cookbook: add MLflow observability integration via OpenInference

[ysolanky]

Summary

Add a cookbook example showing how to instrument Agno agents with OpenInference and send traces to an MLflow Tracking Server via OTLP.

Follows the same pattern as existing observability integrations (Langfuse, LangSmith, Opik, etc.) using OTLPSpanExporter pointed at MLflow's /api/2.0/mlflow/traces endpoint.

Type of change

• New feature
• Other: Cookbook example

---

Checklist

• Code complies with style guidelines
• Ran format/validation scripts (./scripts/format.sh and ./scripts/validate.sh)
• Self-review completed
• Documentation updated (comments, docstrings)
• Examples and guides: Relevant cookbook examples have been included or updated (if applicable)
• Tested in clean environment
• Tests added/updated (if applicable)

---

Additional Notes

Files added/changed:

• cookbook/92_integrations/observability/mlflow_via_openinference.py — new cookbook
• cookbook/92_integrations/observability/README.md — added to integrations list

Usage:

# Start MLflow tracking server
mlflow server --host 127.0.0.1 --port 5000

# Run the cookbook
.venvs/demo/bin/python cookbook/92_integrations/observability/mlflow_via_openinference.py

Dependencies: mlflow, opentelemetry-exporter-otlp-proto-http, openinference-instrumentation-agno

🤖 Generated with Claude Code

[kausmeows]

also this- agno-agi/docs#330 (comment)

the user had a different type of cookbook, so we might want to add that one as well.

[kausmeows]

Suggested change

	pip install mlflow opentelemetry-exporter-otlp-proto-http openinference-instrumentation-agno
	pip install -U mlflow opentelemetry-exporter-otlp-proto-http openinference-instrumentation-agno