Feat/first implementation

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @edgee-cloud/edgeers

.github/workflows/check.yml

@@ -0,0 +1,26 @@
+name: Check
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  Check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+      - name: Set up Python
+        run: uv python install 3.12
+      - name: Install dependencies
+        run: uv sync --all-extras
+      - name: Ruff format check
+        run: uv run ruff format --check .
+      - name: Ruff lint
+        run: uv run ruff check .
+      - name: Run tests
+        run: uv run pytest

.github/workflows/release.yml

@@ -0,0 +1,30 @@
+name: Release to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # Required for trusted publishing
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build dependencies
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+

README.md

@@ -24,7 +24,7 @@ response = edgee.send(
     input="What is the capital of France?",
 )
 
-print(response.choices[0].message["content"])
+print(response.text)
 ```
 
 ### Full Input with Messages
@@ -67,8 +67,40 @@ response = edgee.send(
     },
 )
 
-if response.choices[0].message.get("tool_calls"):
-    print(response.choices[0].message["tool_calls"])
+if response.tool_calls:
+    print(response.tool_calls)
+```
+
+### Streaming
+
+Access chunk properties for streaming:
+
+```python
+for chunk in edgee.stream(model="gpt-4o", input="Tell me a story"):
+    if chunk.text:
+        print(chunk.text, end="", flush=True)
+```
+
+#### Alternative: Using send(stream=True)
+
+```python
+for chunk in edgee.send(model="gpt-4o", input="Tell me a story", stream=True):
+    if chunk.text:
+        print(chunk.text, end="", flush=True)
+```
+
+#### Accessing Full Chunk Data
+
+When you need complete access to the streaming response:
+
+```python
+for chunk in edgee.stream(model="gpt-4o", input="Hello"):
+    if chunk.role:
+        print(f"Role: {chunk.role}")
+    if chunk.text:
+        print(chunk.text, end="", flush=True)
+    if chunk.finish_reason:
+        print(f"\nFinish: {chunk.finish_reason}")
 ```
 
 ## Response
@@ -79,6 +111,12 @@ class SendResponse:
     choices: list[Choice]
     usage: Optional[Usage]
 
+    # Convenience properties for easy access
+    text: str | None  # Shortcut for choices[0].message["content"]
+    message: dict | None  # Shortcut for choices[0].message
+    finish_reason: str | None  # Shortcut for choices[0].finish_reason
+    tool_calls: list | None  # Shortcut for choices[0].message["tool_calls"]
+
 @dataclass
 class Choice:
     index: int
@@ -91,3 +129,30 @@ class Usage:
     completion_tokens: int
     total_tokens: int
 ```
+
+### Streaming Response
+
+```python
+@dataclass
+class StreamChunk:
+    choices: list[StreamChoice]
+
+    # Convenience properties for easy access
+    text: str | None  # Shortcut for choices[0].delta.content
+    role: str | None  # Shortcut for choices[0].delta.role
+    finish_reason: str | None  # Shortcut for choices[0].finish_reason
+
+@dataclass
+class StreamChoice:
+    index: int
+    delta: StreamDelta
+    finish_reason: str | None
+
+@dataclass
+class StreamDelta:
+    role: str | None  # Only present in first chunk
+    content: str | None
+    tool_calls: list[dict] | None
+```
+
+To learn more about this SDK, please refer to the [dedicated documentation](https://www.edgee.cloud/docs/sdk/python).