feat(examples): migrate AI examples to OpenTelemetry instrumentation

[richardsolomou]

Problem

Our AI examples use PostHog's direct SDK wrappers (posthog.ai.openai, posthog.ai.anthropic, etc.) for tracking LLM calls. We want to silently deprecate these in favor of standard OpenTelemetry auto-instrumentation, which is more portable and follows industry conventions.

Changes

Migrates Python AI examples from PostHog wrappers to OpenTelemetry auto-instrumentation:

• OpenAI-compatible providers (Groq, DeepSeek, Mistral, xAI, Together AI, Ollama, Cohere, Hugging Face, Perplexity, Cerebras, Fireworks AI, OpenRouter, Helicone, Vercel AI Gateway, Portkey) → opentelemetry-instrumentation-openai-v2
• OpenAI (all files), Azure OpenAI, Instructor, Autogen, Mirascope, Semantic Kernel, smolagents → opentelemetry-instrumentation-openai-v2
• Anthropic (chat, streaming, extended thinking) → opentelemetry-instrumentation-anthropic
• LangChain, LangGraph → opentelemetry-instrumentation-langchain
• LlamaIndex → opentelemetry-instrumentation-llamaindex
• Gemini → opentelemetry-instrumentation-google-generativeai

All OTel-based examples set resource attributes to demonstrate the full feature set:

resource = Resource(
    attributes={
        SERVICE_NAME: "example-groq-app",
        "posthog.distinct_id": "example-user",
        "foo": "bar",
        "conversation_id": "abc-123",
    }
)

These map to distinct_id and custom event properties via PostHog's OTLP ingestion endpoint.

Kept as-is: CrewAI (uses LiteLLM callbacks, internally manages its own TracerProvider), LiteLLM/DSPy (use LiteLLM's built-in PostHog callback), OpenAI Agents (uses dedicated posthog.ai.openai_agents.instrument()), Pydantic AI (already OTel via Agent.instrument_all()), AWS Bedrock (already OTel via opentelemetry-instrumentation-botocore).

Key implementation details:

• Uses SimpleSpanProcessor instead of BatchSpanProcessor so spans export immediately without needing provider.shutdown()
• # noqa: E402 on intentional late imports after Instrumentor().instrument() calls
• Azure OpenAI example uses the generic gpt-4o model name instead of a deployment-specific one

How did you test this code?

Manually ran each example against real provider API keys via llm-analytics-apps/run-examples.sh to verify:

1. Each script runs successfully end-to-end
2. Traces arrive at PostHog as $ai_generation events
3. Resource attributes (posthog.distinct_id, foo, conversation_id) flow through as event properties
4. distinct_id is correctly set on each event

All examples passing ruff format and ruff check.

This is an agent-authored PR — I haven't manually tested each provider end-to-end beyond spot checks, though all examples follow the same pattern and the migration was verified on several providers.

Publish to changelog?

No

Docs update

The onboarding docs will be updated separately in PostHog/posthog#53668 and PostHog/posthog.com#16236.

🤖 LLM context

Co-authored with Claude Code. Related PRs:

• feat(examples): migrate AI examples to OpenTelemetry instrumentation posthog-js#3349 (Node.js examples)
• docs(llma): migrate onboarding docs to OpenTelemetry auto-instrumentation posthog#53668 (in-app onboarding docs)
• docs(llma): update TOC for OTel onboarding migration posthog.com#16236 (docs.posthog.com TOC updates)

[github-actions]

posthog-python Compliance Report

Date: 2026-04-08 14:49:10 UTC
Duration: 171ms

✅ All Tests Passed!

0/0 tests passed

---

[socket-security]

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	anthropic@​0.87.0
	opentelemetry-sdk@​1.39.1
	opentelemetry-sdk@​1.40.0
	requests@​2.33.1
	opentelemetry-exporter-otlp-proto-http@​1.39.1
	opentelemetry-exporter-otlp-proto-http@​1.40.0
	opentelemetry-exporter-otlp-proto-http@​1.34.1
	opentelemetry-sdk@​1.34.1
	opentelemetry-instrumentation-anthropic@​0.57.0

View full report

[greptile-apps]

Vulnerabilities

No security concerns identified. API keys are sourced exclusively from environment variables (os.environ[...]) and are not hardcoded. The OTLP exporter sends keys in an HTTP Authorization header over HTTPS to the PostHog endpoint, which is the expected pattern.

Prompt To Fix All With AI

This is a comment left during a code review.
Path: examples/example-ai-azure-openai/chat.py
Line: 28

Comment:
**Unrecognized Azure model name**

`grok-4-20-non-reasoning` does not correspond to any model ID in Azure AI Foundry's catalog. The available xAI Grok names there are `grok-4`, `grok-4-fast-non-reasoning`, `grok-4-fast-reasoning`, `grok-4.1-fast-non-reasoning`, etc. This looks like a typo or an accidental change — using this value in an example will mislead anyone who tries to replicate it and will fail against any standard deployment. This change also appears unrelated to the OTel migration that is the purpose of this PR.

```suggestion
    model="gpt-4o",
```

How can I resolve this? If you propose a fix, please make it concise.

---

This is a comment left during a code review.
Path: examples/example-ai-openai/transcription.py
Line: 31-34

Comment:
**Inconsistent `provider.shutdown()` on early exit path**

This `provider.shutdown()` before `sys.exit(0)` is the only remaining shutdown call across all 28 migrated examples. The PR description explicitly states that `SimpleSpanProcessor` is used so spans export immediately without needing `provider.shutdown()`. Remove it for consistency.

```suggestion
if not os.path.exists(audio_path):
    print(f"Skipping: audio file not found at '{audio_path}'")
    print("Set AUDIO_PATH to a valid audio file (mp3, wav, m4a, etc.)")
    sys.exit(0)
```

How can I resolve this? If you propose a fix, please make it concise.

_{Reviews (1): Last reviewed commit: "style(examples): add noqa: E402 for inte..." | Re-trigger Greptile}

[andrewm4894]

i think the otel examples should be as full featured as possible and show stuff like setting distinct id and any custom foo-bar properties - am i missing that or something?