Add Opik AutoGen Tracing to example

[SajidAlamQB]

Related PR: kedro-org/kedro-plugins#1295

This PR adds use OpikTraceDataset with mode: autogen to trace AutoGen agent conversations.

In kedro-academy:

pip install -r requirements.txt 
# Install kedro from main branch instead
pip install git+https://github.com/kedro-org/kedro.git

In kedro-datasets:

cd kedro-datasets
pip install -e ".[opik-opiktracedataset-autogen]"

Then in kedro-academy, update catalog.yml to use Opik tracers:

intent_tracer_opik:
  type: kedro_datasets_experimental.opik.OpikTraceDataset
  credentials: opik_credentials
  mode: langchain

autogen_tracer_opik:
  type: kedro_datasets_experimental.opik.OpikTraceDataset
  credentials: opik_credentials
  mode: autogen

And add Opik credentials to credentials.yml:

opik_credentials:
  api_key: "your-opik-api-key"
  workspace: "your-workspace"
  project_name: "kedro-agentic-test"
  endpoint: "https://www.comet.com/opik/api/v1/private/otel/v1/traces"

Update the pipeline inputs to reference intent_tracer_opik and autogen_tracer_opik instead of the Langfuse equivalents, then run:

kedro run --pipeline autogen --params user_id=3