Skip to content

docs(llma): add Dedalus Labs and Cloudflare AI Gateway onboarding docs #54663

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
richardsolomou merged 8 commits into from
Apr 16, 2026
+476 −41
Merged

docs(llma): add Dedalus Labs and Cloudflare AI Gateway onboarding docs #54663

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
265e7a0
docs(llma): add Dedalus Labs and Cloudflare AI Gateway onboarding docs
richardsolomou Apr 15, 2026
c28d483
docs(llma): use real Cloudinary logos for Dedalus and Cloudflare AI G…
richardsolomou Apr 15, 2026
327548f
docs(llma): unify Anthropic model ID across Dedalus and Cloudflare ex…
richardsolomou Apr 15, 2026
73114c0
fix(llma): escape JSX braces and use fyi CalloutBox type
richardsolomou Apr 15, 2026
84aac35
fix(llma): use cf-aig-authorization header in Cloudflare AI Gateway docs
richardsolomou Apr 16, 2026
3efb350
Merge branch 'master' into docs/otel-llm-analytics-dedalus-and-cloudf…
richardsolomou Apr 16, 2026
bb5060b
Merge branch 'master' into docs/otel-llm-analytics-dedalus-and-cloudf…
richardsolomou Apr 16, 2026
2c41e44
test(storybook): update UI snapshots
tests-posthog[bot] Apr 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
209 changes: 209 additions & 0 deletions docs/onboarding/llm-analytics/cloudflare-ai-gateway.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,209 @@
import { OnboardingComponentsContext, createInstallation } from 'scenes/onboarding/OnboardingDocsContentWrapper'

import { StepDefinition } from '../steps'

export const getCloudflareAIGatewaySteps = (ctx: OnboardingComponentsContext): StepDefinition[] => {
const { CodeBlock, CalloutBox, Markdown, Blockquote, dedent, snippets } = ctx

const NotableGenerationProperties = snippets?.NotableGenerationProperties

return [
{
title: 'Install dependencies',
badge: 'required',
content: (
<>
<CalloutBox type="fyi" icon="IconInfo" title="Full working examples">
<Markdown>
See the complete
[Node.js](https://github.com/PostHog/posthog-js/tree/main/examples/example-ai-cloudflare-ai-gateway)
and
[Python](https://github.com/PostHog/posthog-python/tree/master/examples/example-ai-cloudflare-ai-gateway)
examples on GitHub.
</Markdown>
</CalloutBox>

<Markdown>Install the OpenTelemetry SDK, the OpenAI instrumentation, and the OpenAI SDK.</Markdown>

<CodeBlock
blocks={[
{
language: 'bash',
file: 'Python',
code: dedent`
pip install openai opentelemetry-sdk posthog[otel] opentelemetry-instrumentation-openai-v2
`,
},
{
language: 'bash',
file: 'Node',
code: dedent`
npm install openai @posthog/ai @opentelemetry/sdk-node @opentelemetry/resources @opentelemetry/instrumentation-openai
`,
},
]}
/>
</>
),
},
{
title: 'Set up OpenTelemetry tracing',
badge: 'required',
content: (
<>
<Markdown>
Configure OpenTelemetry to auto-instrument OpenAI SDK calls and export traces to PostHog.
PostHog converts `gen_ai.*` spans into `$ai_generation` events automatically.
</Markdown>

<CodeBlock
blocks={[
{
language: 'python',
file: 'Python',
code: dedent`
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.resources import Resource, SERVICE_NAME
from posthog.ai.otel import PostHogSpanProcessor
from opentelemetry.instrumentation.openai_v2 import OpenAIInstrumentor

resource = Resource(attributes={
SERVICE_NAME: "my-app",
"posthog.distinct_id": "user_123", # optional: identifies the user in PostHog
"foo": "bar", # custom properties are passed through
})

provider = TracerProvider(resource=resource)
provider.add_span_processor(
PostHogSpanProcessor(
api_key="<ph_project_token>",
host="<ph_client_api_host>",
)
)
trace.set_tracer_provider(provider)

OpenAIInstrumentor().instrument()
`,
},
{
language: 'typescript',
file: 'Node',
code: dedent`
import { NodeSDK } from '@opentelemetry/sdk-node'
import { resourceFromAttributes } from '@opentelemetry/resources'
import { PostHogSpanProcessor } from '@posthog/ai/otel'
import { OpenAIInstrumentation } from '@opentelemetry/instrumentation-openai'

const sdk = new NodeSDK({
resource: resourceFromAttributes({
'service.name': 'my-app',
'posthog.distinct_id': 'user_123', // optional: identifies the user in PostHog
foo: 'bar', // custom properties are passed through
}),
spanProcessors: [
new PostHogSpanProcessor({
apiKey: '<ph_project_token>',
host: '<ph_client_api_host>',
}),
],
instrumentations: [new OpenAIInstrumentation()],
})
sdk.start()
`,
},
]}
/>
</>
),
},
{
title: 'Call Cloudflare AI Gateway',
badge: 'required',
content: (
<>
<Markdown>
{dedent`
Cloudflare AI Gateway exposes an OpenAI-compatible \`compat\` endpoint at
\`https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat\`. Point the OpenAI SDK at
this URL with your upstream provider key (e.g. your OpenAI key) and pass your AI Gateway token via
the \`cf-aig-authorization\` header. Specify models as \`provider/model-id\` (for example
\`openai/gpt-5-mini\` or \`anthropic/claude-sonnet-4-5\`).
`}
</Markdown>

<CodeBlock
blocks={[
{
language: 'python',
file: 'Python',
code: dedent`
import openai

client = openai.OpenAI(
api_key="<openai_api_key>",
default_headers={
"cf-aig-authorization": "Bearer <cf_aig_token>",
},
base_url="https://gateway.ai.cloudflare.com/v1/<account_id>/<gateway_id>/compat",
)

response = client.chat.completions.create(
model="openai/gpt-5-mini",
max_completion_tokens=1024,
messages=[
{"role": "user", "content": "Tell me a fun fact about hedgehogs"}
],
)

print(response.choices[0].message.content)
`,
},
{
language: 'typescript',
file: 'Node',
code: dedent`
import OpenAI from 'openai'

const client = new OpenAI({
apiKey: '<openai_api_key>',
defaultHeaders: {
'cf-aig-authorization': 'Bearer <cf_aig_token>',
},
baseURL: 'https://gateway.ai.cloudflare.com/v1/<account_id>/<gateway_id>/compat',
})

const response = await client.chat.completions.create({
model: 'openai/gpt-5-mini',
max_completion_tokens: 1024,
messages: [{ role: 'user', content: 'Tell me a fun fact about hedgehogs' }],
})

console.log(response.choices[0].message.content)
`,
},
]}
/>

<Blockquote>
<Markdown>
{dedent`
**Note:** If you want to capture LLM events anonymously, omit the \`posthog.distinct_id\` resource attribute. See our docs on [anonymous vs identified events](https://posthog.com/docs/data/anonymous-vs-identified-events) to learn more.
`}
</Markdown>
</Blockquote>

<Markdown>
{dedent`
You can expect captured \`$ai_generation\` events to have the following properties:
`}
</Markdown>

{NotableGenerationProperties && <NotableGenerationProperties />}
</>
),
},
]
}

export const CloudflareAIGatewayInstallation = createInstallation(getCloudflareAIGatewaySteps)
Loading
Loading