lemonade-python-sdk 1.0.3__tar.gz → 1.0.4__tar.gz

{lemonade_python_sdk-1.0.3 → lemonade_python_sdk-1.0.4}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: lemonade-python-sdk
-Version: 1.0.3
+Version: 1.0.4
 Summary: A clean interface for interacting with the Lemonade LLM server
 Home-page: https://github.com/Tetramatrix/lemonade-python-sdk
-Author: Your Name
-Author-email: your.email@example.com
+Author: Tetramatrix
+Author-email: contact@tetramatrix.dev
 Project-URL: Bug Reports, https://github.com/Tetramatrix/lemonade-python-sdk/issues
 Project-URL: Source, https://github.com/Tetramatrix/lemonade-python-sdk
 Keywords: llm,ai,lemonade,sdk,api
@@ -52,7 +52,8 @@ This SDK provides a clean, pythonic interface for interacting with local LLMs ru
 
 * **Auto-Discovery:** Automatically scans multiple ports and hosts to find active Lemonade instances.
 * **Low-Overhead Architecture:** Designed as a thin, efficient wrapper to leverage Lemonade's C++ performance with minimal Python latency.
-* **Health Checks & Recovery:** Built-in utilities to verify server status and handle connection drops.
+* **Health Checks & Stats:** Lightweight `/api/v1/health` endpoint for connectivity checks plus `get_stats()` for server performance metrics.
+* **Server Statistics:** Retrieve token usage, requests served, and performance metrics via `get_stats()`.
 * **Type-Safe Client:** Full Python type hinting for better developer experience (IDE autocompletion).
 * **Model Management:** Simple API to load, unload, and list models dynamically.
 * **Embeddings API:** Generate text embeddings for semantic search, RAG, and clustering (FLM & llamacpp backends).
@@ -92,6 +93,21 @@ else:
     print("No Lemonade instance found.")
 ```
 
+### 1.1 Health Check & Stats
+
+```python
+# Check if server is alive (uses /api/v1/health endpoint)
+if client.health_check():
+    print("Lemonade is running!")
+
+# Get server statistics
+stats = client.get_stats()
+if stats:
+    print(f"Tokens generated: {stats.get('total_tokens', 0)}")
+    print(f"Tokens/sec: {stats.get('tokens_per_second', 0):.1f}")
+    print(f"Requests served: {stats.get('requests_served', 0)}")
+```
+
 ### 2. Chat Completion
 
 ```python

{lemonade_python_sdk-1.0.3 → lemonade_python_sdk-1.0.4}/README.md

@@ -11,7 +11,8 @@ This SDK provides a clean, pythonic interface for interacting with local LLMs ru
 
 * **Auto-Discovery:** Automatically scans multiple ports and hosts to find active Lemonade instances.
 * **Low-Overhead Architecture:** Designed as a thin, efficient wrapper to leverage Lemonade's C++ performance with minimal Python latency.
-* **Health Checks & Recovery:** Built-in utilities to verify server status and handle connection drops.
+* **Health Checks & Stats:** Lightweight `/api/v1/health` endpoint for connectivity checks plus `get_stats()` for server performance metrics.
+* **Server Statistics:** Retrieve token usage, requests served, and performance metrics via `get_stats()`.
 * **Type-Safe Client:** Full Python type hinting for better developer experience (IDE autocompletion).
 * **Model Management:** Simple API to load, unload, and list models dynamically.
 * **Embeddings API:** Generate text embeddings for semantic search, RAG, and clustering (FLM & llamacpp backends).
@@ -51,6 +52,21 @@ else:
     print("No Lemonade instance found.")
 ```
 
+### 1.1 Health Check & Stats
+
+```python
+# Check if server is alive (uses /api/v1/health endpoint)
+if client.health_check():
+    print("Lemonade is running!")
+
+# Get server statistics
+stats = client.get_stats()
+if stats:
+    print(f"Tokens generated: {stats.get('total_tokens', 0)}")
+    print(f"Tokens/sec: {stats.get('tokens_per_second', 0):.1f}")
+    print(f"Requests served: {stats.get('requests_served', 0)}")
+```
+
 ### 2. Chat Completion
 
 ```python

{lemonade_python_sdk-1.0.3 → lemonade_python_sdk-1.0.4}/lemonade_python_sdk.egg-info/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: lemonade-python-sdk
-Version: 1.0.3
+Version: 1.0.4
 Summary: A clean interface for interacting with the Lemonade LLM server
 Home-page: https://github.com/Tetramatrix/lemonade-python-sdk
-Author: Your Name
-Author-email: your.email@example.com
+Author: Tetramatrix
+Author-email: contact@tetramatrix.dev
 Project-URL: Bug Reports, https://github.com/Tetramatrix/lemonade-python-sdk/issues
 Project-URL: Source, https://github.com/Tetramatrix/lemonade-python-sdk
 Keywords: llm,ai,lemonade,sdk,api
@@ -52,7 +52,8 @@ This SDK provides a clean, pythonic interface for interacting with local LLMs ru
 
 * **Auto-Discovery:** Automatically scans multiple ports and hosts to find active Lemonade instances.
 * **Low-Overhead Architecture:** Designed as a thin, efficient wrapper to leverage Lemonade's C++ performance with minimal Python latency.
-* **Health Checks & Recovery:** Built-in utilities to verify server status and handle connection drops.
+* **Health Checks & Stats:** Lightweight `/api/v1/health` endpoint for connectivity checks plus `get_stats()` for server performance metrics.
+* **Server Statistics:** Retrieve token usage, requests served, and performance metrics via `get_stats()`.
 * **Type-Safe Client:** Full Python type hinting for better developer experience (IDE autocompletion).
 * **Model Management:** Simple API to load, unload, and list models dynamically.
 * **Embeddings API:** Generate text embeddings for semantic search, RAG, and clustering (FLM & llamacpp backends).
@@ -92,6 +93,21 @@ else:
     print("No Lemonade instance found.")
 ```
 
+### 1.1 Health Check & Stats
+
+```python
+# Check if server is alive (uses /api/v1/health endpoint)
+if client.health_check():
+    print("Lemonade is running!")
+
+# Get server statistics
+stats = client.get_stats()
+if stats:
+    print(f"Tokens generated: {stats.get('total_tokens', 0)}")
+    print(f"Tokens/sec: {stats.get('tokens_per_second', 0):.1f}")
+    print(f"Requests served: {stats.get('requests_served', 0)}")
+```
+
 ### 2. Chat Completion
 
 ```python

{lemonade_python_sdk-1.0.3 → lemonade_python_sdk-1.0.4}/lemonade_sdk/client.py

@@ -79,11 +79,31 @@ class LemonadeClient:
             bool: True if the server is reachable, otherwise False
         """
         try:
-            models = self.list_models()
-            return len(models) >= 0  # If we don't get an error, the server is reachable
-        except:
+            url = f"{self.base_url}/api/v1/health"
+            response = self.session.get(url, timeout=10)
+            return response.status_code == 200
+        except Exception:
             return False
-    
+
+    def get_stats(self) -> Dict[str, Any]:
+        """
+        Retrieves server statistics including token usage, requests served, and performance metrics.
+
+        Returns:
+            Dict[str, Any]: Server stats with token counts, tokens_per_second, etc.
+        """
+        url = f"{self.base_url}/api/v1/stats"
+        try:
+            response = self.session.get(url, timeout=10)
+            response.raise_for_status()
+            return response.json()
+        except requests.exceptions.RequestException as e:
+            print(f"Error retrieving stats: {e}")
+            return {}
+        except json.JSONDecodeError as e:
+            print(f"Error parsing stats response: {e}")
+            return {}
+
     def get_current_model(self) -> Optional[str]:
         """
         Retrieves the currently active model from the Lemonade server.

{lemonade_python_sdk-1.0.3 → lemonade_python_sdk-1.0.4}/setup.py

@@ -13,9 +13,9 @@ with open("LICENSE", "r", encoding="utf-8") as fh:
 
 setup(
     name="lemonade-python-sdk",
-    version="1.0.3",
-    author="Your Name",
-    author_email="your.email@example.com",
+    version="1.0.4",
+    author="Tetramatrix",
+    author_email="contact@tetramatrix.dev",
     description="A clean interface for interacting with the Lemonade LLM server",
     long_description=long_description,
     long_description_content_type="text/markdown",