turn into pypi package, so we can use in cli which itself is published

Author: Ademfcan

.github/workflows/deploy.yml

@@ -0,0 +1,25 @@
+name: Deploy to PyPI
+
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+      - name: Build and publish
+        env:
+          POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          poetry build
+          poetry publish

README.md

@@ -1,9 +1,9 @@
-#  aisuite
+#  aisuite-extendedmodels
 
-[![PyPI](https://img.shields.io/pypi/v/aisuite)](https://pypi.org/project/aisuite/)
+[![PyPI](https://img.shields.io/pypi/v/aisuite-extendedmodels)](https://pypi.org/project/aisuite-extendedmodels/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-`aisuite` is a lightweight Python library that provides a **unified API for working with multiple Generative AI providers**.  
+`aisuite-extendedmodels` is a lightweight Python library that provides a **unified API for working with multiple Generative AI providers**.  
 It offers a consistent interface for models from *OpenAI, Anthropic, Google Vertex AI, Google GenAI, Hugging Face, AWS, Cohere, Mistral, Ollama*, and others—abstracting away SDK differences, authentication details, and parameter variations.  
 Its design is modeled after OpenAI’s API style, making it instantly familiar and easy to adopt.
 
@@ -27,24 +27,24 @@ It’s designed for low learning curve — so you can focus on building AI syste
 
 ## Installation
 
-You can install just the base `aisuite` package, or install a provider's package along with `aisuite`.
+You can install just the base `aisuite-extendedmodels` package, or install a provider's package along with `aisuite-extendedmodels`.
 
 Install just the base package without any provider SDKs:
 
 ```shell
-pip install aisuite
+pip install aisuite-extendedmodels
 ```
 
-Install aisuite with a specific provider (e.g., Anthropic):
+Install aisuite-extendedmodels with a specific provider (e.g., Anthropic):
 
 ```shell
-pip install 'aisuite[anthropic]'
+pip install 'aisuite-extendedmodels[anthropic]'
 ```
 
-Install aisuite with all provider libraries:
+Install aisuite-extendedmodels with all provider libraries:
 
 ```shell
-pip install 'aisuite[all]'
+pip install 'aisuite-extendedmodels[all]'
 ```
 
 ## Setup

aisuite-js/package.json

@@ -1,5 +1,5 @@
 {
-  "name": "aisuite",
+  "name": "aisuite-extendedmodels",
   "version": "0.1.1",
   "description": "Unified TypeScript library for multiple LLM providers",
   "main": "dist/index.js",

pyproject.toml

@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "aisuite"
+name = "aisuite-extendedmodels"
 version = "0.1.14"
 description = "Uniform access layer for LLMs"
 authors = ["Andrew Ng <ng@deeplearning.ai>", "Rohit P <rohit.prasad15@gmail.com>"]

tests/mcp/README.md

@@ -15,9 +15,9 @@ To run these tests, you need:
    pip install pytest pytest-asyncio python-dotenv
    ```
 
-3. **MCP package** (should already be installed if you have aisuite[mcp]):
+3. **MCP package** (should already be installed if you have aisuite-extendedmodels[mcp]):
    ```bash
-   pip install 'aisuite[mcp]'
+   pip install 'aisuite-extendedmodels[mcp]'
    ```
 
 4. **Environment variables** (for e2e tests that mock LLM calls):
@@ -203,7 +203,7 @@ pytest tests/mcp/ -v -m "integration and not llm"
 - Install Node.js from https://nodejs.org/
 
 **Error: "MCP package not installed"**
-- Run: `pip install 'aisuite[mcp]'`
+- Run: `pip install 'aisuite-extendedmodels[mcp]'`
 
 **Tests hang or timeout**
 - Check Node.js/npx is working: `npx --version`