agentic-blocks 0.1.1__tar.gz → 0.1.3__tar.gz

{agentic_blocks-0.1.1/src/agentic_blocks.egg-info → agentic_blocks-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-blocks
-Version: 0.1.1
+Version: 0.1.3
 Summary: Simple building blocks for agentic AI systems with MCP client and conversation management
 Author-email: Magnus Bjelkenhed <bjelkenhed@gmail.com>
 License: MIT
@@ -41,8 +41,9 @@ Agentic Blocks provides clean, simple components for building AI agent systems,
 
 - **MCP Client**: Connect to Model Control Protocol (MCP) endpoints with a sync-by-default API
 - **Messages**: Manage LLM conversation history with OpenAI-compatible format
+- **LLM**: Simple function for calling OpenAI-compatible completion APIs
 
-Both components follow principles of simplicity, maintainability, and ease of use.
+All components follow principles of simplicity, maintainability, and ease of use.
 
 ## Installation
 
@@ -123,10 +124,73 @@ conversation = messages.get_messages()
 print(messages)
 ```
 
-## Complete Example - Agent with MCP Tools
+### LLM - Call OpenAI-Compatible APIs
+
+The `call_llm` function provides a simple interface for calling LLM completion APIs:
+
+```python
+from agentic_blocks import call_llm, Messages
+
+# Method 1: Using with Messages object
+messages = Messages(
+    system_prompt="You are a helpful assistant.",
+    user_prompt="What is the capital of France?"
+)
+
+response = call_llm(messages, temperature=0.7)
+print(response)  # "The capital of France is Paris."
+```
+
+```python
+# Method 2: Using with raw message list  
+messages_list = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What is 2+2?"}
+]
+
+response = call_llm(messages_list, model="gpt-4o-mini")
+print(response)  # "2+2 equals 4."
+```
 
 ```python
-from agentic_blocks import MCPClient, Messages
+# Method 3: Using with tools (for function calling)
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {"type": "string", "description": "City name"}
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+messages = Messages(user_prompt="What's the weather like in Stockholm?")
+response = call_llm(messages, tools=tools)
+print(response)
+```
+
+**Environment Setup:**
+Create a `.env` file in your project root:
+```
+OPENAI_API_KEY=your_api_key_here
+```
+
+Or pass the API key directly:
+```python
+response = call_llm(messages, api_key="your_api_key_here")
+```
+
+## Complete Example - Agent with MCP Tools and LLM
+
+```python
+from agentic_blocks import MCPClient, Messages, call_llm
 
 def simple_agent():
     # Initialize MCP client and conversation
@@ -170,10 +234,10 @@ def simple_agent():
                 response_text = result["content"][0]["text"]
                 messages.add_tool_response("search_001", response_text)
             
-            # Add final assistant response
-            messages.add_assistant_message(
-                "Based on my search, here's what I found about the latest AI news..."
-            )
+            # Use LLM to generate response based on search results
+            messages.add_user_message("Based on the search results, please summarize the key AI news.")
+            llm_response = call_llm(messages, temperature=0.7)
+            messages.add_assistant_message(llm_response)
     
     # Print conversation
     print("\\nConversation:")
@@ -224,6 +288,21 @@ Messages(system_prompt=None, user_prompt=None, add_date_and_time=False)
 - `get_messages() -> List[Dict]`: Get all messages
 - `has_pending_tool_calls() -> bool`: Check for pending tool calls
 
+### call_llm
+
+```python
+call_llm(messages, tools=None, api_key=None, model="gpt-4o-mini", **kwargs) -> str
+```
+
+**Parameters:**
+- `messages`: Either a `Messages` instance or list of message dictionaries
+- `tools`: Optional list of tools in OpenAI function calling format
+- `api_key`: OpenAI API key (defaults to OPENAI_API_KEY from .env)
+- `model`: Model name to use for completion
+- `**kwargs`: Additional parameters passed to OpenAI API (temperature, max_tokens, etc.)
+
+**Returns:** The assistant's response content as a string
+
 ## Requirements
 
 - Python >= 3.11

{agentic_blocks-0.1.1 → agentic_blocks-0.1.3}/README.md

@@ -8,8 +8,9 @@ Agentic Blocks provides clean, simple components for building AI agent systems,
 
 - **MCP Client**: Connect to Model Control Protocol (MCP) endpoints with a sync-by-default API
 - **Messages**: Manage LLM conversation history with OpenAI-compatible format
+- **LLM**: Simple function for calling OpenAI-compatible completion APIs
 
-Both components follow principles of simplicity, maintainability, and ease of use.
+All components follow principles of simplicity, maintainability, and ease of use.
 
 ## Installation
 
@@ -90,10 +91,73 @@ conversation = messages.get_messages()
 print(messages)
 ```
 
-## Complete Example - Agent with MCP Tools
+### LLM - Call OpenAI-Compatible APIs
+
+The `call_llm` function provides a simple interface for calling LLM completion APIs:
+
+```python
+from agentic_blocks import call_llm, Messages
+
+# Method 1: Using with Messages object
+messages = Messages(
+    system_prompt="You are a helpful assistant.",
+    user_prompt="What is the capital of France?"
+)
+
+response = call_llm(messages, temperature=0.7)
+print(response)  # "The capital of France is Paris."
+```
+
+```python
+# Method 2: Using with raw message list  
+messages_list = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What is 2+2?"}
+]
+
+response = call_llm(messages_list, model="gpt-4o-mini")
+print(response)  # "2+2 equals 4."
+```
 
 ```python
-from agentic_blocks import MCPClient, Messages
+# Method 3: Using with tools (for function calling)
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {"type": "string", "description": "City name"}
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+messages = Messages(user_prompt="What's the weather like in Stockholm?")
+response = call_llm(messages, tools=tools)
+print(response)
+```
+
+**Environment Setup:**
+Create a `.env` file in your project root:
+```
+OPENAI_API_KEY=your_api_key_here
+```
+
+Or pass the API key directly:
+```python
+response = call_llm(messages, api_key="your_api_key_here")
+```
+
+## Complete Example - Agent with MCP Tools and LLM
+
+```python
+from agentic_blocks import MCPClient, Messages, call_llm
 
 def simple_agent():
     # Initialize MCP client and conversation
@@ -137,10 +201,10 @@ def simple_agent():
                 response_text = result["content"][0]["text"]
                 messages.add_tool_response("search_001", response_text)
             
-            # Add final assistant response
-            messages.add_assistant_message(
-                "Based on my search, here's what I found about the latest AI news..."
-            )
+            # Use LLM to generate response based on search results
+            messages.add_user_message("Based on the search results, please summarize the key AI news.")
+            llm_response = call_llm(messages, temperature=0.7)
+            messages.add_assistant_message(llm_response)
     
     # Print conversation
     print("\\nConversation:")
@@ -191,6 +255,21 @@ Messages(system_prompt=None, user_prompt=None, add_date_and_time=False)
 - `get_messages() -> List[Dict]`: Get all messages
 - `has_pending_tool_calls() -> bool`: Check for pending tool calls
 
+### call_llm
+
+```python
+call_llm(messages, tools=None, api_key=None, model="gpt-4o-mini", **kwargs) -> str
+```
+
+**Parameters:**
+- `messages`: Either a `Messages` instance or list of message dictionaries
+- `tools`: Optional list of tools in OpenAI function calling format
+- `api_key`: OpenAI API key (defaults to OPENAI_API_KEY from .env)
+- `model`: Model name to use for completion
+- `**kwargs`: Additional parameters passed to OpenAI API (temperature, max_tokens, etc.)
+
+**Returns:** The assistant's response content as a string
+
 ## Requirements
 
 - Python >= 3.11

{agentic_blocks-0.1.1 → agentic_blocks-0.1.3}/pyproject.toml

@@ -14,7 +14,7 @@ agentic_blocks = []
 
 [project]
 name = "agentic-blocks"
-version = "0.1.1"
+version = "0.1.3"
 description = "Simple building blocks for agentic AI systems with MCP client and conversation management"
 readme = "README.md"
 requires-python = ">=3.11"

{agentic_blocks-0.1.1 → agentic_blocks-0.1.3}/src/agentic_blocks/__init__.py

@@ -2,6 +2,7 @@
 
 from .mcp_client import MCPClient, MCPEndpointError
 from .messages import Messages
+from .llm import call_llm, LLMError
 
 # Get version from package metadata
 try:
@@ -10,4 +11,4 @@ try:
 except Exception:
     __version__ = "unknown"
 
-__all__ = ["MCPClient", "MCPEndpointError", "Messages"]
+__all__ = ["MCPClient", "MCPEndpointError", "Messages", "call_llm", "LLMError"]

agentic_blocks-0.1.3/src/agentic_blocks/llm.py

@@ -0,0 +1,140 @@
+"""
+Simplified LLM client for calling completion APIs.
+"""
+
+import os
+from typing import List, Dict, Any, Optional, Union
+
+from dotenv import load_dotenv
+from openai import OpenAI
+
+from agentic_blocks.messages import Messages
+
+
+class LLMError(Exception):
+    """Exception raised when there's an error calling the LLM API."""
+
+    pass
+
+
+def call_llm(
+    messages: Union[Messages, List[Dict[str, Any]]],
+    tools: Optional[List[Dict[str, Any]]] = None,
+    api_key: Optional[str] = None,
+    model: str = "gpt-4o-mini",
+    **kwargs,
+) -> str:
+    """
+    Call an LLM completion API with the provided messages.
+
+    Args:
+        messages: Either a Messages instance or a list of message dicts
+        tools: Optional list of tools in OpenAI function calling format
+        api_key: OpenAI API key (if not provided, loads from .env OPENAI_API_KEY)
+        model: Model name to use for completion
+        **kwargs: Additional parameters to pass to OpenAI API
+
+    Returns:
+        The assistant's response content as a string
+
+    Raises:
+        LLMError: If API call fails or configuration is invalid
+    """
+    # Load environment variables
+    load_dotenv()
+
+    # Get API key
+    if not api_key:
+        api_key = os.getenv("OPENAI_API_KEY")
+
+    if not api_key:
+        raise LLMError(
+            "OpenAI API key not found. Set OPENAI_API_KEY environment variable or pass api_key parameter."
+        )
+
+    # Initialize OpenAI client
+    client = OpenAI(api_key=api_key)
+
+    # Handle different message input types
+    if isinstance(messages, Messages):
+        conversation_messages = messages.get_messages()
+    else:
+        conversation_messages = messages
+
+    if not conversation_messages:
+        raise LLMError("No messages provided for completion.")
+
+    try:
+        # Prepare completion parameters
+        completion_params = {
+            "model": model,
+            "messages": conversation_messages,
+            **kwargs,
+        }
+
+        if tools:
+            completion_params["tools"] = tools
+            completion_params["tool_choice"] = "auto"
+
+        # Make completion request
+        response = client.chat.completions.create(**completion_params)
+
+        # Extract and return response content
+        return response.choices[0].message.content or ""
+
+    except Exception as e:
+        raise LLMError(f"Failed to call LLM API: {e}")
+
+
+def example_usage():
+    """Example of how to use the call_llm function."""
+    # Example 1: Using with Messages object
+    messages_obj = Messages(
+        system_prompt="You are a helpful assistant.",
+        user_prompt="What is the capital of France?",
+    )
+
+    # Example 2: Using with raw message list
+    messages_list = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "What is the capital of France?"},
+    ]
+
+    # Example tools
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get current weather for a location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "City and state, e.g. San Francisco, CA",
+                        }
+                    },
+                    "required": ["location"],
+                },
+            },
+        }
+    ]
+
+    try:
+        # Call with Messages object
+        print("Using Messages object:")
+        response1 = call_llm(messages_obj, temperature=0.7)
+        print(f"Response: {response1}")
+
+        # Call with raw message list
+        print("\nUsing raw message list:")
+        response2 = call_llm(messages_list, tools=tools, temperature=0.5)
+        print(f"Response: {response2}")
+
+    except LLMError as e:
+        print(f"Error: {e}")
+
+
+if __name__ == "__main__":
+    example_usage()

{agentic_blocks-0.1.1 → agentic_blocks-0.1.3/src/agentic_blocks.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-blocks
-Version: 0.1.1
+Version: 0.1.3
 Summary: Simple building blocks for agentic AI systems with MCP client and conversation management
 Author-email: Magnus Bjelkenhed <bjelkenhed@gmail.com>
 License: MIT
@@ -41,8 +41,9 @@ Agentic Blocks provides clean, simple components for building AI agent systems,
 
 - **MCP Client**: Connect to Model Control Protocol (MCP) endpoints with a sync-by-default API
 - **Messages**: Manage LLM conversation history with OpenAI-compatible format
+- **LLM**: Simple function for calling OpenAI-compatible completion APIs
 
-Both components follow principles of simplicity, maintainability, and ease of use.
+All components follow principles of simplicity, maintainability, and ease of use.
 
 ## Installation
 
@@ -123,10 +124,73 @@ conversation = messages.get_messages()
 print(messages)
 ```
 
-## Complete Example - Agent with MCP Tools
+### LLM - Call OpenAI-Compatible APIs
+
+The `call_llm` function provides a simple interface for calling LLM completion APIs:
+
+```python
+from agentic_blocks import call_llm, Messages
+
+# Method 1: Using with Messages object
+messages = Messages(
+    system_prompt="You are a helpful assistant.",
+    user_prompt="What is the capital of France?"
+)
+
+response = call_llm(messages, temperature=0.7)
+print(response)  # "The capital of France is Paris."
+```
+
+```python
+# Method 2: Using with raw message list  
+messages_list = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What is 2+2?"}
+]
+
+response = call_llm(messages_list, model="gpt-4o-mini")
+print(response)  # "2+2 equals 4."
+```
 
 ```python
-from agentic_blocks import MCPClient, Messages
+# Method 3: Using with tools (for function calling)
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {"type": "string", "description": "City name"}
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+messages = Messages(user_prompt="What's the weather like in Stockholm?")
+response = call_llm(messages, tools=tools)
+print(response)
+```
+
+**Environment Setup:**
+Create a `.env` file in your project root:
+```
+OPENAI_API_KEY=your_api_key_here
+```
+
+Or pass the API key directly:
+```python
+response = call_llm(messages, api_key="your_api_key_here")
+```
+
+## Complete Example - Agent with MCP Tools and LLM
+
+```python
+from agentic_blocks import MCPClient, Messages, call_llm
 
 def simple_agent():
     # Initialize MCP client and conversation
@@ -170,10 +234,10 @@ def simple_agent():
                 response_text = result["content"][0]["text"]
                 messages.add_tool_response("search_001", response_text)
             
-            # Add final assistant response
-            messages.add_assistant_message(
-                "Based on my search, here's what I found about the latest AI news..."
-            )
+            # Use LLM to generate response based on search results
+            messages.add_user_message("Based on the search results, please summarize the key AI news.")
+            llm_response = call_llm(messages, temperature=0.7)
+            messages.add_assistant_message(llm_response)
     
     # Print conversation
     print("\\nConversation:")
@@ -224,6 +288,21 @@ Messages(system_prompt=None, user_prompt=None, add_date_and_time=False)
 - `get_messages() -> List[Dict]`: Get all messages
 - `has_pending_tool_calls() -> bool`: Check for pending tool calls
 
+### call_llm
+
+```python
+call_llm(messages, tools=None, api_key=None, model="gpt-4o-mini", **kwargs) -> str
+```
+
+**Parameters:**
+- `messages`: Either a `Messages` instance or list of message dictionaries
+- `tools`: Optional list of tools in OpenAI function calling format
+- `api_key`: OpenAI API key (defaults to OPENAI_API_KEY from .env)
+- `model`: Model name to use for completion
+- `**kwargs`: Additional parameters passed to OpenAI API (temperature, max_tokens, etc.)
+
+**Returns:** The assistant's response content as a string
+
 ## Requirements
 
 - Python >= 3.11

{agentic_blocks-0.1.1 → agentic_blocks-0.1.3}/src/agentic_blocks.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 src/agentic_blocks/__init__.py
+src/agentic_blocks/llm.py
 src/agentic_blocks/mcp_client.py
 src/agentic_blocks/messages.py
 src/agentic_blocks.egg-info/PKG-INFO