agentic-blocks 0.1.4__tar.gz → 0.1.5__tar.gz

{agentic_blocks-0.1.4/src/agentic_blocks.egg-info → agentic_blocks-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-blocks
-Version: 0.1.4
+Version: 0.1.5
 Summary: Simple building blocks for agentic AI systems with MCP client and conversation management
 Author-email: Magnus Bjelkenhed <bjelkenhed@gmail.com>
 License: MIT

{agentic_blocks-0.1.4 → agentic_blocks-0.1.5}/pyproject.toml

@@ -14,7 +14,7 @@ agentic_blocks = []
 
 [project]
 name = "agentic-blocks"
-version = "0.1.4"
+version = "0.1.5"
 description = "Simple building blocks for agentic AI systems with MCP client and conversation management"
 readme = "README.md"
 requires-python = ">=3.11"

{agentic_blocks-0.1.4 → agentic_blocks-0.1.5}/src/agentic_blocks/llm.py

@@ -24,7 +24,7 @@ def call_llm(
     model: str = "gpt-4o-mini",
     base_url: Optional[str] = None,
     **kwargs,
-) -> str:
+) -> Any:
     """
     Call an LLM completion API with the provided messages.
 
@@ -37,7 +37,7 @@ def call_llm(
         **kwargs: Additional parameters to pass to OpenAI API
 
     Returns:
-        The assistant's response content as a string
+        The complete message object from the OpenAI API response
 
     Raises:
         LLMError: If API call fails or configuration is invalid
@@ -86,8 +86,8 @@ def call_llm(
         # Make completion request
         response = client.chat.completions.create(**completion_params)
 
-        # Extract and return response content
-        return response.choices[0].message.content or ""
+        # Return the complete message object
+        return response.choices[0].message
 
     except Exception as e:
         raise LLMError(f"Failed to call LLM API: {e}")
@@ -132,12 +132,17 @@ def example_usage():
         # Call with Messages object
         print("Using Messages object:")
         response1 = call_llm(messages_obj, temperature=0.7)
-        print(f"Response: {response1}")
+        print(f"Response: {response1.content}")
 
         # Call with raw message list
         print("\nUsing raw message list:")
         response2 = call_llm(messages_list, tools=tools, temperature=0.5)
-        print(f"Response: {response2}")
+        if hasattr(response2, 'tool_calls') and response2.tool_calls:
+            print(f"Tool calls requested: {len(response2.tool_calls)}")
+            for i, tool_call in enumerate(response2.tool_calls):
+                print(f"  {i+1}. {tool_call.function.name}({tool_call.function.arguments})")
+        else:
+            print(f"Response: {response2.content}")
 
     except LLMError as e:
         print(f"Error: {e}")

{agentic_blocks-0.1.4 → agentic_blocks-0.1.5/src/agentic_blocks.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-blocks
-Version: 0.1.4
+Version: 0.1.5
 Summary: Simple building blocks for agentic AI systems with MCP client and conversation management
 Author-email: Magnus Bjelkenhed <bjelkenhed@gmail.com>
 License: MIT