document auto tool calling in README (#31)

* Update README.md to reflect changes in tool calling syntax

- Modified the description of tool usage to replace `auto_tool_call=True` with `call_tools=True` for clarity.
- Updated example code to demonstrate the new syntax for invoking tools in the LLM class.

* update

* update

* rename

* fix ci

Author: aniketmaurya

README.md

@@ -133,7 +133,7 @@ print("Sentiment:", sentiment)
 ```
 
 ### Tools ([docs](https://lightning.ai/docs/litai/features/tools))
-Tools allow models to get real-world data or take actions. In LitAI, there is no magic with tool use, agents can decide to call tools (`auto_tool_call=True`), or you can manually call a tool with `llm.call_tool(...)` for full control. Zero magic, just plain Python.
+Tools allow models to get real-world data or take actions. In LitAI, there is no magic with tool use, agents can decide to call tools (`auto_tool_calls=True`), or you can manually call a tool with `llm.call_tool(...)` for full control. Zero magic, just plain Python.
 
 ```python
 from litai import LLM, tool
@@ -144,13 +144,15 @@ def get_weather(location: str):
 
 llm = LLM(model="openai/gpt-4")
 
-chosen_tool = llm.chat("What's the weather in Tokyo?", tools=[get_weather])
+result = llm.chat("What's the weather in Tokyo?", tools=[get_weather], auto_tool_calls=True)
+# The weather in Tokyo is sunny
 
+chosen_tool = llm.chat("What's the weather in Tokyo?", tools=[get_weather])
 result = llm.call_tool(chosen_tool, tools=[get_weather])
 # The weather in London is sunny
 ```
 
-Choose automatic or manual tool calling based on production needs. `auto_tool_call=True` is great for quick demos, but can obscure when and why a tool runs which can lead to surprises in production. `llm.call_tool(...)` gives you full control to decide when tools execute, making it easier to log, debug, test, and audit. This clarity is critical for reliability, safety, and trust in real-world systems.
+Choose automatic or manual tool calling based on production needs. `auto_tool_calls=True` is great for quick demos, but can obscure when and why a tool runs which can lead to surprises in production. `llm.call_tool(...)` gives you full control to decide when tools execute, making it easier to log, debug, test, and audit. This clarity is critical for reliability, safety, and trust in real-world systems.
 
 <br/>
 

src/litai/llm.py

@@ -324,7 +324,7 @@ def chat(  # noqa: D417
             conversation_history (Dict[str, List[Dict[str, Any]]]): A dictionary to store conversation history,
             categorized by conversation ID.
             full_response (bool): Whether the entire response should be returned from the chat.
-            auto_call_tools (bool): Tools will be executed automatically whenever applicable. Defaults to False. 
+            auto_call_tools (bool): Tools will be executed automatically whenever applicable. Defaults to False.
             **kwargs (Any): Additional keyword arguments
 
         Returns: