haiku.rag 0.13.1__py3-none-any.whl → 0.13.2__py3-none-any.whl

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/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/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/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/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:

{haiku_rag-0.13.1.dist-info → haiku_rag-0.13.2.dist-info}/METADATA

@@ -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.dist-info → haiku_rag-0.13.2.dist-info}/RECORD

@@ -1,11 +1,11 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=lNPYYWQLOPlOLYiwIR4yQuwzl-LrRNQn7n2nacgdq_k,21594
+haiku/rag/app.py,sha256=hjHZoXfMvb2Pvd4sSdzQVq759zO7UGR9YuyXXA6ZbDI,21514
 haiku/rag/chunker.py,sha256=pA0S0fFKAuvzGm2dGyp7FAkeFZA0YTCm_ata83Pnflw,1566
 haiku/rag/cli.py,sha256=Y42tnlVFGvCZVjBcLWrIVgM0A7KjNYX9MAuk9-zQvvE,14523
 haiku/rag/client.py,sha256=cG6DAhzJJ4vdo8QFn9p8iA6YTa0arMrTtIswoZc7sY0,26816
 haiku/rag/logging.py,sha256=dm65AwADpcQsH5OAPtRA-4hsw0w5DK-sGOvzYkj6jzw,1720
 haiku/rag/mcp.py,sha256=txuEnrUMWvs_shQBk15gEkJD7xNdSYzp3z75UUWaHFM,9328
-haiku/rag/monitor.py,sha256=d92oRufhI8oYXH7oF6oYVf1_AcpFUafjM6tl4VhAupI,3322
+haiku/rag/monitor.py,sha256=EGQ-sKH1uKBSHtglehuW1COytx-4zKCKAT198tTr0Fo,4889
 haiku/rag/reader.py,sha256=aW8LG0X31kVWS7kU2tKVpe8RqP3Ne_oIidd_X3UDLH0,3307
 haiku/rag/utils.py,sha256=47ehVYJlLz6Of_Ua89qj94JclO5ZPBFU9eyonifvnVg,6131
 haiku/rag/a2a/__init__.py,sha256=tY_jLSUM0zKzyBctMkjpqmDWpxWc9QVEK1qAsb-plGs,5933
@@ -16,9 +16,9 @@ haiku/rag/a2a/prompts.py,sha256=yCla8x0hbOhKrkuaqVrF1upn-YjQM3-2NsE2TSnet0M,3030
 haiku/rag/a2a/skills.py,sha256=dwyD2Bn493eL3Vf4uQzmyxj_9IUSb66kQ-085FBAuCs,2701
 haiku/rag/a2a/storage.py,sha256=c8vmGCiZ3nuV9wUuTnwpoRD2HVVvK2JPySQOc5PVMvg,2759
 haiku/rag/a2a/worker.py,sha256=S9hiA1ncpJPdtN0eEmMjsvr5LQ4wMVN5R8CjYkTeohU,12367
-haiku/rag/config/__init__.py,sha256=PSHsc7gXjvRxpzN4rxR083-WYU-pocqm0hf2uhkr9Vw,1019
-haiku/rag/config/loader.py,sha256=eWkD8uVTa19nf7d7yyZImk7t5k0-SagYH4RSBqfkPxQ,4848
-haiku/rag/config/models.py,sha256=vkq2WyJfuY1cm8YEFlox0Cd8sVyXb4l1XX2fkBjI6I4,2169
+haiku/rag/config/__init__.py,sha256=1AiYIX9fiVvi4nKlRnCf18ywFHQECZ-mXXvOIRYfGSU,1059
+haiku/rag/config/loader.py,sha256=P2vKmk1fi9O2fbQAyWAq5SqLaFBAq_sbVr8lqi8YtlY,4982
+haiku/rag/config/models.py,sha256=yySklxjYODF5Tj6xTQogG8LTjNaKnO8SLwqdeP6buKY,2334
 haiku/rag/embeddings/__init__.py,sha256=zwWRU9S5YGEJxlgPv5haHBgj3LUJMe-dEwr3LKLa9RY,1731
 haiku/rag/embeddings/base.py,sha256=kzca54e2HGzS_0YKt9OLESM9lrFKpBm_97V07jx0aas,783
 haiku/rag/embeddings/ollama.py,sha256=_uIIObbZX9QVU1lcgWQFooA3b-AeZRNncM7yQ2TxlEU,825
@@ -70,8 +70,8 @@ haiku/rag/store/repositories/settings.py,sha256=15gS7Xj7cG4qetv_ioxZO_r31by7GuSq
 haiku/rag/store/upgrades/__init__.py,sha256=RQ8A6rEXBASLb5PD9vdDnEas_m_GgRzzdVu4B88Snqc,1975
 haiku/rag/store/upgrades/v0_10_1.py,sha256=qNGnxj6hoHaHJ1rKTiALfw0c9NQOi0KAK-VZCD_073A,1959
 haiku/rag/store/upgrades/v0_9_3.py,sha256=NrjNilQSgDtFWRbL3ZUtzQzJ8tf9u0dDRJtnDFwwbdw,3322
-haiku_rag-0.13.1.dist-info/METADATA,sha256=xoojNWUahlMw6gWdujYr_VNti4ss4We0mL0rkTOkxgo,8139
-haiku_rag-0.13.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.13.1.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.13.1.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.13.1.dist-info/RECORD,,
+haiku_rag-0.13.2.dist-info/METADATA,sha256=YyvjWsHy7Y8DX8-spZcc7wzUsb7yn2okaMS3SiWw2Nk,8179
+haiku_rag-0.13.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.13.2.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.13.2.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.13.2.dist-info/RECORD,,