Test delete non-existent document
retrieved_doc = await client.get_document_by_id(created_doc.id) deleted_again = await client.delete_document(created_doc.id)
assert retrieved_doc is None assert deleted_again is False
# Test delete non-existent document
deleted_again = await client.delete_document(created_doc.id)
assert deleted_again is False
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_source(): async def test_client_create_document_from_source():
"""Test creating a document from a file source.""" """Test creating a document from a file source."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
with tempfile.TemporaryDirectory() as temp_dir:
test_content = "This is test content from a file."
temp_path = Path(temp_dir) / "test.txt"
temp_path.write_text(test_content)
# Create a temporary text file # Test create_document_from_source with Path
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f: doc = await client.create_document_from_source(source=temp_path)
test_content = "This is test content from a file."
f.write(test_content)
temp_path = Path(f.name)
try: assert doc.id is not None
# Test create_document_from_source with Path assert doc.content == test_content
doc = await client.create_document_from_source( assert doc.uri == temp_path.as_uri()
source=temp_path, metadata={"source_type": "file"} assert "contentType" in doc.metadata
) assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "text/plain"
assert doc.id is not None # Test create_document_from_source with string path
assert doc.content == test_content doc2 = await client.create_document_from_source(source=str(temp_path))
assert doc.uri == temp_path.as_uri()
assert doc.metadata["source_type"] == "file"
assert "contentType" in doc.metadata
assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "text/plain"
# Test create_document_from_source with string path assert doc2.id is not None
doc2 = await client.create_document_from_source(source=str(temp_path)) assert doc2.content == test_content
assert doc2.uri == temp_path.as_uri()
assert doc2.id is not None assert "contentType" in doc2.metadata
assert doc2.content == test_content assert "md5" in doc2.metadata
assert doc2.uri == temp_path.as_uri()
assert "contentType" in doc2.metadata
assert "md5" in doc2.metadata
finally:
# Clean up
temp_path.unlink()
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_source_unsupported(): async def test_client_create_document_from_source_unsupported():
"""Test creating a document from an unsupported file type.""" """Test creating a document from an unsupported file type."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Create a temporary file with unsupported extension
with tempfile.NamedTemporaryFile(
mode="w", suffix=".unsupported", delete=False
) as f:
f.write("content")
temp_path = Path(f.name)
# Create a temporary file with unsupported extension # Should raise ValueError for unsupported extension
with tempfile.NamedTemporaryFile( with pytest.raises(ValueError, match="Unsupported file extension"):
mode="w", suffix=".unsupported", delete=False await client.create_document_from_source(temp_path)
) as f:
f.write("content")
temp_path = Path(f.name)
try:
# Should raise ValueError for unsupported extension
with pytest.raises(ValueError, match="Unsupported file extension"):
await client.create_document_from_source(temp_path)
finally:
temp_path.unlink()
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_source_nonexistent(): async def test_client_create_document_from_source_nonexistent():
"""Test creating a document from a non-existent file.""" """Test creating a document from a non-existent file."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
non_existent_path = Path("/non/existent/file.txt")
non_existent_path = Path("/non/existent/file.txt") # Should raise ValueError when file doesn't exist
with pytest.raises(ValueError, match="File does not exist"):
# Should raise ValueError when file doesn't exist await client.create_document_from_source(non_existent_path)
with pytest.raises(ValueError, match="File does not exist"):
await client.create_document_from_source(non_existent_path)
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_url(): async def test_client_create_document_from_url():
"""Test creating a document from a URL.""" """Test creating a document from a URL."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Mock the HTTP response
mock_response = AsyncMock()
mock_response.content = b"<html><body><h1>Test Page</h1><p>This is test content from a webpage.</p></body></html>"
mock_response.headers = {"content-type": "text/html"}
mock_response.raise_for_status = AsyncMock()
# Mock the HTTP response with patch("httpx.AsyncClient.get", return_value=mock_response):
mock_response = AsyncMock() doc = await client.create_document_from_source(
mock_response.content = b"<html><body><h1>Test Page</h1><p>This is test content from a webpage.</p></body></html>" source="https://example.com/test.html", metadata={"source_type": "web"}
mock_response.headers = {"content-type": "text/html"} )
mock_response.raise_for_status = AsyncMock()
with patch("httpx.AsyncClient.get", return_value=mock_response): assert doc.id is not None
doc = await client.create_document_from_source( assert "Test Page" in doc.content
source="https://example.com/test.html", metadata={"source_type": "web"} assert "test content" in doc.content
) assert doc.uri == "https://example.com/test.html"
assert doc.metadata["source_type"] == "web"
assert doc.id is not None assert "contentType" in doc.metadata
assert "Test Page" in doc.content assert "md5" in doc.metadata
assert "test content" in doc.content assert doc.metadata["contentType"] == "text/html"
assert doc.uri == "https://example.com/test.html"
assert doc.metadata["source_type"] == "web"
assert "contentType" in doc.metadata
assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "text/html"
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_url_with_different_content_types(): async def test_client_create_document_from_url_with_different_content_types():
"""Test creating documents from URLs with different content types.""" """Test creating documents from URLs with different content types."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Test JSON content
# Test JSON content mock_json_response = AsyncMock()
mock_json_response = AsyncMock() mock_json_response.content = (
mock_json_response.content = ( b'{"title": "Test JSON", "content": "This is JSON content"}'
b'{"title": "Test JSON", "content": "This is JSON content"}'
)
mock_json_response.headers = {"content-type": "application/json"}
mock_json_response.raise_for_status = AsyncMock()
with patch("httpx.AsyncClient.get", return_value=mock_json_response):
doc = await client.create_document_from_source(
"https://api.example.com/data.json"
) )
mock_json_response.headers = {"content-type": "application/json"}
mock_json_response.raise_for_status = AsyncMock()
assert doc.id is not None with patch("httpx.AsyncClient.get", return_value=mock_json_response):
assert "Test JSON" in doc.content doc = await client.create_document_from_source(
assert doc.uri == "https://api.example.com/data.json" "https://api.example.com/data.json"
assert "contentType" in doc.metadata )
assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "application/json"
# Test plain text content assert doc.id is not None
mock_text_response = AsyncMock() assert "Test JSON" in doc.content
mock_text_response.content = b"This is plain text content from a URL." assert doc.uri == "https://api.example.com/data.json"
mock_text_response.headers = {"content-type": "text/plain"} assert "contentType" in doc.metadata
mock_text_response.raise_for_status = AsyncMock() assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "application/json"
with patch("httpx.AsyncClient.get", return_value=mock_text_response): # Test plain text content
doc = await client.create_document_from_source("https://example.com/readme.txt") mock_text_response = AsyncMock()
mock_text_response.content = b"This is plain text content from a URL."
mock_text_response.headers = {"content-type": "text/plain"}
mock_text_response.raise_for_status = AsyncMock()
assert doc.id is not None with patch("httpx.AsyncClient.get", return_value=mock_text_response):
assert doc.content == "This is plain text content from a URL." doc = await client.create_document_from_source(
assert doc.uri == "https://example.com/readme.txt" "https://example.com/readme.txt"
assert "contentType" in doc.metadata )
assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "text/plain"
client.close() assert doc.id is not None
assert doc.content == "This is plain text content from a URL."
assert doc.uri == "https://example.com/readme.txt"
assert "contentType" in doc.metadata
assert "md5" in doc.metadata
assert doc.metadata["contentType"] == "text/plain"
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_url_unsupported_content(): async def test_client_create_document_from_url_unsupported_content():
"""Test creating a document from URL with unsupported content type.""" """Test creating a document from URL with unsupported content type."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Mock response with unsupported content type
mock_response = AsyncMock()
mock_response.content = b"binary content"
mock_response.headers = {"content-type": "application/octet-stream"}
mock_response.raise_for_status = AsyncMock()
# Mock response with unsupported content type with patch("httpx.AsyncClient.get", return_value=mock_response):
mock_response = AsyncMock() with pytest.raises(ValueError, match="Unsupported content type"):
mock_response.content = b"binary content" await client.create_document_from_source(
mock_response.headers = {"content-type": "application/octet-stream"} "https://example.com/binary.bin"
mock_response.raise_for_status = AsyncMock() )
with patch("httpx.AsyncClient.get", return_value=mock_response):
with pytest.raises(ValueError, match="Unsupported content type"):
await client.create_document_from_source("https://example.com/binary.bin")
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_document_from_url_http_error(): async def test_client_create_document_from_url_http_error():
"""Test handling HTTP errors when creating document from URL.""" """Test handling HTTP errors when creating document from URL."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
with patch("httpx.AsyncClient.get") as mock_get:
with patch("httpx.AsyncClient.get") as mock_get: mock_get.side_effect = httpx.HTTPStatusError(
mock_get.side_effect = httpx.HTTPStatusError( "404 Not Found",
"404 Not Found", request=httpx.Request("GET", "https://example.com/notfound.html"),
request=httpx.Request("GET", "https://example.com/notfound.html"), response=httpx.Response(404),
response=httpx.Response(404),
)
with pytest.raises(httpx.HTTPStatusError):
await client.create_document_from_source(
"https://example.com/notfound.html"
) )
client.close() with pytest.raises(httpx.HTTPStatusError):
await client.create_document_from_source(
"https://example.com/notfound.html"
)
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_get_extension_from_content_type_or_url(): async def test_get_extension_from_content_type_or_url():
"""Test the helper method for determining file extensions.""" """Test the helper method for determining file extensions."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Test content type mappings
# Test content type mappings assert (
assert client._get_extension_from_content_type_or_url("", "text/html") == ".html" client._get_extension_from_content_type_or_url("", "text/html") == ".html"
assert (
client._get_extension_from_content_type_or_url("", "application/pdf") == ".pdf"
)
assert client._get_extension_from_content_type_or_url("", "text/plain") == ".txt"
# Test URL extension detection
assert (
client._get_extension_from_content_type_or_url(
"https://example.com/doc.pdf", ""
) )
== ".pdf" assert (
) client._get_extension_from_content_type_or_url("", "application/pdf")
assert ( == ".pdf"
client._get_extension_from_content_type_or_url(
"https://example.com/data.json", ""
) )
== ".json" assert (
) client._get_extension_from_content_type_or_url("", "text/plain") == ".txt"
# Test default fallback
assert (
client._get_extension_from_content_type_or_url("https://example.com/", "")
== ".html"
)
# Test content type priority over URL extension
assert (
client._get_extension_from_content_type_or_url(
"https://example.com/file.txt", "application/pdf"
) )
== ".pdf"
)
client.close() # Test URL extension detection
assert (
client._get_extension_from_content_type_or_url(
"https://example.com/doc.pdf", ""
)
== ".pdf"
)
assert (
client._get_extension_from_content_type_or_url(
"https://example.com/data.json", ""
)
== ".json"
)
# Test default fallback
assert (
client._get_extension_from_content_type_or_url("https://example.com/", "")
== ".html"
)
# Test content type priority over URL extension
assert (
client._get_extension_from_content_type_or_url(
"https://example.com/file.txt", "application/pdf"
)
== ".pdf"
)
@pytest.mark.asyncio @pytest.mark.asyncio
@ -313,165 +283,147 @@ async def test_client_metadata_content_type_and_md5():
"""Test that contentType and md5 metadata are correctly set.""" """Test that contentType and md5 metadata are correctly set."""
import hashlib import hashlib
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Create a temporary file with known content
test_content = "Test content for MD5 calculation."
expected_md5 = hashlib.md5(test_content.encode()).hexdigest()
# Create a temporary file with known content with tempfile.TemporaryDirectory() as temp_dir:
test_content = "Test content for MD5 calculation." temp_path = Path(temp_dir) / "test.txt"
expected_md5 = hashlib.md5(test_content.encode()).hexdigest() temp_path.write_text(test_content)
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f: doc = await client.create_document_from_source(temp_path)
f.write(test_content)
temp_path = Path(f.name)
try: assert doc.metadata["contentType"] == "text/plain"
doc = await client.create_document_from_source(temp_path) assert doc.metadata["md5"] == expected_md5
assert doc.metadata["contentType"] == "text/plain" mock_response = AsyncMock()
assert doc.metadata["md5"] == expected_md5 mock_response.content = test_content.encode()
mock_response.headers = {"content-type": "text/plain"}
mock_response.raise_for_status = AsyncMock()
mock_response = AsyncMock() with patch("httpx.AsyncClient.get", return_value=mock_response):
mock_response.content = test_content.encode() url_doc = await client.create_document_from_source(
mock_response.headers = {"content-type": "text/plain"} "https://example.com/test.txt"
mock_response.raise_for_status = AsyncMock() )
with patch("httpx.AsyncClient.get", return_value=mock_response): assert url_doc.metadata["contentType"] == "text/plain"
url_doc = await client.create_document_from_source( assert url_doc.metadata["md5"] == expected_md5
"https://example.com/test.txt"
)
assert url_doc.metadata["contentType"] == "text/plain"
assert url_doc.metadata["md5"] == expected_md5
finally:
temp_path.unlink()
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_create_update_no_op_behavior(): async def test_client_create_update_no_op_behavior():
"""Test create/update/no-op behavior based on MD5 changes.""" """Test create/update/no-op behavior based on MD5 changes."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Create a temporary file
test_content = "Original content for testing."
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir) / "test.txt"
temp_path.write_text(test_content)
# Create a temporary file # First call - should create new document
test_content = "Original content for testing." doc1 = await client.create_document_from_source(temp_path)
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f: assert doc1.id is not None
f.write(test_content) assert doc1.content == test_content
temp_path = Path(f.name) original_id = doc1.id
try: # Second call with same content - should return existing document (no-op)
# First call - should create new document doc2 = await client.create_document_from_source(temp_path)
doc1 = await client.create_document_from_source(temp_path) assert doc2.id == original_id # Same document
assert doc1.id is not None assert doc2.content == test_content
assert doc1.content == test_content
original_id = doc1.id
# Second call with same content - should return existing document (no-op) # Modify file content
doc2 = await client.create_document_from_source(temp_path) updated_content = "Updated content for testing."
assert doc2.id == original_id # Same document temp_path.write_text(updated_content)
assert doc2.content == test_content
# Modify file content # Third call with changed content - should update existing document
updated_content = "Updated content for testing." doc3 = await client.create_document_from_source(temp_path)
temp_path.write_text(updated_content) assert doc3.id == original_id # Same document ID
assert doc3.content == updated_content # Updated content
# Third call with changed content - should update existing document # Verify the document was actually updated in database
doc3 = await client.create_document_from_source(temp_path) retrieved_doc = await client.get_document_by_id(original_id)
assert doc3.id == original_id # Same document ID assert retrieved_doc is not None
assert doc3.content == updated_content # Updated content assert retrieved_doc.content == updated_content
# Verify the document was actually updated in database
retrieved_doc = await client.get_document_by_id(original_id)
assert retrieved_doc is not None
assert retrieved_doc.content == updated_content
finally:
temp_path.unlink()
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_url_create_update_no_op_behavior(): async def test_client_url_create_update_no_op_behavior():
"""Test create/update/no-op behavior for URLs based on MD5 changes.""" """Test create/update/no-op behavior for URLs based on MD5 changes."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
url = "https://example.com/test.txt"
original_content = b"Original URL content"
updated_content = b"Updated URL content"
url = "https://example.com/test.txt" # Mock first response
original_content = b"Original URL content" mock_response1 = AsyncMock()
updated_content = b"Updated URL content" mock_response1.content = original_content
mock_response1.headers = {"content-type": "text/plain"}
mock_response1.raise_for_status = AsyncMock()
# Mock first response with patch("httpx.AsyncClient.get", return_value=mock_response1):
mock_response1 = AsyncMock() # First call - should create new document
mock_response1.content = original_content doc1 = await client.create_document_from_source(url)
mock_response1.headers = {"content-type": "text/plain"} assert doc1.id is not None
mock_response1.raise_for_status = AsyncMock() original_id = doc1.id
with patch("httpx.AsyncClient.get", return_value=mock_response1): # Second call with same content - should return existing document (no-op)
# First call - should create new document doc2 = await client.create_document_from_source(url)
doc1 = await client.create_document_from_source(url) assert doc2.id == original_id # Same document
assert doc1.id is not None
original_id = doc1.id
# Second call with same content - should return existing document (no-op) mock_response2 = AsyncMock()
doc2 = await client.create_document_from_source(url) mock_response2.content = updated_content
assert doc2.id == original_id # Same document mock_response2.headers = {"content-type": "text/plain"}
mock_response2.raise_for_status = AsyncMock()
mock_response2 = AsyncMock() with patch("httpx.AsyncClient.get", return_value=mock_response2):
mock_response2.content = updated_content # Third call with changed content - should update existing document
mock_response2.headers = {"content-type": "text/plain"} doc3 = await client.create_document_from_source(url)
mock_response2.raise_for_status = AsyncMock() assert doc3.id == original_id # Same document ID
assert doc3.content == updated_content.decode() # Updated content
with patch("httpx.AsyncClient.get", return_value=mock_response2):
# Third call with changed content - should update existing document
doc3 = await client.create_document_from_source(url)
assert doc3.id == original_id # Same document ID
assert doc3.content == updated_content.decode() # Updated content
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_client_search(): async def test_client_search():
"""Test HaikuRAG search functionality.""" """Test HaikuRAG search functionality."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
# Add multiple documents to search from
doc1_text = "Python is a high-level programming language known for its simplicity and readability."
doc2_text = "Machine learning algorithms help computers learn patterns from data without explicit programming."
doc3_text = "Data science combines statistics, programming, and domain expertise to extract insights."
# Add multiple documents to search from # Create documents
doc1_text = "Python is a high-level programming language known for its simplicity and readability." doc1 = await client.create_document(
doc2_text = "Machine learning algorithms help computers learn patterns from data without explicit programming." content=doc1_text, uri="doc1.txt", metadata={"topic": "python"}
doc3_text = "Data science combines statistics, programming, and domain expertise to extract insights." )
doc2 = await client.create_document(
content=doc2_text, uri="doc2.txt", metadata={"topic": "ml"}
)
await client.create_document(
content=doc3_text, uri="doc3.txt", metadata={"topic": "data_science"}
)
# Create documents # Test search with keyword that should match doc1
doc1 = await client.create_document( results = await client.search("Python programming", limit=3)
content=doc1_text, uri="doc1.txt", metadata={"topic": "python"}
)
doc2 = await client.create_document(
content=doc2_text, uri="doc2.txt", metadata={"topic": "ml"}
)
await client.create_document(
content=doc3_text, uri="doc3.txt", metadata={"topic": "data_science"}
)
# Test search with keyword that should match doc1 assert len(results) > 0
results = await client.search("Python programming", limit=3) assert all(len(result) == 2 for result in results)
assert len(results) > 0 # Verify first result is from the Python document (doc1)
assert all(len(result) == 2 for result in results) first_chunk, _ = results[0]
assert first_chunk.document_id == doc1.id
# Verify first result is from the Python document (doc1) # Test search with different query
first_chunk, _ = results[0] ml_results = await client.search("machine learning data", limit=2)
assert first_chunk.document_id == doc1.id assert len(ml_results) > 0
# Test search with different query # Verify first result is from the machine learning document (doc2)
ml_results = await client.search("machine learning data", limit=2) first_ml_chunk, _ = ml_results[0]
assert len(ml_results) > 0 assert first_ml_chunk.document_id == doc2.id
# Verify first result is from the machine learning document (doc2) # Test search with limit parameter
first_ml_chunk, _ = ml_results[0] limited_results = await client.search("programming", limit=1)
assert first_ml_chunk.document_id == doc2.id assert len(limited_results) <= 1
# Test search with limit parameter
limited_results = await client.search("programming", limit=1)
assert len(limited_results) <= 1
client.close()
@pytest.mark.asyncio @pytest.mark.asyncio

View file

@ -13,11 +13,10 @@ from haiku.rag.store.models.document import Document
async def test_file_watcher_upsert_document(): async def test_file_watcher_upsert_document():
"""Test FileWatcher._upsert_document method.""" """Test FileWatcher._upsert_document method."""
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f: with tempfile.TemporaryDirectory() as temp_dir:
f.write("Test content for file watcher") temp_path = Path(temp_dir) / "test.txt"
temp_path = Path(f.name) temp_path.write_text("Test content for file watcher")
try:
mock_client = AsyncMock(spec=HaikuRAG) mock_client = AsyncMock(spec=HaikuRAG)
mock_doc = Document(id=1, content="Test content", uri=temp_path.as_uri()) mock_doc = Document(id=1, content="Test content", uri=temp_path.as_uri())
mock_client.create_document_from_source.return_value = mock_doc mock_client.create_document_from_source.return_value = mock_doc
@ -32,19 +31,15 @@ async def test_file_watcher_upsert_document():
mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri()) mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri())
mock_client.create_document_from_source.assert_called_once_with(str(temp_path)) mock_client.create_document_from_source.assert_called_once_with(str(temp_path))
finally:
temp_path.unlink(missing_ok=True)
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_file_watcher_upsert_existing_document(): async def test_file_watcher_upsert_existing_document():
"""Test FileWatcher._upsert_document with existing document.""" """Test FileWatcher._upsert_document with existing document."""
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f: with tempfile.TemporaryDirectory() as temp_dir:
f.write("Test content for file watcher") temp_path = Path(temp_dir) / "test.txt"
temp_path = Path(f.name) temp_path.write_text("Test content for file watcher")
try:
mock_client = AsyncMock(spec=HaikuRAG) mock_client = AsyncMock(spec=HaikuRAG)
existing_doc = Document(id=1, content="Old content", uri=temp_path.as_uri()) existing_doc = Document(id=1, content="Old content", uri=temp_path.as_uri())
updated_doc = Document(id=1, content="Updated content", uri=temp_path.as_uri()) updated_doc = Document(id=1, content="Updated content", uri=temp_path.as_uri())
@ -61,9 +56,6 @@ async def test_file_watcher_upsert_existing_document():
mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri()) mock_client.get_document_by_uri.assert_called_once_with(temp_path.as_uri())
mock_client.create_document_from_source.assert_called_once_with(str(temp_path)) mock_client.create_document_from_source.assert_called_once_with(str(temp_path))
finally:
temp_path.unlink(missing_ok=True)
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_file_watcher_delete_document(): async def test_file_watcher_delete_document():

View file

@ -8,45 +8,42 @@ from haiku.rag.store.models.document import Document
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_rebuild_database(qa_corpus: Dataset): async def test_rebuild_database(qa_corpus: Dataset):
"""Test rebuild functionality with existing documents.""" """Test rebuild functionality with existing documents."""
client = HaikuRAG(":memory:") async with HaikuRAG(":memory:") as client:
created_docs: list[Document] = []
for content in qa_corpus["document_extracted"][:3]:
doc = await client.create_document(
content=content,
)
created_docs.append(doc)
created_docs: list[Document] = [] documents_before = await client.list_documents()
for content in qa_corpus["document_extracted"][:3]: assert len(documents_before) == 3
doc = await client.create_document(
content=content,
)
created_docs.append(doc)
documents_before = await client.list_documents() chunks_before = []
assert len(documents_before) == 3 for doc in created_docs:
assert doc.id is not None
chunks_before = []
for doc in created_docs:
assert doc.id is not None
doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
chunks_before.extend(doc_chunks)
assert len(chunks_before) > 0
# Perform rebuild
processed_doc_ids = []
async for doc_id in client.rebuild_database():
processed_doc_ids.append(doc_id)
# Verify all documents were processed
expected_doc_ids = [doc.id for doc in created_docs]
assert set(processed_doc_ids) == set(expected_doc_ids)
documents_after = await client.list_documents()
assert len(documents_after) == 3
# Verify chunks were recreated
chunks_after = []
for doc in documents_after:
if doc.id is not None:
doc_chunks = await client.chunk_repository.get_by_document_id(doc.id) doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
chunks_after.extend(doc_chunks) chunks_before.extend(doc_chunks)
assert len(chunks_after) > 0 assert len(chunks_before) > 0
client.close() # Perform rebuild
processed_doc_ids = []
async for doc_id in client.rebuild_database():
processed_doc_ids.append(doc_id)
# Verify all documents were processed
expected_doc_ids = [doc.id for doc in created_docs]
assert set(processed_doc_ids) == set(expected_doc_ids)
documents_after = await client.list_documents()
assert len(documents_after) == 3
# Verify chunks were recreated
chunks_after = []
for doc in documents_after:
if doc.id is not None:
doc_chunks = await client.chunk_repository.get_by_document_id(doc.id)
chunks_after.extend(doc_chunks)
assert len(chunks_after) > 0

81
tests/test_settings.py Normal file
View file

@ -0,0 +1,81 @@
import tempfile
from pathlib import Path
import pytest
from haiku.rag.client import HaikuRAG
from haiku.rag.config import Config
from haiku.rag.store.engine import Store
from haiku.rag.store.repositories.settings import (
ConfigMismatchError,
SettingsRepository,
)
def test_settings_table_populated_on_store_init():
"""Test that settings table is populated with current config when store is initialized."""
store = Store(":memory:")
settings_repo = SettingsRepository(store)
db_settings = settings_repo.get()
config_dict = Config.model_dump(mode="json")
assert db_settings == config_dict
store.close()
def test_settings_save_and_retrieve():
"""Test saving and retrieving settings after config change."""
store = Store(":memory:")
settings_repo = SettingsRepository(store)
original_chunk_size = Config.CHUNK_SIZE
Config.CHUNK_SIZE = 2 * original_chunk_size
settings_repo.save()
retrieved_settings = settings_repo.get()
assert retrieved_settings["CHUNK_SIZE"] == 2 * original_chunk_size
Config.CHUNK_SIZE = original_chunk_size
store.close()
async def test_config_validation_on_db_load():
"""Test that config validation fails when loading db with mismatched settings."""
# Create a temporary database file
with tempfile.NamedTemporaryFile(suffix=".sqlite") as tmp:
db_path = Path(tmp.name)
# Create store and save settings
store1 = Store(db_path)
SettingsRepository(store1)
store1.close()
# Change config
original_chunk_size = Config.CHUNK_SIZE
Config.CHUNK_SIZE = 999
try:
# Loading the database should raise ConfigMismatchError
with pytest.raises(ConfigMismatchError) as exc_info:
Store(db_path)
assert "CHUNK_SIZE" in str(exc_info.value)
assert "Consider rebuilding" in str(exc_info.value)
# Rebuild
async with HaikuRAG(db_path=db_path, skip_validation=True) as client:
async for _ in client.rebuild_database():
pass # Process all documents
# Verify we can now load the database without exception (settings were updated)
store2 = Store(db_path)
settings_repo2 = SettingsRepository(store2)
db_settings = settings_repo2.get()
assert db_settings["CHUNK_SIZE"] == 999
store2.close()
finally:
Config.CHUNK_SIZE = original_chunk_size

View file

@ -881,7 +881,7 @@ dev = [
{ name = "mkdocs", specifier = ">=1.6.1" }, { name = "mkdocs", specifier = ">=1.6.1" },
{ name = "mkdocs-material", specifier = ">=9.6.14" }, { name = "mkdocs-material", specifier = ">=9.6.14" },
{ name = "pre-commit", specifier = ">=4.2.0" }, { name = "pre-commit", specifier = ">=4.2.0" },
{ name = "pyright", specifier = ">=1.1.402" }, { name = "pyright", specifier = ">=1.1.403" },
{ name = "pytest", specifier = ">=8.4.0" }, { name = "pytest", specifier = ">=8.4.0" },
{ name = "pytest-asyncio", specifier = ">=1.0.0" }, { name = "pytest-asyncio", specifier = ">=1.0.0" },
{ name = "pytest-cov", specifier = ">=6.2.1" }, { name = "pytest-cov", specifier = ">=6.2.1" },
@ -2305,15 +2305,15 @@ wheels = [
[[package]] [[package]]
name = "pyright" name = "pyright"
version = "1.1.402" version = "1.1.403"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
dependencies = [ dependencies = [
{ name = "nodeenv" }, { name = "nodeenv" },
{ name = "typing-extensions" }, { name = "typing-extensions" },
] ]
sdist = { url = "https://files.pythonhosted.org/packages/aa/04/ce0c132d00e20f2d2fb3b3e7c125264ca8b909e693841210534b1ea1752f/pyright-1.1.402.tar.gz", hash = "sha256:85a33c2d40cd4439c66aa946fd4ce71ab2f3f5b8c22ce36a623f59ac22937683", size = 3888207, upload-time = "2025-06-11T08:48:35.759Z" } sdist = { url = "https://files.pythonhosted.org/packages/fe/f6/35f885264ff08c960b23d1542038d8da86971c5d8c955cfab195a4f672d7/pyright-1.1.403.tar.gz", hash = "sha256:3ab69b9f41c67fb5bbb4d7a36243256f0d549ed3608678d381d5f51863921104", size = 3913526, upload-time = "2025-07-09T07:15:52.882Z" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/fe/37/1a1c62d955e82adae588be8e374c7f77b165b6cb4203f7d581269959abbc/pyright-1.1.402-py3-none-any.whl", hash = "sha256:2c721f11869baac1884e846232800fe021c33f1b4acb3929cff321f7ea4e2982", size = 5624004, upload-time = "2025-06-11T08:48:33.998Z" }, { url = "https://files.pythonhosted.org/packages/49/b6/b04e5c2f41a5ccad74a1a4759da41adb20b4bc9d59a5e08d29ba60084d07/pyright-1.1.403-py3-none-any.whl", hash = "sha256:c0eeca5aa76cbef3fcc271259bbd785753c7ad7bcac99a9162b4c4c7daed23b3", size = 5684504, upload-time = "2025-07-09T07:15:50.958Z" },
] ]
[[package]] [[package]]