inferencefit 0.1.0__tar.gz

inferencefit-0.1.0/.gitignore

@@ -0,0 +1,222 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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/
+.env*
+!.env.example
+/.vs
+.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+.inferencefit/
+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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

inferencefit-0.1.0/CHANGELOG.md

@@ -0,0 +1,25 @@
+# Changelog
+
+All notable changes to InferenceFit are documented in this file.
+
+## 0.1.0
+
+Initial public release.
+
+- Evaluate LLM configurations against workload-specific, file-based datasets and
+  `EvaluationSpec` files.
+- Use the deterministic offline fixture provider or the non-streaming OpenAI-compatible
+  provider architecture. Fireworks and DeepSeek integrations have been validated against
+  their real APIs.
+- Score responses with declarative exact, regular-expression, enum, JSON Schema, numeric,
+  contains, and local Python validators.
+- Measure quality, cost, latency, and reliability, then apply hard constraints and expose the
+  Pareto frontier.
+- Select eligible configurations with deterministic optimization objectives, including a
+  documented balanced heuristic.
+- Produce a runtime-valid two-stage fallback cascade that reacts only to provider errors and
+  runtime-capable validation gates.
+- Persist resumable filesystem runs with provenance, observations, result summaries, and an
+  open `routing-policy.yaml` artifact.
+- Run the same benchmark core through the `inferencefit` CLI, the async Python API, or a local
+  FastAPI daemon.

inferencefit-0.1.0/LICENSE

@@ -0,0 +1,190 @@
+                                 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
+
+   Copyright 2026 Eugene Kamaev
+
+   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.

inferencefit-0.1.0/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.5
+Name: inferencefit
+Version: 0.1.0
+Summary: Local-first, workload-specific evaluation and deterministic optimization for LLM configurations.
+Project-URL: Homepage, https://github.com/Jauhenka/InferenceFit
+Project-URL: Repository, https://github.com/Jauhenka/InferenceFit
+Project-URL: Issues, https://github.com/Jauhenka/InferenceFit/issues
+Project-URL: Documentation, https://github.com/Jauhenka/InferenceFit/tree/main/docs
+Author: InferenceFit contributors
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: benchmarking,evaluation,llm,optimization,routing
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Requires-Dist: fastapi>=0.115
+Requires-Dist: httpx>=0.27
+Requires-Dist: jsonschema>=4.21
+Requires-Dist: pydantic>=2.7
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: typer>=0.12
+Requires-Dist: uvicorn>=0.30
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == 'dev'
+Requires-Dist: httpx>=0.27; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: respx>=0.21; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Requires-Dist: twine>=5.1; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# InferenceFit
+
+InferenceFit is a local-first toolkit for evaluating and selecting LLM configurations for a
+specific workload. Instead of asking which model is universally "best," it runs your versioned
+test cases against candidate providers and models, measures quality, reliability, latency, token
+use, and cost, applies your hard constraints, and produces a deterministic recommendation and an
+open routing policy.
+
+InferenceFit 0.1.0 is a pre-1.0 release. Public APIs and serialized schemas may change before 1.0.
+
+## Installation
+
+InferenceFit requires Python 3.11 or newer.
+
+```bash
+pip install inferencefit
+```
+
+## Offline quick start
+
+The repository includes a deterministic fixture workload that needs no API key and makes no
+network requests. From a source checkout, run:
+
+```bash
+inferencefit validate examples/basic/eval.yaml
+inferencefit benchmark examples/basic/eval.yaml
+```
+
+The example compares two fixtures and evaluates a schema-gated fallback cascade. The benchmark
+prints the run ID, recommendation, and artifact directory under `.inferencefit/runs/`.
+
+The same benchmark entry point is available from Python:
+
+```python
+import asyncio
+
+from inferencefit import benchmark
+
+result = asyncio.run(benchmark("examples/basic/eval.yaml"))
+print(result.recommendation)
+```
+
+## Opt-in provider examples
+
+Live examples are intentionally separate from the offline quick start. They make network requests
+and can spend provider credits. Set the named environment variable in your shell, then explicitly
+run the corresponding smoke spec:
+
+```bash
+# Requires FIREWORKS_API_KEY
+inferencefit benchmark examples/lead_semantic_units/eval.fireworks.smoke.yaml
+
+# Requires DEEPSEEK_API_KEY
+inferencefit benchmark examples/lead_semantic_units/eval.deepseek.smoke.yaml
+```
+
+These specs use synthetic lead-extraction cases. See the
+[example guide](examples/lead_semantic_units/README.md) and the
+[E0.5 validation report](docs/e0.5-real-world-validation.md) for their contract, pricing snapshots,
+and observed results.
+
+## How evaluation works
+
+An `EvaluationSpec` YAML file connects a JSONL dataset to candidates, validators, hard constraints,
+an optimization objective, and bounded execution settings. Candidate pricing is an explicit
+snapshot in USD per million input and output tokens; InferenceFit does not fetch prices.
+
+Built-in validators cover exact values, regular expressions, enums, JSON Schema, numeric values,
+containment, and local Python callables. Exact, numeric, and Python validators can use hidden
+evaluation answers and are evaluation-only. Runtime routing gates must use runtime-capable checks,
+such as JSON Schema. Local Python validators execute with the current process permissions and are
+not sandboxed, so do not run untrusted validator code.
+
+Each candidate is summarized with end-to-end success, provider reliability, p50/p95 latency,
+input/output tokens, and configured cost. Hard constraints can exclude configurations by success,
+error rate, latency, or cost. Remaining candidates appear on a Pareto frontier and are ranked by
+`min_cost`, `min_latency`, `max_quality`, `max_reliability`, or the versioned `balanced` objective.
+
+E0 also simulates one two-stage cascade. Fallback occurs only after a provider error or failure of a
+runtime-capable routing gate; hidden expected answers are never production routing signals. If no
+configuration satisfies the constraints, the result is explicitly non-routable.
+
+## Results, artifacts, and resume
+
+The Python API returns a `ResultBundle`. Every completed CLI or Python run also writes a versioned
+run-artifact directory at `.inferencefit/runs/<run-id>/` with:
+
+- `manifest.json` — provenance, settings, and lifecycle state;
+- `spec.yaml` and `dataset.jsonl` — exact input snapshots;
+- `observations.jsonl` — one flushed terminal record per planned evaluation;
+- `result.json` — metrics, constraints, Pareto frontier, ranking, and recommendation;
+- `summary.md` — a human-readable result summary;
+- `routing-policy.yaml` — a single, fallback, or explicitly non-routable policy.
+
+Interrupted compatible runs can reuse completed observations:
+
+```bash
+inferencefit benchmark examples/basic/eval.yaml --resume <run-id>
+```
+
+Resume checks the spec and dataset hashes before skipping completed
+`(case, candidate, repetition)` identities.
+
+## Providers and credentials
+
+The `fixture` provider is deterministic and offline. The generic, non-streaming OpenAI-compatible
+adapter accepts an explicit base URL and includes endpoint presets for Fireworks, DeepSeek,
+OpenRouter, Ollama, and vLLM. It uses the providers' chat-completions-shaped HTTP interface without
+vendor SDKs.
+
+Credentials are resolved from opaque references. For example, `credential_ref: fireworks-main`
+checks `INFERENCEFIT_CREDENTIAL_FIREWORKS_MAIN` and then `FIREWORKS_API_KEY`; DeepSeek similarly
+falls back to `DEEPSEEK_API_KEY`, and OpenRouter to `OPENROUTER_API_KEY`. Secret values are not
+written to run artifacts.
+
+## Local daemon
+
+```bash
+inferencefit serve
+```
+
+The daemon defaults to `127.0.0.1:8787` and exposes health, run creation, status, result, and
+cancellation endpoints. It has no authentication and is intended only for trusted localhost use;
+do not expose it to a network.
+
+## Current limitations
+
+Version 0.1.0 uses a local process job manager and filesystem artifact store. It supports
+non-streaming chat completions, a single two-stage fallback, and Python only. Pricing is static
+configuration rather than provider billing data. Exact validators intentionally do not provide
+semantic-equivalence scoring. There is no hosted Cloud/SaaS service, account system, traffic proxy,
+browser UI, distributed worker system, learned routing, or model training.
+
+## Roadmap (not available in 0.1.0)
+
+Potential post-0.1 work includes richer request modalities, more provider-specific metadata,
+scalable artifact-store adapters, and additional language SDKs. These are directions, not current
+features or commitments.
+
+## Development and documentation
+
+For an editable development install:
+
+```bash
+python -m venv .venv
+pip install -e ".[dev]"
+pytest
+ruff check .
+ruff format --check .
+```
+
+Normal tests use fixtures and do not spend provider credits. Live provider testing is opt-in; run
+it only explicitly, with the required credential configured and awareness of provider charges.
+
+Detailed references:
+
+- [Architecture](docs/architecture.md)
+- [Serialized contracts](docs/contracts.md)
+- [E0.5 real-world validation](docs/e0.5-real-world-validation.md)
+
+## License
+
+InferenceFit is licensed under the [Apache License 2.0](LICENSE) (`Apache-2.0`).