Merge pull request #9 from stereosky/update-docs

docs: fix typos and async code samples

Author: rockwotj

docs/index.md

@@ -45,14 +45,15 @@ agents:
     # See them all at https://docs.redpanda.com/redpanda-connect/components/outputs/about/
     output:
       <output>
-    # See options here: https://docs.redpanda.com/redpanda-connect/components/tracer/about/
+    # Configure Redpanda Connect to send tracing events to Jaeger, Open Telemetry collector and more.
+    # See options here: https://docs.redpanda.com/redpanda-connect/components/tracers/about/
     tracer:
         <tracer>
 ```
 
 ### `agents/*.py`
 
-Each agent recieves input from `input` and sends it's output to `output`. You can create an agent
+Each agent receives input from `input` and sends its output to `output`. You can create an agent
 by importing from `redpanda.agents`. Creating an `Agent` looks like:
 
 ```python
@@ -63,6 +64,8 @@ my_agent = Agent(
 )
 ```
 
+In this example, OpenAI GPT-4o is configured and requires you to set `OPENAI_API_KEY` as an environment variable.
+
 Once you've created the agent, you pass it off to the runtime to handle messages in the pipeline like so:
 
 ```python

docs/tutorial/01_agent_.md

@@ -24,6 +24,7 @@ Below is a short snippet showing how we can instantiate and use an Agent:
 
 ```python
 # In a file like main.py
+import asyncio
 from redpanda.agents import Agent
 
 # Create an agent with minimal setup
@@ -34,8 +35,11 @@ my_agent = Agent(
 )
 
 # Now let's ask something
-response = await my_agent.run("Hello Agent, what's your favorite color?")
-print(response)  # It will print a response based on the language model
+async def run_agent():
+   response = asyncio.run(my_agent.run("Hello Agent, what's your favorite color?"))
+   print(response)  # It will print a response based on the language model
+
+asyncio.run(run_agent())
 ```
 
 Explanation of the snippet:

docs/tutorial/02_tool_.md

@@ -85,6 +85,7 @@ Imagine we have an Agent that wants to handle math questions. Let’s register o
 
 ```python
 # main.py
+import asyncio
 from redpanda.agents import Agent
 from number_cruncher_tool import NumberCruncher
 
@@ -100,8 +101,11 @@ my_agent = Agent(
 )
 
 # Agent usage
-response = await my_agent.run("What is the product of 3 and 4?")
-print(response)
+async def run_agent():
+    response = await my_agent.run("What is the product of 3 and 4?")
+    print(response)
+
+asyncio.run(run_agent())
 ```
 
 ### Explanation of What Happens

docs/tutorial/03_toolresponse_.md

@@ -87,6 +87,7 @@ Let’s create an Agent using our `PictureMaker` tool. Suppose we send the Agent
 
 ```python
 # main.py
+import asyncio
 from redpanda.agents import Agent
 from picture_maker_tool import PictureMaker
 
@@ -102,8 +103,11 @@ my_agent = Agent(
 )
 
 # 3) Run and see what happens
-response = await my_agent.run("Please generate me a picture of a small cat.")
-print(response)  # The Agent will eventually include text + image data in some manner
+async def run_agent():
+    response = await my_agent.run("Please generate me a picture of a small cat.")
+    print(response)  # The Agent will eventually include text + image data in some manner
+
+asyncio.run(run_agent())
 ```
 
 ### What Happens Behind the Scenes?

docs/tutorial/04_agenthooks_.md

@@ -50,6 +50,7 @@ Let’s attach our `MyLoggingHooks` to an Agent. Now, whenever the Agent decides
 
 ```python
 # main.py
+import asyncio
 from redpanda.agents import Agent
 from custom_hooks import MyLoggingHooks
 from number_cruncher_tool import NumberCruncher  # from previous chapters
@@ -62,8 +63,11 @@ my_agent = Agent(
 )
 
 # Run a sample query to see the hooks in action
-response = await my_agent.run("What is 3 + 4?")
-print("Final response:", response)
+async def run_agent():
+    response = await my_agent.run("What is 3 + 4?")
+    print("Final response:", response)
+
+asyncio.run(run_agent())
 ```
 
 What happens:  

docs/tutorial/05_mcpendpoint_.md

@@ -6,7 +6,7 @@ In the [previous chapter: AgentHooks](04_agenthooks_.md), we saw how to track ke
 
 ## 1. Why MCPEndpoint?
 
-Sometimes, your Agent might not have all the tools it needs locally. Or maybe you want to delegate tasks to a remote service. MCPEndpoint is like creating a “phone line” for your Agent to talk to any external MCP (Multi-Channel Processing?) server, whether it’s running on your local machine or out on the internet.
+Sometimes, your Agent might not have all the tools it needs locally. Or maybe you want to delegate tasks to a remote service. MCPEndpoint is like creating a “phone line” for your Agent to talk to any external MCP (Model Context Protocol) server, whether it’s running on your local machine or out on the internet.
 
 For example:
 • You can connect via standard input/output (like launching a program and talking with it).