haiku.rag 0.13.1__tar.gz → 0.13.2__tar.gz

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.13.1
+Version: 0.13.2
 Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -17,19 +17,20 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Typing :: Typed
 Requires-Python: >=3.12
-Requires-Dist: docling>=2.56.1
-Requires-Dist: fastmcp>=2.12.4
+Requires-Dist: docling>=2.58.0
+Requires-Dist: fastmcp>=2.13.0.2
 Requires-Dist: httpx>=0.28.1
 Requires-Dist: lancedb>=0.25.2
-Requires-Dist: pydantic-ai>=1.0.18
-Requires-Dist: pydantic-graph>=1.0.18
-Requires-Dist: pydantic>=2.12.2
-Requires-Dist: python-dotenv>=1.1.1
-Requires-Dist: pyyaml>=6.0.1
+Requires-Dist: pathspec>=0.12.1
+Requires-Dist: pydantic-ai>=1.7.0
+Requires-Dist: pydantic-graph>=1.7.0
+Requires-Dist: pydantic>=2.12.3
+Requires-Dist: python-dotenv>=1.2.1
+Requires-Dist: pyyaml>=6.0.3
 Requires-Dist: rich>=14.2.0
 Requires-Dist: tiktoken>=0.12.0
-Requires-Dist: typer>=0.19.2
-Requires-Dist: watchfiles>=1.1.0
+Requires-Dist: typer<0.20.0,>=0.19.2
+Requires-Dist: watchfiles>=1.1.1
 Provides-Extra: a2a
 Requires-Dist: fasta2a>=0.1.0; extra == 'a2a'
 Provides-Extra: mxbai

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "haiku.rag"
 description = "Agentic Retrieval Augmented Generation (RAG) with LanceDB"
-version = "0.13.1"
+version = "0.13.2"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }
@@ -22,19 +22,20 @@ classifiers = [
 ]
 
 dependencies = [
-    "docling>=2.56.1",
-    "fastmcp>=2.12.4",
+    "docling>=2.58.0",
+    "fastmcp>=2.13.0.2",
     "httpx>=0.28.1",
     "lancedb>=0.25.2",
-    "pydantic>=2.12.2",
-    "pydantic-ai>=1.0.18",
-    "pydantic-graph>=1.0.18",
-    "python-dotenv>=1.1.1",
-    "pyyaml>=6.0.1",
+    "pathspec>=0.12.1",
+    "pydantic>=2.12.3",
+    "pydantic-ai>=1.7.0",
+    "pydantic-graph>=1.7.0",
+    "python-dotenv>=1.2.1",
+    "pyyaml>=6.0.3",
     "rich>=14.2.0",
     "tiktoken>=0.12.0",
-    "typer>=0.19.2",
-    "watchfiles>=1.1.0",
+    "typer>=0.19.2,<0.20.0",
+    "watchfiles>=1.1.1",
 ]
 
 [project.optional-dependencies]
@@ -57,17 +58,17 @@ packages = ["src/haiku"]
 
 [dependency-groups]
 dev = [
-    "datasets>=4.1.0",
-    "logfire>=4.7.0",
+    "datasets>=4.3.0",
+    "logfire>=4.14.2",
     "mkdocs>=1.6.1",
-    "mkdocs-material>=9.6.14",
-    "pydantic-evals>=1.0.8",
-    "pre-commit>=4.2.0",
-    "pyright>=1.1.406",
+    "mkdocs-material>=9.6.22",
+    "pydantic-evals>=1.7.0",
+    "pre-commit>=4.3.0",
+    "pyright>=1.1.407",
     "pytest>=8.4.2",
     "pytest-asyncio>=1.2.0",
     "pytest-cov>=7.0.0",
-    "ruff>=0.13.0",
+    "ruff>=0.14.2",
 ]
 
 [tool.ruff]

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/src/haiku/rag/app.py

@@ -474,9 +474,7 @@ class HaikuRAGApp:
 
             # Start file monitor if enabled
             if enable_monitor:
-                monitor = FileWatcher(
-                    paths=Config.storage.monitor_directories, client=client
-                )
+                monitor = FileWatcher(client=client)
                 monitor_task = asyncio.create_task(monitor.observe())
                 tasks.append(monitor_task)
 

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/src/haiku/rag/config/__init__.py

@@ -11,6 +11,7 @@ from haiku.rag.config.models import (
     AppConfig,
     EmbeddingsConfig,
     LanceDBConfig,
+    MonitorConfig,
     OllamaConfig,
     ProcessingConfig,
     ProvidersConfig,
@@ -25,6 +26,7 @@ __all__ = [
     "Config",
     "AppConfig",
     "StorageConfig",
+    "MonitorConfig",
     "LanceDBConfig",
     "EmbeddingsConfig",
     "RerankingConfig",

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/src/haiku/rag/config/loader.py

@@ -10,7 +10,7 @@ def find_config_file(cli_path: Path | None = None) -> Path | None:
     Search order:
     1. CLI-provided path (via HAIKU_RAG_CONFIG_PATH env var or parameter)
     2. ./haiku.rag.yaml (current directory)
-    3. ~/.config/haiku.rag/config.yaml (user config)
+    3. Platform-specific user config directory
 
     Returns None if no config file is found.
     """
@@ -29,8 +29,10 @@ def find_config_file(cli_path: Path | None = None) -> Path | None:
     if cwd_config.exists():
         return cwd_config
 
-    user_config_dir = Path.home() / ".config" / "haiku.rag"
-    user_config = user_config_dir / "config.yaml"
+    # Use same directory as data storage for config
+    from haiku.rag.utils import get_default_data_dir
+
+    user_config = get_default_data_dir() / "config.yaml"
     if user_config.exists():
         return user_config
 
@@ -50,10 +52,14 @@ def generate_default_config() -> dict:
         "environment": "production",
         "storage": {
             "data_dir": "",
-            "monitor_directories": [],
             "disable_autocreate": False,
             "vacuum_retention_seconds": 60,
         },
+        "monitor": {
+            "directories": [],
+            "ignore_patterns": [],
+            "include_patterns": [],
+        },
         "lancedb": {"uri": "", "api_key": "", "region": ""},
         "embeddings": {
             "provider": "ollama",
@@ -88,7 +94,7 @@ def load_config_from_env() -> dict:
     env_mappings = {
         "ENV": "environment",
         "DEFAULT_DATA_DIR": ("storage", "data_dir"),
-        "MONITOR_DIRECTORIES": ("storage", "monitor_directories"),
+        "MONITOR_DIRECTORIES": ("monitor", "directories"),
         "DISABLE_DB_AUTOCREATE": ("storage", "disable_autocreate"),
         "VACUUM_RETENTION_SECONDS": ("storage", "vacuum_retention_seconds"),
         "LANCEDB_URI": ("lancedb", "uri"),

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/src/haiku/rag/config/models.py

@@ -7,11 +7,16 @@ from haiku.rag.utils import get_default_data_dir
 
 class StorageConfig(BaseModel):
     data_dir: Path = Field(default_factory=get_default_data_dir)
-    monitor_directories: list[Path] = []
     disable_autocreate: bool = False
     vacuum_retention_seconds: int = 60
 
 
+class MonitorConfig(BaseModel):
+    directories: list[Path] = []
+    ignore_patterns: list[str] = []
+    include_patterns: list[str] = []
+
+
 class LanceDBConfig(BaseModel):
     uri: str = ""
     api_key: str = ""
@@ -72,6 +77,7 @@ class A2AConfig(BaseModel):
 class AppConfig(BaseModel):
     environment: str = "production"
     storage: StorageConfig = Field(default_factory=StorageConfig)
+    monitor: MonitorConfig = Field(default_factory=MonitorConfig)
     lancedb: LanceDBConfig = Field(default_factory=LanceDBConfig)
     embeddings: EmbeddingsConfig = Field(default_factory=EmbeddingsConfig)
     reranking: RerankingConfig = Field(default_factory=RerankingConfig)

{haiku_rag-0.13.1 → haiku_rag-0.13.2}/src/haiku/rag/monitor.py

@@ -2,9 +2,12 @@ import logging
 from pathlib import Path
 from typing import TYPE_CHECKING
 
+import pathspec
+from pathspec.patterns.gitwildmatch import GitWildMatchPattern
 from watchfiles import Change, DefaultFilter, awatch
 
 from haiku.rag.client import HaikuRAG
+from haiku.rag.config import AppConfig, Config
 from haiku.rag.store.models.document import Document
 
 if TYPE_CHECKING:
@@ -14,25 +17,63 @@ logger = logging.getLogger(__name__)
 
 
 class FileFilter(DefaultFilter):
-    def __init__(self, *, ignore_paths: list[Path] | None = None) -> None:
+    def __init__(
+        self,
+        *,
+        ignore_patterns: list[str] | None = None,
+        include_patterns: list[str] | None = None,
+    ) -> None:
         # Lazy import to avoid loading docling
         from haiku.rag.reader import FileReader
 
         self.extensions = tuple(FileReader.extensions)
-        super().__init__(ignore_paths=ignore_paths)
+        self.ignore_spec = (
+            pathspec.PathSpec.from_lines(GitWildMatchPattern, ignore_patterns)
+            if ignore_patterns
+            else None
+        )
+        self.include_spec = (
+            pathspec.PathSpec.from_lines(GitWildMatchPattern, include_patterns)
+            if include_patterns
+            else None
+        )
+        super().__init__()
 
     def __call__(self, change: Change, path: str) -> bool:
-        return path.endswith(self.extensions) and super().__call__(change, path)
+        # Check extension filter
+        if not path.endswith(self.extensions):
+            return False
+
+        # Apply include patterns if specified (whitelist mode)
+        if self.include_spec:
+            if not self.include_spec.match_file(path):
+                return False
+
+        # Apply ignore patterns (blacklist mode)
+        if self.ignore_spec:
+            if self.ignore_spec.match_file(path):
+                return False
+
+        # Apply default watchfiles filter
+        return super().__call__(change, path)
 
 
 class FileWatcher:
-    def __init__(self, paths: list[Path], client: HaikuRAG):
-        self.paths = paths
+    def __init__(
+        self,
+        client: HaikuRAG,
+        config: AppConfig = Config,
+    ):
+        self.paths = config.monitor.directories
         self.client = client
+        self.ignore_patterns = config.monitor.ignore_patterns or None
+        self.include_patterns = config.monitor.include_patterns or None
 
     async def observe(self):
         logger.info(f"Watching files in {self.paths}")
-        filter = FileFilter()
+        filter = FileFilter(
+            ignore_patterns=self.ignore_patterns, include_patterns=self.include_patterns
+        )
         await self.refresh()
 
         async for changes in awatch(*self.paths, watch_filter=filter):
@@ -49,10 +90,17 @@ class FileWatcher:
         # Lazy import to avoid loading docling
         from haiku.rag.reader import FileReader
 
+        # Create filter to apply same logic as observe()
+        filter = FileFilter(
+            ignore_patterns=self.ignore_patterns, include_patterns=self.include_patterns
+        )
+
         for path in self.paths:
             for f in Path(path).rglob("**/*"):
                 if f.is_file() and f.suffix in FileReader.extensions:
-                    await self._upsert_document(f)
+                    # Apply pattern filters
+                    if filter(Change.added, str(f)):
+                        await self._upsert_document(f)
 
     async def _upsert_document(self, file: Path) -> Document | None:
         try: