Add LangChain integration example

[kmadan]

Goal

Create examples/langchain-app/ showing how to capture LangChain agent runs into an AICertify contract and evaluate them — without users having to write the capture logic themselves.

Why this matters

LangChain is the most common LLM framework in Python. A documented integration pattern unblocks many AI teams from running compliance checks at all.

Files likely involved

• New: examples/langchain-app/ (six-file shape)
• Optionally: a thin callback handler under aicertify/integrations/langchain.py if a clean pattern emerges
• examples/README.md table entry

Acceptance criteria

• A runnable LangChain app (e.g. a RetrievalQA chain or a tools-using agent)
• A callback handler that records each Human/AI message pair into an AICertify contract
• An run.py that runs the app, then runs AICertify, then prints the report path
• README documents the callback pattern and the gotchas (streaming, tool calls)

Help

Comment here if you want to work on this and I will help you get started. First-time contributors are welcome — open a draft PR early and I'll review.