beaver-db 0.18.6__py3-none-any.whl → 0.19.2__py3-none-any.whl

beaver/__init__.py

@@ -2,4 +2,4 @@ from .core import BeaverDB
 from .types import Model
 from .collections import Document, WalkDirection
 
-__version__ = "0.18.6"
+__version__ = "0.19.2"

beaver/blobs.py

@@ -122,5 +122,16 @@ class BlobManager[M]:
             yield row["key"]
         cursor.close()
 
+    def __len__(self) -> int:
+        """Returns the number of blobs in the store."""
+        cursor = self._db.connection.cursor()
+        cursor.execute(
+            "SELECT COUNT(*) FROM beaver_blobs WHERE store_name = ?",
+            (self._name,)
+        )
+        count = cursor.fetchone()[0]
+        cursor.close()
+        return count
+
     def __repr__(self) -> str:
         return f"BlobManager(name='{self._name}')"

beaver/core.py

@@ -9,6 +9,7 @@ from .channels import ChannelManager
 from .collections import CollectionManager, Document
 from .dicts import DictManager
 from .lists import ListManager
+from .locks import LockManager
 from .logs import LogManager
 from .queues import QueueManager
 
@@ -99,6 +100,35 @@ class BeaverDB:
             self._create_pubsub_table()
             self._create_trigrams_table()
             self._create_versions_table()
+            self._create_locks_table()
+
+    def _create_locks_table(self):  # <-- Add this new method
+        """Creates the table for managing inter-process lock waiters."""
+        self.connection.execute(
+            """
+            CREATE TABLE IF NOT EXISTS beaver_lock_waiters (
+                lock_name TEXT NOT NULL,
+                waiter_id TEXT NOT NULL,
+                requested_at REAL NOT NULL,
+                expires_at REAL NOT NULL,
+                PRIMARY KEY (lock_name, requested_at)
+            )
+            """
+        )
+        # Index for fast cleanup of expired locks
+        self.connection.execute(
+            """
+            CREATE INDEX IF NOT EXISTS idx_lock_expires
+            ON beaver_lock_waiters (lock_name, expires_at)
+            """
+        )
+        # Index for fast deletion by the lock holder
+        self.connection.execute(
+            """
+            CREATE INDEX IF NOT EXISTS idx_lock_waiter_id
+            ON beaver_lock_waiters (lock_name, waiter_id)
+            """
+        )
 
     def _create_logs_table(self):
         """Creates the table for time-indexed logs."""
@@ -421,3 +451,24 @@ class BeaverDB:
             raise TypeError("The model parameter must be a JsonSerializable class.")
 
         return LogManager(name, self, self._db_path, model)
+
+    def lock(
+        self,
+        name: str,
+        timeout: float | None = None,
+        lock_ttl: float = 60.0,
+        poll_interval: float = 0.1,
+    ) -> LockManager:
+        """
+        Returns an inter-process lock manager for a given lock name.
+
+        Args:
+            name: The unique name of the lock (e.g., "run_compaction").
+            timeout: Max seconds to wait to acquire the lock.
+                    If None, it will wait forever.
+            lock_ttl: Max seconds the lock can be held. If the process crashes,
+                    the lock will auto-expire after this time.
+            poll_interval: Seconds to wait between polls. Shorter intervals
+                        are more responsive but create more DB I/O.
+        """
+        return LockManager(self, name, timeout, lock_ttl, poll_interval)

beaver/locks.py

@@ -0,0 +1,173 @@
+import random
+import time
+import os
+import uuid
+from typing import Optional
+from .types import IDatabase
+
+
+class LockManager:
+    """
+    An inter-process, deadlock-proof, and fair (FIFO) lock built on SQLite.
+
+    This class provides a context manager (`with` statement) to ensure that
+    only one process (among many) can enter a critical section of code at a
+    time.
+
+    It is "fair" because it uses a FIFO queue (based on insertion time).
+    It is "deadlock-proof" because locks have a Time-To-Live (TTL); if a
+    process crashes, its lock will eventually expire and be cleaned up.
+    """
+
+    def __init__(
+        self,
+        db: IDatabase,
+        name: str,
+        timeout: Optional[float] = None,
+        lock_ttl: float = 60.0,
+        poll_interval: float = 0.1,
+    ):
+        """
+        Initializes the lock manager.
+
+        Args:
+            db: The BeaverDB instance.
+            name: The unique name of the lock (e.g., "run_compaction").
+            timeout: Max seconds to wait to acquire the lock. If None,
+                     it will wait forever.
+            lock_ttl: Max seconds the lock can be held. If the process crashes,
+                      the lock will auto-expire after this time.
+            poll_interval: Seconds to wait between polls.
+        """
+        if not isinstance(name, str) or not name:
+            raise ValueError("Lock name must be a non-empty string.")
+        if lock_ttl <= 0:
+            raise ValueError("lock_ttl must be positive.")
+        if poll_interval <= 0:
+            raise ValueError("poll_interval must be positive.")
+
+        self._db = db
+        self._lock_name = name
+        self._timeout = timeout
+        self._lock_ttl = lock_ttl
+        self._poll_interval = poll_interval
+        # A unique ID for this specific lock instance across all processes
+        self._waiter_id = f"pid:{os.getpid()}:id:{uuid.uuid4()}"
+        self._acquired = False  # State to track if this instance holds the lock
+
+    def acquire(self) -> "LockManager":
+        """
+        Blocks until the lock is acquired or the timeout expires.
+
+        Raises:
+            TimeoutError: If the lock cannot be acquired within the specified timeout.
+        """
+        if self._acquired:
+            # This instance already holds the lock
+            return self
+
+        start_time = time.time()
+        requested_at = time.time()
+        expires_at = requested_at + self._lock_ttl
+
+        conn = self._db.connection
+
+        try:
+            # 1. Add self to the FIFO queue (atomic)
+            with conn:
+                conn.execute(
+                    """
+                    INSERT INTO beaver_lock_waiters (lock_name, waiter_id, requested_at, expires_at)
+                    VALUES (?, ?, ?, ?)
+                    """,
+                    (self._lock_name, self._waiter_id, requested_at, expires_at),
+                )
+
+            # 2. Start polling loop
+            while True:
+                with conn:
+                    # 3. Clean up expired locks from crashed processes
+                    now = time.time()
+                    conn.execute(
+                        "DELETE FROM beaver_lock_waiters WHERE lock_name = ? AND expires_at < ?",
+                        (self._lock_name, now),
+                    )
+
+                    # 4. Check who is at the front of the queue
+                    cursor = conn.cursor()
+                    cursor.execute(
+                        """
+                        SELECT waiter_id FROM beaver_lock_waiters
+                        WHERE lock_name = ?
+                        ORDER BY requested_at ASC
+                        LIMIT 1
+                        """,
+                        (self._lock_name,),
+                    )
+                    result = cursor.fetchone()
+                    cursor.close()
+
+                    if result and result["waiter_id"] == self._waiter_id:
+                        # We are at the front. We own the lock.
+                        self._acquired = True
+                        return self
+
+                # 5. Check for timeout
+                if self._timeout is not None:
+                    if (time.time() - start_time) > self._timeout:
+                        # We timed out. Remove ourselves from the queue and raise.
+                        self._release_from_queue()
+                        raise TimeoutError(
+                            f"Failed to acquire lock '{self._lock_name}' within {self._timeout}s."
+                        )
+
+                # 6. Wait politely before polling again
+                # Add +/- 10% jitter to the poll interval to avoid thundering herd
+                jitter = self._poll_interval * 0.1
+                sleep_time = random.uniform(
+                    self._poll_interval - jitter, self._poll_interval + jitter
+                )
+                time.sleep(sleep_time)
+
+        except Exception:
+            # If anything goes wrong, try to clean up our waiter entry
+            self._release_from_queue()
+            raise
+
+    def _release_from_queue(self):
+        """
+        Atomically removes this instance's entry from the waiter queue.
+        This is a best-effort, fire-and-forget operation.
+        """
+        try:
+            with self._db.connection:
+                self._db.connection.execute(
+                    "DELETE FROM beaver_lock_waiters WHERE lock_name = ? AND waiter_id = ?",
+                    (self._lock_name, self._waiter_id),
+                )
+        except Exception:
+            # Don't raise errors during release/cleanup
+            pass
+
+    def release(self):
+        """
+        Releases the lock, allowing the next process in the queue to acquire it.
+        This is safe to call multiple times.
+        """
+        if not self._acquired:
+            # We don't hold the lock, so nothing to do.
+            return
+
+        self._release_from_queue()
+        self._acquired = False
+
+    def __enter__(self) -> "LockManager":
+        """Acquires the lock when entering a 'with' statement."""
+        return self.acquire()
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Releases the lock when exiting a 'with' statement."""
+        self.release()
+
+    def __repr__(self) -> str:
+        return f"LockManager(name='{self._lock_name}', acquired={self._acquired})"

beaver/server.py

@@ -2,11 +2,23 @@ try:
     from typing import Any, Optional, List
     import json
     from datetime import datetime, timedelta, timezone
-    from fastapi import FastAPI, HTTPException, Body, UploadFile, File, Form, Response, WebSocket, WebSocketDisconnect
+    from fastapi import (
+        FastAPI,
+        HTTPException,
+        Body,
+        UploadFile,
+        File,
+        Form,
+        Response,
+        WebSocket,
+        WebSocketDisconnect,
+    )
     import uvicorn
     from pydantic import BaseModel, Field
 except ImportError:
-    raise ImportError("Please install server dependencies with: pip install \"beaver-db[server]\"")
+    raise ImportError(
+        'Please install server dependencies with: pip install "beaver-db[server]"'
+    )
 
 from .core import BeaverDB
 from .collections import Document, WalkDirection
@@ -14,6 +26,7 @@ from .collections import Document, WalkDirection
 
 # --- Pydantic Models for Collections ---
 
+
 class IndexRequest(BaseModel):
     id: Optional[str] = None
     embedding: Optional[List[float]] = None
@@ -21,28 +34,36 @@ class IndexRequest(BaseModel):
     fts: bool = True
     fuzzy: bool = False
 
+
 class SearchRequest(BaseModel):
     vector: List[float]
     top_k: int = 10
 
+
 class MatchRequest(BaseModel):
     query: str
     on: Optional[List[str]] = None
     top_k: int = 10
     fuzziness: int = 0
 
+
 class ConnectRequest(BaseModel):
     source_id: str
     target_id: str
     label: str
     metadata: Optional[dict] = None
 
+
 class WalkRequest(BaseModel):
     labels: List[str]
     depth: int
     direction: WalkDirection = WalkDirection.OUTGOING
 
 
+class CountResponse(BaseModel):
+    count: int
+
+
 def build(db: BeaverDB) -> FastAPI:
     """Constructs a FastAPI instance for a given BeaverDB."""
     app = FastAPI(title="BeaverDB Server")
@@ -55,7 +76,9 @@ def build(db: BeaverDB) -> FastAPI:
         d = db.dict(name)
         value = d.get(key)
         if value is None:
-            raise HTTPException(status_code=404, detail=f"Key '{key}' not found in dictionary '{name}'")
+            raise HTTPException(
+                status_code=404, detail=f"Key '{key}' not found in dictionary '{name}'"
+            )
         return value
 
     @app.put("/dicts/{name}/{key}", tags=["Dicts"])
@@ -73,8 +96,15 @@ def build(db: BeaverDB) -> FastAPI:
             del d[key]
             return {"status": "ok"}
         except KeyError:
-            raise HTTPException(status_code=404, detail=f"Key '{key}' not found in dictionary '{name}'")
+            raise HTTPException(
+                status_code=404, detail=f"Key '{key}' not found in dictionary '{name}'"
+            )
 
+    @app.get("/dicts/{name}/count", tags=["Dicts"], response_model=CountResponse)
+    def get_dict_count(name: str) -> dict:
+        """Retrieves the number of key-value pairs in the dictionary."""
+        d = db.dict(name)
+        return {"count": len(d)}
 
     # --- Lists Endpoints ---
 
@@ -91,7 +121,9 @@ def build(db: BeaverDB) -> FastAPI:
         try:
             return l[index]
         except IndexError:
-            raise HTTPException(status_code=404, detail=f"Index {index} out of bounds for list '{name}'")
+            raise HTTPException(
+                status_code=404, detail=f"Index {index} out of bounds for list '{name}'"
+            )
 
     @app.post("/lists/{name}", tags=["Lists"])
     def push_list_item(name: str, value: Any = Body(...)):
@@ -108,7 +140,9 @@ def build(db: BeaverDB) -> FastAPI:
             l[index] = value
             return {"status": "ok"}
         except IndexError:
-            raise HTTPException(status_code=404, detail=f"Index {index} out of bounds for list '{name}'")
+            raise HTTPException(
+                status_code=404, detail=f"Index {index} out of bounds for list '{name}'"
+            )
 
     @app.delete("/lists/{name}/{index}", tags=["Lists"])
     def delete_list_item(name: str, index: int):
@@ -118,7 +152,15 @@ def build(db: BeaverDB) -> FastAPI:
             del l[index]
             return {"status": "ok"}
         except IndexError:
-            raise HTTPException(status_code=404, detail=f"Index {index} out of bounds for list '{name}'")
+            raise HTTPException(
+                status_code=404, detail=f"Index {index} out of bounds for list '{name}'"
+            )
+
+    @app.get("/lists/{name}/count", tags=["Lists"], response_model=CountResponse)
+    def get_list_count(name: str) -> dict:
+        """Retrieves the number of items in the list."""
+        l = db.list(name)
+        return {"count": len(l)}
 
     # --- Queues Endpoints ---
 
@@ -149,11 +191,19 @@ def build(db: BeaverDB) -> FastAPI:
             item = q.get(block=True, timeout=timeout)
             return item
         except TimeoutError:
-            raise HTTPException(status_code=408, detail=f"Request timed out after {timeout}s waiting for an item in queue '{name}'")
+            raise HTTPException(
+                status_code=408,
+                detail=f"Request timed out after {timeout}s waiting for an item in queue '{name}'",
+            )
         except IndexError:
             # This case is less likely with block=True but good to handle
             raise HTTPException(status_code=404, detail=f"Queue '{name}' is empty")
 
+    @app.get("/queues/{name}/count", tags=["Queues"], response_model=CountResponse)
+    def get_queue_count(name: str) -> dict:
+        """RetrieVIes the number of items currently in the queue."""
+        q = db.queue(name)
+        return {"count": len(q)}
 
     # --- Blobs Endpoints ---
 
@@ -163,12 +213,20 @@ def build(db: BeaverDB) -> FastAPI:
         blobs = db.blobs(name)
         blob = blobs.get(key)
         if blob is None:
-            raise HTTPException(status_code=404, detail=f"Blob with key '{key}' not found in store '{name}'")
+            raise HTTPException(
+                status_code=404,
+                detail=f"Blob with key '{key}' not found in store '{name}'",
+            )
         # Return the raw bytes with a generic binary content type
         return Response(content=blob.data, media_type="application/octet-stream")
 
     @app.put("/blobs/{name}/{key}", tags=["Blobs"])
-    async def put_blob(name: str, key: str, data: UploadFile = File(...), metadata: Optional[str] = Form(None)):
+    async def put_blob(
+        name: str,
+        key: str,
+        data: UploadFile = File(...),
+        metadata: Optional[str] = Form(None),
+    ):
         """Stores a blob (binary file) with optional JSON metadata."""
         blobs = db.blobs(name)
         file_bytes = await data.read()
@@ -178,7 +236,9 @@ def build(db: BeaverDB) -> FastAPI:
             try:
                 meta_dict = json.loads(metadata)
             except json.JSONDecodeError:
-                raise HTTPException(status_code=400, detail="Invalid JSON format for metadata.")
+                raise HTTPException(
+                    status_code=400, detail="Invalid JSON format for metadata."
+                )
 
         blobs.put(key=key, data=file_bytes, metadata=meta_dict)
         return {"status": "ok"}
@@ -191,8 +251,16 @@ def build(db: BeaverDB) -> FastAPI:
             blobs.delete(key)
             return {"status": "ok"}
         except KeyError:
-            raise HTTPException(status_code=404, detail=f"Blob with key '{key}' not found in store '{name}'")
+            raise HTTPException(
+                status_code=404,
+                detail=f"Blob with key '{key}' not found in store '{name}'",
+            )
 
+    @app.get("/blobs/{name}/count", tags=["Blobs"], response_model=CountResponse)
+    def get_blob_count(name: str) -> dict:
+        """Retrieves the number of blobs in the store."""
+        b = db.blobs(name)
+        return {"count": len(b)}
 
     # --- Logs Endpoints ---
 
@@ -208,12 +276,25 @@ def build(db: BeaverDB) -> FastAPI:
         """Retrieves log entries within a specific time window."""
         log = db.log(name)
         # Ensure datetimes are timezone-aware (UTC) for correct comparison
-        start_utc = start.astimezone(timezone.utc) if start.tzinfo else start.replace(tzinfo=timezone.utc)
-        end_utc = end.astimezone(timezone.utc) if end.tzinfo else end.replace(tzinfo=timezone.utc)
+        start_utc = (
+            start.astimezone(timezone.utc)
+            if start.tzinfo
+            else start.replace(tzinfo=timezone.utc)
+        )
+        end_utc = (
+            end.astimezone(timezone.utc)
+            if end.tzinfo
+            else end.replace(tzinfo=timezone.utc)
+        )
         return log.range(start=start_utc, end=end_utc)
 
     @app.websocket("/logs/{name}/live", name="Logs")
-    async def live_log_feed(websocket: WebSocket, name: str, window_seconds: int = 5, period_seconds: int = 1):
+    async def live_log_feed(
+        websocket: WebSocket,
+        name: str,
+        window_seconds: int = 5,
+        period_seconds: int = 1,
+    ):
         """Streams live, aggregated log data over a WebSocket."""
         await websocket.accept()
 
@@ -222,7 +303,10 @@ def build(db: BeaverDB) -> FastAPI:
         # This simple aggregator function runs in the background and returns a
         # JSON-serializable summary of the data in the current window.
         def simple_aggregator(window):
-            return {"count": len(window), "latest_timestamp": window[-1]["timestamp"] if window else None}
+            return {
+                "count": len(window),
+                "latest_timestamp": window[-1]["timestamp"] if window else None,
+            }
 
         live_stream = async_logs.live(
             window=timedelta(seconds=window_seconds),
@@ -239,7 +323,6 @@ def build(db: BeaverDB) -> FastAPI:
             # Cleanly close the underlying iterator and its background thread.
             live_stream.close()
 
-
     # --- Channels Endpoints ---
 
     @app.post("/channels/{name}/publish", tags=["Channels"])
@@ -263,7 +346,6 @@ def build(db: BeaverDB) -> FastAPI:
         except WebSocketDisconnect:
             print(f"Client disconnected from channel '{name}' subscription.")
 
-
     # --- Collections Endpoints ---
 
     @app.get("/collections/{name}", tags=["Collections"])
@@ -282,7 +364,10 @@ def build(db: BeaverDB) -> FastAPI:
             return {"status": "ok", "id": doc.id}
         except TypeError as e:
             if "vector" in str(e):
-                raise HTTPException(status_code=501, detail="Vector indexing requires the '[vector]' extra. Install with: pip install \"beaver-db[vector]\"")
+                raise HTTPException(
+                    status_code=501,
+                    detail="Vector indexing requires the '[vector]' extra. Install with: pip install \"beaver-db[vector]\"",
+                )
             raise e
 
     @app.post("/collections/{name}/search", tags=["Collections"])
@@ -291,18 +376,29 @@ def build(db: BeaverDB) -> FastAPI:
         collection = db.collection(name)
         try:
             results = collection.search(vector=req.vector, top_k=req.top_k)
-            return [{"document": doc.to_dict(metadata_only=False), "distance": dist} for doc, dist in results]
+            return [
+                {"document": doc.to_dict(metadata_only=False), "distance": dist}
+                for doc, dist in results
+            ]
         except TypeError as e:
             if "vector" in str(e):
-                raise HTTPException(status_code=501, detail="Vector search requires the '[vector]' extra. Install with: pip install \"beaver-db[vector]\"")
+                raise HTTPException(
+                    status_code=501,
+                    detail="Vector search requires the '[vector]' extra. Install with: pip install \"beaver-db[vector]\"",
+                )
             raise e
 
     @app.post("/collections/{name}/match", tags=["Collections"])
     def match_collection(name: str, req: MatchRequest) -> List[dict]:
         """Performs a full-text or fuzzy search on the collection."""
         collection = db.collection(name)
-        results = collection.match(query=req.query, on=req.on, top_k=req.top_k, fuzziness=req.fuzziness)
-        return [{"document": doc.to_dict(metadata_only=False), "score": score} for doc, score in results]
+        results = collection.match(
+            query=req.query, on=req.on, top_k=req.top_k, fuzziness=req.fuzziness
+        )
+        return [
+            {"document": doc.to_dict(metadata_only=False), "score": score}
+            for doc, score in results
+        ]
 
     @app.post("/collections/{name}/connect", tags=["Collections"])
     def connect_documents(name: str, req: ConnectRequest):
@@ -310,11 +406,15 @@ def build(db: BeaverDB) -> FastAPI:
         collection = db.collection(name)
         source_doc = Document(id=req.source_id)
         target_doc = Document(id=req.target_id)
-        collection.connect(source=source_doc, target=target_doc, label=req.label, metadata=req.metadata)
+        collection.connect(
+            source=source_doc, target=target_doc, label=req.label, metadata=req.metadata
+        )
         return {"status": "ok"}
 
     @app.get("/collections/{name}/{doc_id}/neighbors", tags=["Collections"])
-    def get_neighbors(name: str, doc_id: str, label: Optional[str] = None) -> List[dict]:
+    def get_neighbors(
+        name: str, doc_id: str, label: Optional[str] = None
+    ) -> List[dict]:
         """Retrieves the neighboring documents for a given document."""
         collection = db.collection(name)
         doc = Document(id=doc_id)
@@ -326,9 +426,22 @@ def build(db: BeaverDB) -> FastAPI:
         """Performs a graph traversal (BFS) from a starting document."""
         collection = db.collection(name)
         source_doc = Document(id=doc_id)
-        results = collection.walk(source=source_doc, labels=req.labels, depth=req.depth, direction=req.direction)
+        results = collection.walk(
+            source=source_doc,
+            labels=req.labels,
+            depth=req.depth,
+            direction=req.direction,
+        )
         return [doc.to_dict(metadata_only=False) for doc in results]
 
+    @app.get(
+        "/collections/{name}/count", tags=["Collections"], response_model=CountResponse
+    )
+    def get_collection_count(name: str) -> dict:
+        """RetrieRetrieves the number of documents in the collection."""
+        c = db.collection(name)
+        return {"count": len(c)}
+
     return app
 
 

{beaver_db-0.18.6.dist-info → beaver_db-0.19.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: beaver-db
-Version: 0.18.6
+Version: 0.19.2
 Summary: Fast, embedded, and multi-modal DB based on SQLite for AI-powered applications.
 License-File: LICENSE
 Classifier: License :: OSI Approved :: MIT License
@@ -23,7 +23,11 @@ Provides-Extra: vector
 Requires-Dist: faiss-cpu>=1.12.0; extra == 'vector'
 Description-Content-Type: text/markdown
 
-# beaver 🦫
+<div style="text-align: center;">
+  <img src="https://github.com/syalia-srl/beaver/blob/main/logo.png?raw=true" width="256px">
+</div>
+
+---
 
 <!-- Project badges -->
 ![PyPI - Version](https://img.shields.io/pypi/v/beaver-db)
@@ -32,11 +36,13 @@ Description-Content-Type: text/markdown
 ![PyPi - Downloads (Monthly)](https://img.shields.io/pypi/dm/beaver-db)
 ![Github - Commits](https://img.shields.io/github/commit-activity/m/apiad/beaver)
 
-A fast, single-file, multi-modal database for Python, built with the standard `sqlite3` library.
+> A fast, single-file, multi-modal database for Python, built with the standard `sqlite3` library.
+
+---
 
 `beaver` is the **B**ackend for **E**mbedded, **A**ll-in-one **V**ector, **E**ntity, and **R**elationship storage. It's a simple, local, and embedded database designed to manage complex, modern data types without requiring a database server, built on top of SQLite.
 
-> If you like beaver's minimalist, no-bullshit philosophy, check out [castor](https://github.com/apiad/castor) for an equally minimalistic approach to task orchestration.
+> If you like beaver's minimalist, no-bullshit philosophy, check out [castor](https://github.com/apiad/castor "null") for an equally minimalistic approach to task orchestration.
 
 ## Design Philosophy
 
@@ -55,6 +61,7 @@ A fast, single-file, multi-modal database for Python, built with the standard `s
 - **Namespaced Key-Value Dictionaries**: A Pythonic, dictionary-like interface for storing any JSON-serializable object within separate namespaces with optional TTL for cache implementations.
 - **Pythonic List Management**: A fluent, Redis-like interface for managing persistent, ordered lists.
 - **Persistent Priority Queue**: A high-performance, persistent priority queue perfect for task orchestration across multiple processes. Also with optional async support.
+- **Inter-Process Locking**: A robust, deadlock-proof, and fair (FIFO) distributed lock (`db.lock()`) to coordinate multiple processes and prevent race conditions.
 - **Time-Indexed Log for Monitoring**: A specialized data structure for structured, time-series logs. Query historical data by time range or create a live, aggregated view of the most recent events for real-time dashboards.
 - **Simple Blob Storage**: A dictionary-like interface for storing medium-sized binary files (like PDFs or images) directly in the database, ensuring transactional integrity with your other data.
 - **High-Performance Vector Storage & Search (Optional)**: Store vector embeddings and perform fast approximate nearest neighbor searches using a `faiss`-based hybrid index.
@@ -103,14 +110,14 @@ pip install "beaver-db[full]"
 ```
 
 ### Running with Docker
+
 For a fully embedded and lightweight solution, you can run the BeaverDB REST API server using Docker. This is the easiest way to get a self-hosted instance up and running.
 
 ```bash
 docker run -p 8000:8000 -v $(pwd)/data:/app apiad/beaverdb
 ```
 
-This command will start the BeaverDB server, and your database file will be stored in the data directory on your host machine. You can access the API at <http://localhost:8000>.
-
+This command will start the BeaverDB server, and your database file will be stored in the data directory on your host machine. You can access the API at [http://localhost:8000](http://localhost:8000").
 
 ## Quickstart
 
@@ -172,12 +179,12 @@ Here are a couple of examples using `curl`:
 
 ```bash
 # Set a value in the 'app_config' dictionary
-curl -X PUT http://127.0.0.1:8000/dicts/app_config/api_key
+curl -X PUT [http://127.0.0.1:8000/dicts/app_config/api_key](http://127.0.0.1:8000/dicts/app_config/api_key)
      -H "Content-Type: application/json"
      -d '"your-secret-api-key"'
 
 # Get the value back
-curl http://127.0.0.1:8000/dicts/app_config/api_key
+curl [http://127.0.0.1:8000/dicts/app_config/api_key](http://127.0.0.1:8000/dicts/app_config/api_key)
 # Output: "your-secret-api-key"
 ```
 
@@ -341,6 +348,34 @@ for summary in live_summary:
     print(f"Live Stats (10s window): Count={summary['count']}, Mean={summary['mean']:.2f}")
 ```
 
+### 9. Coordinate Distributed Web Scrapers
+
+Run multiple scraper processes in parallel and use `db.lock()` to coordinate them. You can ensure only one process refreshes a shared API token or sitemap, preventing race conditions and rate-limiting.
+
+```python
+import time
+
+scrapers_state = db.dict("scraper_state")
+
+last_refresh = scrapers_state.get("last_sitemap_refresh", 0)
+if time.time() - last_refresh > 3600: # Only refresh once per hour
+    try:
+        # Try to get a lock to refresh the shared sitemap, but don't wait long
+        with db.lock("refresh_sitemap", timeout=1):
+            # We got the lock. Check if it's time to refresh.
+            print(f"PID {os.getpid()} is refreshing the sitemap...")
+            scrapers_state["sitemap"] = ["/page1", "/page2"] # Your fetch_sitemap()
+            scrapers_state["last_sitemap_refresh"] = time.time()
+
+    except TimeoutError:
+        # Another process is already refreshing, so we can skip
+        print(f"PID {os.getpid()} letting other process handle refresh.")
+
+# All processes can now safely use the shared sitemap
+sitemap = scrapers_state.get("sitemap")
+# ... proceed with scraping ...
+```
+
 ## Type-Safe Data Models
 
 For enhanced data integrity and a better developer experience, BeaverDB supports type-safe operations for all modalities. By associating a model with these data structures, you get automatic serialization and deserialization, complete with autocompletion in your editor.
@@ -348,7 +383,6 @@ For enhanced data integrity and a better developer experience, BeaverDB supports
 This feature is designed to be flexible and works seamlessly with two kinds of models:
 
 - **Pydantic Models**: If you're already using Pydantic, your `BaseModel` classes will work out of the box.
-
 - **Lightweight `beaver.Model`**: For a zero-dependency solution, you can inherit from the built-in `beaver.Model` class, which is a standard Python class with serialization methods automatically included.
 
 
@@ -393,10 +427,11 @@ For more in-depth examples, check out the scripts in the `examples/` directory:
 - [`graph.py`](examples/graph.py): Shows how to create relationships between documents and perform multi-hop graph traversals.
 - [`kvstore.py`](examples/kvstore.py): A comprehensive demo of the namespaced dictionary feature.
 - [`list.py`](examples/list.py): Shows the full capabilities of the persistent list, including slicing and in-place updates.
+- [`locks.py`](examples/lock_test.py): Demonstrates how to use the inter-process lock to create critical sections.
 - [`logs.py`](examples/logs.py): A short example showing how to build a realtime dashboard with the logging feature.
 - [`pqueue.py`](examples/pqueue.py): A practical example of using the persistent priority queue for task management.
 - [`producer_consumer.py`](examples/producer_consumer.py): A demonstration of the distributed task queue system in a multi-process environment.
-- [`publisher.py`](examples/publisher.p) and [`subscriber.py`](examples/subscriber.py): A pair of examples demonstrating inter-process message passing with the publish/subscribe system.
+- [`publisher.py`](examples/publisher.py) and [`subscriber.py`](examples/subscriber.py): A pair of examples demonstrating inter-process message passing with the publish/subscribe system.
 - [`pubsub.py`](examples/pubsub.py): A demonstration of the synchronous, thread-safe publish/subscribe system in a single process.
 - [`rerank.py`](examples/rerank.py): Shows how to combine results from vector and text search for more refined results.
 - [`stress_vectors.py`](examples/stress_vectors.py): A stress test for the vector search functionality.
@@ -410,14 +445,13 @@ For more in-depth examples, check out the scripts in the `examples/` directory:
 
 These are some of the features and improvements planned for future releases:
 
-- **Async API**: Extend the async support with on-demand wrappers for all features besides channels.
-- **Type-Safe Models**: Enhance built-in `Model` to handle recursive and embedded types.
-- **Drop-in REST Client**: Implement a `BeaverClient` class that acts as a drop-in replacement for `BeaverDB` but instead of a local database file, it works against a REST API server.
+- **[Issue #2](https://github.com/syalia-srl/beaver/issues/2) Comprehensive async wrappers**: Extend the async support with on-demand wrappers for all data structures, not just channels.
+- **[Issue #9](https://github.com/syalia-srl/beaver/issues/2) Type-safe wrappers based on Pydantic-compatible models**: Enhance the built-in `Model` to handle recursive and embedded types and provide Pydantic compatibility.
+- **[Issue #6](https://github.com/syalia-srl/beaver/issues/2) Drop-in replacement for Beaver REST server client**: Implement a `BeaverClient` class that acts as a drop-in replacement for `BeaverDB` but works against the REST API server.
+- **[Issue #7](https://github.com/syalia-srl/beaver/issues/2) Replace `faiss` with simpler, linear `numpy` vectorial search**: Investigate removing the heavy `faiss` dependency in favor of a pure `numpy` implementation to improve installation simplicity, accepting a trade-off in search performance for O(1) installation.
 
-Check out the [roadmap](roadmap.md) for a detailed list of upcoming features and design ideas.
 
 If you think of something that would make `beaver` more useful for your use case, please open an issue and/or submit a pull request.
-
 ## License
 
 This project is licensed under the MIT License.

{beaver_db-0.18.6.dist-info → beaver_db-0.19.2.dist-info}/RECORD

@@ -1,18 +1,19 @@
-beaver/__init__.py,sha256=jeTzeVn_M64ZYQyO3f62tBlLi427gv_8jwVxDGbbzvg,125
-beaver/blobs.py,sha256=YkIEskHD6oHRaJTF0P25HrTT8LqM-REyV_UBPVQxeqQ,4055
+beaver/__init__.py,sha256=HjTNjk3x58Pw9Iv_eAPVL088wDVEua-JEgecZ28NgMc,125
+beaver/blobs.py,sha256=U5n6NLRQGAzsePGR2SJPRXHy22K8T9cJVMIb0JGzsY0,4399
 beaver/channels.py,sha256=kIuwKMDBdDQObaKT23znsMXzfpKfE7pXSxvf-u4LlpY,9554
 beaver/cli.py,sha256=Sxm-mYU3LGd4tIqw-5LHb0ektWebjV9vn51hm-CMJD0,2232
 beaver/collections.py,sha256=UAQAuRxJRCqY5PHfxJNm3CdKqMNuyY8DOLdodvY6jpk,26107
-beaver/core.py,sha256=d37hnD1xaYdZFKf1z0sDAoGwYwuPU8ETrOotso7aHfk,15209
+beaver/core.py,sha256=JRkRvc0Sb3FT9KlR3YbmiPcqCQ686dFKmHSNZ_UJ_aE,17100
 beaver/dicts.py,sha256=Xp8lPfQt08O8zCbptQLWQLO79OxG6uAVER6ryj3SScQ,5495
 beaver/lists.py,sha256=rfJ8uTNLkMREYc0uGx0z1VKt2m3eR9hvbdvDD58EbmQ,10140
+beaver/locks.py,sha256=GWDSRkPw2lrAQfXIRqvkc5PK9zZ2eLYWKTuzHTs9j_A,6321
 beaver/logs.py,sha256=a5xenwl5NZeegIU0dWVEs67lvaHzzw-JRAZtEzNNO3E,9529
 beaver/queues.py,sha256=Fr3oie63EtceSoiC8EOEDSLu1tDI8q2MYLXd8MEeC3g,6476
-beaver/server.py,sha256=WoNcPXU9oh6hcHtb60IbEk5DfZT5J4Fb-yubJE3YLIc,13642
+beaver/server.py,sha256=At3BoEV7JfpYjNtyHMdPUF8shj4V4D5nStXWb6Bv53A,15947
 beaver/types.py,sha256=m0ohT7A8r0Y1a7bJEx4VanLaOUWU2VYxaLHPsVPjrIw,1651
 beaver/vectors.py,sha256=EGZf1s364-rMubxkYoTcjBl72lRRxM1cUwypjsoC6ec,18499
-beaver_db-0.18.6.dist-info/METADATA,sha256=jwuZKs1NM14M9Q6aMYoKutgTUCkBKlc8OmAZeUaZvQs,21232
-beaver_db-0.18.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-beaver_db-0.18.6.dist-info/entry_points.txt,sha256=bd5E2s45PoBdtdR9-ToKSdLNhmHp8naV1lWP5mOzlrc,42
-beaver_db-0.18.6.dist-info/licenses/LICENSE,sha256=1xrIY5JnMk_QDQzsqmVzPIIyCgZAkWCC8kF2Ddo1UT0,1071
-beaver_db-0.18.6.dist-info/RECORD,,
+beaver_db-0.19.2.dist-info/METADATA,sha256=Iec3mTpq384nkp_R8fD2AGjXHRzarA93uxL623ZtyVE,23431
+beaver_db-0.19.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+beaver_db-0.19.2.dist-info/entry_points.txt,sha256=bd5E2s45PoBdtdR9-ToKSdLNhmHp8naV1lWP5mOzlrc,42
+beaver_db-0.19.2.dist-info/licenses/LICENSE,sha256=1xrIY5JnMk_QDQzsqmVzPIIyCgZAkWCC8kF2Ddo1UT0,1071
+beaver_db-0.19.2.dist-info/RECORD,,