feat: publish inferencelab-llm-eval-kit to PyPI with INFERENCE Lab co…

README.md

@@ -2,6 +2,7 @@
 
 [![Python Version](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![PyPI](https://img.shields.io/pypi/v/llm-eval-kit-v1.svg)](https://pypi.org/project/llm-eval-kit-v1/)
 
 `llm-eval-kit` is a lightweight, fully offline Python library designed to evaluate the quality of LLM responses. It runs evaluation checks locally—requiring **no external APIs, no internet connection (after setup), and no paid subscriptions**.
 
@@ -25,13 +26,29 @@ Designed to fit seamlessly into CI/CD pipelines, this library helps automate pro
 Install the package via `pip` (requires Python 3.9+):
 
 ```bash
-pip install llm-eval-kit
+pip install llm-eval-kit-v1
 ```
 
 *Note: On first run, the library will automatically download the local embedding model `all-MiniLM-L6-v2` (approx. 90MB) to your local cache. All subsequent executions run entirely offline.*
 
 ---
 
+## Dependencies
+
+`llm-eval-kit` requires **Python 3.9+** and uses the following dependencies:
+
+### Core Dependencies
+- **[`sentence-transformers`](https://pypi.org/project/sentence-transformers/) (`>=2.2.0`)**: Generates local dense semantic embeddings via `all-MiniLM-L6-v2` for cosine similarity, relevance, and grounding checks.
+- **[`scikit-learn`](https://pypi.org/project/scikit-learn/) (`>=1.0.0`)**: Powers vector computations and similarity metrics.
+- **[`typer`](https://pypi.org/project/typer/) (`>=0.9.0`)**: Provides the developer-friendly CLI interface (`llm-eval`).
+
+### Development & Testing Dependencies (Optional)
+Install via `pip install "llm-eval-kit-v1[dev]"`:
+- **[`pytest`](https://pypi.org/project/pytest/) (`>=7.0.0`)**: Test discovery and execution.
+- **[`pytest-cov`](https://pypi.org/project/pytest-cov/) (`>=4.0.0`)**: Test suite coverage analysis and reporting.
+
+---
+
 ## Quick Start (Python API)
 
 Here is a 4-line example demonstrating how to run the evaluator:
@@ -194,3 +211,21 @@ Because `Evaluator.evaluate()` defaults to executing all registered criteria whe
 1. **Semantic Similarity != Factual Accuracy:** Grounding checks reflect semantic alignment with the provided context passage. A response can score high simply by repeating the vocabulary and structure of the context even if a key detail is wrong (mitigated by the numeric mismatch check).
 2. **Directional Refusals:** The `refusal_check` only identifies *whether* a refusal happened. It does not judge if the refusal was appropriate (e.g. refusing harmful prompts).
 3. **Implicit Aspects:** Heuristic aspect-splitting for completeness checks may miss implicit sub-questions in complex prompts.
+
+---
+
+## Authors & Maintainers
+
+- **Authors:**
+  - Mahrukh Baig (Lead Engineer)
+  - Muhammad Maaz (Research & Implementation Engineer)
+  - Warisha Arshad (Integration & Evaluation Engineer)
+- **Maintainer:** [INFERENCE Lab](https://github.com/Inference-LAB)
+
+> **Note:** Developed under the **INFERENCE Lab Engineering Cohort 01**.
+
+---
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).

pyproject.toml

@@ -3,17 +3,23 @@ requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "llm-eval-kit"
-version = "0.1.0"
+name = "llm-eval-kit-v1"
+version = "0.1.2"
 authors = [
-    { name = "Mahrukh Baig", email = "mahrukh@example.com" }
+    { name = "Mahrukh Baig" },
+    { name = "Muhammad Maaz" },
+    { name = "Warisha Arshad" },
 ]
-description = "A lightweight, offline Python library for scoring LLM response quality."
+maintainers = [
+    { name = "INFERENCE Lab" },
+]
+description = "A lightweight, offline Python library for scoring LLM response quality. This project is made under the INFERENCE Lab engineering cohort 01."
 readme = "README.md"
+license = "MIT"
 requires-python = ">=3.9"
+keywords = ["llm", "evaluation", "offline", "inference-lab", "cohort-01"]
 classifiers = [
     "Programming Language :: Python :: 3",
-    "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
 ]
 dependencies = [
@@ -31,6 +37,10 @@ dev = [
 [project.scripts]
 llm-eval = "llm_eval_kit.cli:app"
 
+[project.urls]
+"Homepage" = "https://github.com/Inference-LAB/llm-eval-kit"
+"Repository" = "https://github.com/Inference-LAB/llm-eval-kit.git"
+
 [tool.setuptools.packages.find]
 where = ["."]
 include = ["llm_eval_kit*"]