fastcache-ai 1.1.0__tar.gz

fastcache_ai-1.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

fastcache_ai-1.1.0/PKG-INFO

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: fastcache-ai
+Version: 1.1.0
+Summary: Zero-infrastructure, off-heap, virtual-threaded cache for AI workloads
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/adi407/fast_cache
+Project-URL: Repository, https://github.com/adi407/fast_cache
+Project-URL: Issues, https://github.com/adi407/fast_cache/issues
+Keywords: cache,llm,embeddings,sidecar,off-heap
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: fast
+Requires-Dist: zstandard>=0.21; extra == "fast"
+Requires-Dist: msgpack>=1.0; extra == "fast"
+Provides-Extra: numpy
+Requires-Dist: numpy>=1.23; extra == "numpy"
+Provides-Extra: jre
+Requires-Dist: jdk4py>=21; extra == "jre"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: numpy>=1.23; extra == "dev"
+Requires-Dist: msgpack>=1.0; extra == "dev"
+Requires-Dist: zstandard>=0.21; extra == "dev"
+Dynamic: license-file
+
+# fastcache-ai
+
+**A cache for AI workloads that needs no infrastructure.** No Redis, no Docker, no connection string.
+
+```bash
+pip install fastcache-ai
+```
+
+```python
+from fastcache_ai import fastcache
+
+@fastcache(ttl="15m")
+def embed(prompt: str):
+    return model.encode(prompt)
+```
+
+That is the entire setup. On first use the library finds or boots a Java engine process, reuses it across
+runs, and reaps it if your process dies. A JDK 21+ runtime is required; `pip install "fastcache-ai[jre]"`
+bundles one if you do not have it.
+
+> **The import name is `fastcache_ai`, not `fastcache`.** The bare name on PyPI belongs to an unrelated
+> C implementation of `functools.lru_cache`; sharing it would make the two packages overwrite each other.
+
+## Why it exists
+
+Caching an LLM response should be a one-line change. Instead it usually means standing up Redis, choosing a
+serialization format, and then discovering that a 50 MB context window on the JVM heap causes GC pauses
+costing more than the cache saves. FastCache stores payloads **off-heap**, invisible to the garbage
+collector, and hands you two front doors onto the same engine: this decorator, and a Spring Boot
+annotation for JVM services.
+
+## What you get
+
+- **Off-heap storage** sized for 20–50 MB context windows and vector matrices
+- **Hot-key L1 cache** — a celebrity prompt hit thousands of times per second collapses to one network
+  round trip every few seconds
+- **Stampede protection** — when a hot key expires under concurrency, exactly one caller recomputes and
+  everyone else is served the still-valid previous value
+- **A management console** on `http://127.0.0.1:8081/dashboard` with live memory, hit rate and an
+  estimated-savings figure
+- **Fail-open** — if the engine is unreachable, your function simply runs
+
+```python
+import fastcache_ai as fc
+
+fc.dashboard(open_browser=True)   # live console
+fc.stats()                        # engine, L1 and client telemetry
+fc.info()                         # everything needed to diagnose a problem
+```
+
+## Configuration
+
+Zero configuration is a supported configuration. Common overrides:
+
+| Variable | Purpose | Default |
+|---|---|---|
+| `FASTCACHE_OFFHEAP_MAX` | Native memory budget | `2g` |
+| `FASTCACHE_DEFAULT_TTL` | TTL when the decorator omits one | `15m` |
+| `FASTCACHE_METRICS_PORT` | Console port (`off` disables) | `8081` |
+| `FASTCACHE_L1_TTL` | Local hot-key cache window, seconds | `5.0` |
+| `FASTCACHE_HEARTBEAT_TIMEOUT` | Orphan-reaping window (`0` disables) | `40s` |
+
+## Status
+
+Pre-release. Single-node, non-durable and unauthenticated — it binds to loopback and is not a replacement
+for Redis where you need replication, failover or persistence.
+
+Full documentation, design notes and source:
+**[github.com/adi407/fast_cache](https://github.com/adi407/fast_cache)**
+
+Apache 2.0 licensed.

fastcache_ai-1.1.0/README.md

@@ -0,0 +1,71 @@
+# fastcache-ai
+
+**A cache for AI workloads that needs no infrastructure.** No Redis, no Docker, no connection string.
+
+```bash
+pip install fastcache-ai
+```
+
+```python
+from fastcache_ai import fastcache
+
+@fastcache(ttl="15m")
+def embed(prompt: str):
+    return model.encode(prompt)
+```
+
+That is the entire setup. On first use the library finds or boots a Java engine process, reuses it across
+runs, and reaps it if your process dies. A JDK 21+ runtime is required; `pip install "fastcache-ai[jre]"`
+bundles one if you do not have it.
+
+> **The import name is `fastcache_ai`, not `fastcache`.** The bare name on PyPI belongs to an unrelated
+> C implementation of `functools.lru_cache`; sharing it would make the two packages overwrite each other.
+
+## Why it exists
+
+Caching an LLM response should be a one-line change. Instead it usually means standing up Redis, choosing a
+serialization format, and then discovering that a 50 MB context window on the JVM heap causes GC pauses
+costing more than the cache saves. FastCache stores payloads **off-heap**, invisible to the garbage
+collector, and hands you two front doors onto the same engine: this decorator, and a Spring Boot
+annotation for JVM services.
+
+## What you get
+
+- **Off-heap storage** sized for 20–50 MB context windows and vector matrices
+- **Hot-key L1 cache** — a celebrity prompt hit thousands of times per second collapses to one network
+  round trip every few seconds
+- **Stampede protection** — when a hot key expires under concurrency, exactly one caller recomputes and
+  everyone else is served the still-valid previous value
+- **A management console** on `http://127.0.0.1:8081/dashboard` with live memory, hit rate and an
+  estimated-savings figure
+- **Fail-open** — if the engine is unreachable, your function simply runs
+
+```python
+import fastcache_ai as fc
+
+fc.dashboard(open_browser=True)   # live console
+fc.stats()                        # engine, L1 and client telemetry
+fc.info()                         # everything needed to diagnose a problem
+```
+
+## Configuration
+
+Zero configuration is a supported configuration. Common overrides:
+
+| Variable | Purpose | Default |
+|---|---|---|
+| `FASTCACHE_OFFHEAP_MAX` | Native memory budget | `2g` |
+| `FASTCACHE_DEFAULT_TTL` | TTL when the decorator omits one | `15m` |
+| `FASTCACHE_METRICS_PORT` | Console port (`off` disables) | `8081` |
+| `FASTCACHE_L1_TTL` | Local hot-key cache window, seconds | `5.0` |
+| `FASTCACHE_HEARTBEAT_TIMEOUT` | Orphan-reaping window (`0` disables) | `40s` |
+
+## Status
+
+Pre-release. Single-node, non-durable and unauthenticated — it binds to loopback and is not a replacement
+for Redis where you need replication, failover or persistence.
+
+Full documentation, design notes and source:
+**[github.com/adi407/fast_cache](https://github.com/adi407/fast_cache)**
+
+Apache 2.0 licensed.

fastcache_ai-1.1.0/fastcache_ai/__init__.py

@@ -0,0 +1,191 @@
+"""FastCache — a zero-infrastructure cache for AI workloads.
+
+Installed as ``fastcache-ai``, imported as ``fastcache_ai``. The import name carries the suffix
+because the bare ``fastcache`` name on PyPI already belongs to an unrelated C implementation of
+``functools.lru_cache``; sharing it would make the two packages overwrite each other on disk.
+
+.. code-block:: python
+
+    from fastcache_ai import fastcache
+
+    @fastcache(ttl="15m")
+    def embed(prompt: str):
+        return model.encode(prompt)
+
+Importing this package starts a background thread that locates or boots the Java engine. The import itself
+never blocks and never raises: if no JVM can be found, the decorator degrades to calling your function, and
+the reason is available from :func:`info`.
+
+Set ``FASTCACHE_AUTOSTART=0`` to skip the background warm-up; the sidecar will then be started lazily on
+first cache use instead.
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+import threading
+from typing import Any, Dict, Optional
+
+from .bootstrap import console_url, ensure_sidecar, shutdown_sidecar
+from .client import FastCacheClient
+from .codec import Codec, describe_capabilities
+from .decorator import build_key, default_client, fastcache, set_default_client, single_flight_stats
+from .errors import (
+    FastCacheError,
+    ProtocolError,
+    SerializationError,
+    SidecarStartupError,
+    SidecarUnavailable,
+    WriteRejected,
+)
+from .l1 import HotKeyCache, NullL1
+from .ttl import format_ttl, parse_ttl
+
+__version__ = "1.1.0"
+
+__all__ = [
+    "fastcache",
+    "FastCacheClient",
+    "HotKeyCache",
+    "NullL1",
+    "Codec",
+    "FastCacheError",
+    "SidecarUnavailable",
+    "SidecarStartupError",
+    "ProtocolError",
+    "WriteRejected",
+    "SerializationError",
+    "get",
+    "put",
+    "set",
+    "delete",
+    "stats",
+    "flush",
+    "ping",
+    "info",
+    "configure",
+    "ensure_sidecar",
+    "shutdown_sidecar",
+    "console_url",
+    "dashboard",
+    "single_flight_stats",
+    "default_client",
+    "set_default_client",
+    "build_key",
+    "parse_ttl",
+    "format_ttl",
+    "__version__",
+]
+
+log = logging.getLogger("fastcache")
+
+_startup_error: Optional[BaseException] = None
+_startup_thread: Optional[threading.Thread] = None
+
+
+# ---------------------------------------------------------------------------------------------------
+# Module-level convenience API
+# ---------------------------------------------------------------------------------------------------
+
+def get(key: str, default: Any = None) -> Any:
+    """Reads a value from the shared client."""
+    return default_client().get(key, default)
+
+
+def put(key: str, value: Any, ttl: Any = None) -> int:
+    """Writes a value through the shared client. Returns the wire status (0 = stored)."""
+    return default_client().put(key, value, ttl=ttl)
+
+
+#: Redis-style alias for :func:`put`.
+set = put  # noqa: A001 - shadowing the builtin is intentional and scoped to this module's namespace
+
+
+def delete(key: str) -> bool:
+    return default_client().delete(key)
+
+
+def stats() -> Dict[str, Any]:
+    """Engine, L1 and client telemetry."""
+    return default_client().stats()
+
+
+def flush() -> int:
+    """Drops every cached entry. Mostly useful between test cases."""
+    return default_client().flush()
+
+
+def ping() -> bool:
+    return default_client().ping()
+
+
+def configure(**kwargs: Any) -> FastCacheClient:
+    """Replaces the shared client with one built from ``kwargs``.
+
+    .. code-block:: python
+
+        fastcache.configure(host="10.0.0.5", port=7431, timeout=2.0)
+        fastcache.configure(l1=fastcache.NullL1())   # disable local caching entirely
+    """
+    client = FastCacheClient(**kwargs)
+    set_default_client(client)
+    return client
+
+
+def dashboard(open_browser: bool = False) -> Optional[str]:
+    """Returns the management console URL, optionally opening it.
+
+    .. code-block:: python
+
+        fastcache.dashboard(open_browser=True)   # live savings, memory and hit-rate console
+
+    Returns None when the console is disabled (``FASTCACHE_METRICS_PORT=off``) or its port was already
+    taken — the cache itself is unaffected either way.
+    """
+    ensure_sidecar()
+    url = console_url()
+    if url and open_browser:
+        import webbrowser
+
+        webbrowser.open(url)
+    return url
+
+
+def info() -> Dict[str, Any]:
+    """Everything needed to diagnose a FastCache problem in one call."""
+    from . import bootstrap
+
+    details = bootstrap.info()
+    details["version"] = __version__
+    details["codecs"] = describe_capabilities()
+    details["autostart_error"] = repr(_startup_error) if _startup_error else None
+    details["single_flight"] = single_flight_stats()
+    return details
+
+
+# ---------------------------------------------------------------------------------------------------
+# Import-time autopilot
+# ---------------------------------------------------------------------------------------------------
+
+def _autostart() -> None:
+    """Warms the sidecar in the background.
+
+    Running on a daemon thread is the point: booting a JVM takes a few hundred milliseconds, and an
+    ``import`` that blocks that long is one people work around. By the time the first cache call arrives,
+    the engine is usually already up; if it is not, the call resolves it synchronously.
+
+    Failures are recorded, never raised. A missing JDK on a developer laptop must not break
+    ``import fastcache_ai`` at the top of a training script.
+    """
+    global _startup_error
+    try:
+        ensure_sidecar()
+    except BaseException as exc:  # noqa: BLE001 - an import must not be able to fail here
+        _startup_error = exc
+        log.debug("fastcache: sidecar autostart deferred (%s)", exc)
+
+
+if os.environ.get("FASTCACHE_AUTOSTART", "1").lower() not in {"0", "false", "no"}:
+    _startup_thread = threading.Thread(target=_autostart, name="fastcache-autostart", daemon=True)
+    _startup_thread.start()