Chapter 48 · Instrument LLM Analytics
Subchapter 48.10
references/dspy.mdMarkdown4 KBView on GitHub
Required
Setting up analytics starts with installing the PostHog SDK. The DSPy integration uses PostHog’s LiteLLM callback.
pip install posthog2
Required
Install DSPy and LiteLLM. DSPy uses LiteLLM natively for provider access, and PostHog integrates with LiteLLM’s callback system.
pip install dspy litellm3
Required
Set your PostHog project token and host as environment variables, then configure LiteLLM to use PostHog as a callback handler. You can find your project token in your project settings (opens in a new tab).
import os
import dspy
import litellm
# Set PostHog environment variables
os.environ["POSTHOG_API_KEY"] = "<ph_project_token>"
os.environ["POSTHOG_API_URL"] = "https://us.i.posthog.com"
# Enable PostHog callbacks in LiteLLM
litellm.success_callback = ["posthog"]
litellm.failure_callback = ["posthog"]
# Configure DSPy to use an LLM
lm = dspy.LM("openai/gpt-5-mini", api_key="your_openai_api_key")
dspy.configure(lm=lm)How this works
DSPy uses LiteLLM under the hood for LLM provider access. By configuring PostHog as a LiteLLM callback, all LLM calls made through DSPy are automatically captured as $ai_generation events.
4
Required
Use DSPy as normal. PostHog automatically captures an $ai_generation event for each LLM call made through LiteLLM.
# Define a simple signature
class QA(dspy.Signature):
"""Answer the question."""
question: str = dspy.InputField()
answer: str = dspy.OutputField()
# Create and run a module
predictor = dspy.Predict(QA)
result = predictor(
question="What is a fun fact about hedgehogs?"
)
print(result.answer)You can expect captured $ai_generation events to have the following properties:
| Property | Description |
|---|---|
| $ai_model | The specific model, like gpt-5-mini or claude-4-sonnet |
| $ai_latency | The latency of the LLM call in seconds |
| $ai_time_to_first_token | Time to first token in seconds (streaming only) |
| $ai_tools | Tools and functions available to the LLM |
| $ai_input | List of messages sent to the LLM |
| $ai_input_tokens | The number of tokens in the input (often found in response.usage) |
| $ai_output_choices | List of response choices from the LLM |
| $ai_output_tokens | The number of tokens in the output (often found in response.usage) |
| $ai_total_cost_usd | The total cost in USD (input + output) |
| […] (opens in a new tab) | See full list (opens in a new tab) of properties |
Recommended
Confirm LLM events are being sent to PostHog
Let’s make sure LLM events are being captured and sent to PostHog. Under AI Observability, you should see rows of data appear in the Traces and Generations tabs.


5
Recommended
Now that you’re capturing AI conversations, continue with the resources below to learn what else AI Observability enables within the PostHog platform.
| Resource | Description |
|---|---|
| Basics (opens in a new tab) | Learn the basics of how LLM calls become events in PostHog. |
| Generations (opens in a new tab) | Read about the $ai_generation event and its properties. |
| Traces (opens in a new tab) | Explore the trace hierarchy and how to use it to debug LLM calls. |
| Spans (opens in a new tab) | Review spans and their role in representing individual operations. |
| Anaylze LLM performance (opens in a new tab) | Learn how to create dashboards to analyze LLM performance. |
Ask a question
HelpfulCould be better