token-throttle 0.1.7__tar.gz

token_throttle-0.1.7/.gitignore

@@ -0,0 +1,177 @@
+.DS_Store
+lcov.info
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

token_throttle-0.1.7/LICENSE

@@ -0,0 +1,201 @@
+                                 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 2025 Elijas Dapšauskas
+
+   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.

token_throttle-0.1.7/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: token-throttle
+Version: 0.1.7
+Summary: Simple Multi-Resource Rate Limiting That Saves Unused Tokens. Rate limit API requests across different resources and workers without wasting your quota. Reserve tokens upfront, get refunds for what you don't use, and avoid over-limiting.
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: frozendict>=2.4.6
+Requires-Dist: pydantic>=2.11.3
+Description-Content-Type: text/markdown
+
+# token-throttle
+
+[![Status: Experimental](https://img.shields.io/badge/status-experimental-gold.svg?style=flat)](https://github.com/mkenney/software-guides/blob/master/STABILITY-BADGES.md#experimental)
+[![Maintained: yes](https://img.shields.io/badge/yes-43cd0f.svg?style=flat&label=maintained)](https://github.com/Elijas/token-throttle/issues)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-43cd0f.svg?style=flat&label=license)](LICENSE)
+<a href="https://pypi.org/project/token-throttle"><img src="https://img.shields.io/badge/v0.1.7-version?color=43cd0f&style=flat&label=pypi" alt="PyPI version" /></a>
+<a href="https://github.com/astral-sh/ruff?style=flat"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff"></a>
+
+**Simple Multi-Resource Rate Limiting That Saves Unused Tokens.**
+
+Rate limit API requests across different resources and workers without wasting your quota. Reserve tokens upfront, get refunds for what you don't use, and avoid over-limiting.
+
+- Limits requests across multiple services (like OpenAI, Anthropic)
+- Works across multiple servers/workers
+- Returns unused tokens to your quota automatically
+- Prevents hitting API rate limits while maximizing throughput
+
+Note: the API may unexpectedly change with future minor versions, therefore install with:
+
+```bash
+pip install "token-throttle[redis,tiktoken]>=0.1.7,<0.2.0"
+```
+
+Found this useful? Star the repo on GitHub to show support and follow for updates. Also, find me on Discord if you have questions or would like to join a discussion!
+
+![GitHub Repo stars](https://img.shields.io/github/stars/elijas/token-throttle?style=flat&color=fcfcfc&labelColor=white&logo=github&logoColor=black&label=stars)
+&nbsp;<a href="https://discord.gg/hCppPqm6"><img alt="Discord server invite" src="https://img.shields.io/discord/1119368998161752075?logo=discord&logoColor=white&style=flat&color=fcfcfc&labelColor=7289da" height="20"></a>
+
+### Introduction
+
+This is a tool I built as a rewrite of [openlimit](https://github.com/shobrook/openlimit/issues/20#issuecomment-2782677483) after [not finding any good Python solutions for rate limiting](https://gist.github.com/justinvanwinkle/d9f04950083c4554835c1a35f9d22dad), especially the ones that would be token-aware and had unused token refund capability.
+
+- Rate-limit multiple resources such as requests and tokens and apples and bananas at the same time
+  - This is needed because different APIs have different resource rules, e,g, Anthropic counts request and completion tokens separately.
+  - While this was originally intended for LLM APIs, it's fully customizable: you can limit bananas per 32-second-time-windows and apples per 2-minute-window simultaneously. You can also connect (through Dependency Injection) your own backend if you don't want Redis.
+- Rate-limit multiple resource consumers (such as LLM calling applications that are using the same API key and model).
+- Rate-limit same resource across multiple time-frames
+- Rate-limit each resource on it's own set of quotas
+- Reserve usage while the request is being completed, and then refund/adjust according to actual usage after the request completes
+- Refund unused resources (such as unused tokens).
+
+Treat this as an early preview (no unit tests or extensive testing) but it was stable and worked correctly for my use cases.
+
+### Illustrating use case
+
+- Imagine you have a single API key to your provider.
+- Only up to 10% of the key's throughput capacity is used by a continuously running production service.
+- You want to run a massively parallelized LLM data processing workflow with the same key.
+- But you need to do it without bringing down the production (or your workflow) with 429 Too Many Requests errors.
+- Also, leaving latency on the table is not a good solution; you want the batch results as soon as possible.
+
+> [!NOTE]
+> Note, this example uses [BAML](https://github.com/BoundaryML/baml) to call LLMs, but you can use absolutely anything, because all you need is just a way to retrieve tokens used in the request and actual tokens used in the response. Also note that (optionally) you can use already existing utilities in `token-throttle` to calculate/extract these two values automatically from OpenAI-compatible requests and responses.
+
+```python
+from baml_client import b
+from baml_py import Collector
+token_counter = Collector()
+b = b.with_options(token_counter)
+
+limiter = create_limiter([
+    # Let's say your production only uses up to 10% of
+    # Then this should be set to 90% of your capacity
+    Quota(metric="requests", limit=90_000, per_seconds=60),
+    Quota(metric="tokens", limit=90_000_000, per_seconds=60),
+], backend=redis)
+
+async def massively_parallelized():
+    input_tokens = inp_tok(await b.request.ExtractResume(...))
+    # e.g. max_tokens value of the request
+    # e.g. or 95th percentile of usual b.ExtractResume() consumption
+    output_tokens = 10_000
+
+    # Safe against race-condition and many clients
+    # because it uses Redis locks and atomic operations
+    reservation = await limiter.acquire_capacity(
+        model="gpt-4.1"
+        usage={
+            "requests": 1,
+            "tokens": input_tokens + output_tokens,
+
+            # Anthropic input and output tokens
+            # have separate rate limits:
+            #   "input_tokens": input_tokens
+            #   "output_tokens": output_tokens
+
+        },
+    )
+
+    # Request only continues here only after the capacity
+    # has been reserved to not be consumed by any other LLM calls
+    c = Collector()
+    b = b.with_options(collector=c)
+    resume = await b.ExtractResume(...)
+    actual_usage = {
+        "requests": get_total_tokens(c),
+        "tokens": 1,
+    }
+    await limiter.refund_capacity(actual_usage, reservation)
+    # Now two things happened:
+    # 1. Actual usage recorded
+    #    (e.g. got a capacity refund for unused output tokens)
+    #    (e.g. a negative refund is also possible if actual usage exceeded the expected one)
+    # 2. timestamp of the usage was moved to be the last token generated
+
+```
+
+### Features
+
+Here are the key features of `token-throttle`, explained:
+
+- **Multi-Resource Limiting:**
+
+  - Simultaneously enforce limits on multiple distinct resource types for a single operation (e.g., limit both the number of API requests _and_ the number of tokens consumed within those requests).
+  - Define simultaneous different quotas for different resources (e.g., 60 requests/minute AND 1,000 requests/day AND 1,000,000 tokens/minute).
+
+- **Accurate Capacity Management & Refunding:**
+
+  - Implements a reserve-then-adjust mechanism (`acquire_capacity` followed by `refund_capacity`).
+  - Initially reserves the maximum potential usage for an operation.
+  - Allows refunding unused capacity _or_ accounting for overuse if the actual usage differs from the reservation, ensuring limits are accurately enforced based on _actual_ consumption.
+
+- **Asyncio Native:**
+
+  - Built from the ground up using `asyncio` for non-blocking operation, ideal for high-throughput applications interacting with external APIs.
+
+- **Flexible Time Windows:**
+
+  - Define quotas over various time periods (e.g., per second, per minute, per hour, per day, or anything in-between) using the `per_seconds` parameter in `Quota`.
+  - Enforce limits across multiple windows concurrently for the same resource (e.g., limit requests per minute _and_ requests per day).
+
+- **Correctness & Atomicity:**
+
+  - Designed to avoid common race conditions found in simpler rate limiters, especially when used with distributed backends like Redis.
+  - The provided Redis backend uses locks and appropriate commands to guarantee atomic updates to capacity across multiple workers/processes.
+
+- **Pluggable Backend Architecture:**
+
+  - Core logic is separated from the storage mechanism via `RateLimiterBackend` and `RateLimiterBackendBuilderInterface` interfaces.
+  - Ships with a robust `RedisBackend` for distributed rate limiting.
+  - Allows implementing custom backends (e.g., in-memory for single process, other databases) if needed.
+
+- **Configurable Per "Model" or Endpoint:**
+
+  - Apply different sets of `UsageQuotas` to different logical entities (referred to as `model` or `model_family` internally, e.g., specific API endpoints, different LLM versions sharing a quota).
+    - i.e. This allows for gpt-4o and gpt-4o-mini automatically have separate quotas, while gpt-4o-20241203 and gpt-4o-20241024 are just aliases of each other but are counted in the same quota bucket instance (i.e. belong to the same model_family).
+  - Supports dynamic configuration lookups via a `PerModelConfigGetter` callable.
+
+- **Extensible Usage Counting:**
+
+  - Define custom logic (`UsageCounter`) to calculate the resource usage of a given request _before_ it happens (e.g., estimate token count for an LLM request based on input messages).
+
+- **Observability Hooks:**
+  - Provides callbacks (`RateLimiterCallbacks`) for monitoring key events like starting to wait for capacity, consuming capacity, refunding capacity, and detecting missing state in the backend. Includes `loguru` integration helpers.
+
+### Getting started
+
+For out of the box experience just do `limiter = create_openai_redis_rate_limiter()`, and use it as in the [example-1](https://github.com/shobrook/openlimit/issues/20#issuecomment-2782677483) or [example-2](https://gist.github.com/justinvanwinkle/d9f04950083c4554835c1a35f9d22dad). Otherwise, copy the function and customize it to your needs.