๐ญ OpenLIT
OpenTelemetry-native Observability and Evals for LLMs & GPUs
Embedchain now supports integration with OpenLIT.
Getting Started
1. Set environment variables
# Setting environment variable for OpenTelemetry destination and authetication.
export OTEL_EXPORTER_OTLP_ENDPOINT = "YOUR_OTEL_ENDPOINT"
export OTEL_EXPORTER_OTLP_HEADERS = "YOUR_OTEL_ENDPOINT_AUTH"
2. Install the OpenLIT SDK
Open your terminal and run:
pip install openlit
3. Setup Your Application for Monitoring
Now create an app using Embedchain and initialize OpenTelemetry monitoring
from embedchain import App
import OpenLIT
# Initialize OpenLIT Auto Instrumentation for monitoring.
openlit.init()
# Initialize EmbedChain application.
app = App()
# Add data to your app
app.add("https://en.wikipedia.org/wiki/Elon_Musk")
# Query your app
app.query("How many companies did Elon found?")
4. Visualize
Once youโve set up data collection with OpenLIT, you can visualize and analyze this information to better understand your applicationโs performance:
-
Using OpenLIT UI: Connect to OpenLITโs UI to start exploring performance metrics. Visit the OpenLIT Quickstart Guide for step-by-step details.
-
Integrate with existing Observability Tools: If you use tools like Grafana or DataDog, you can integrate the data collected by OpenLIT. For instructions on setting up these connections, check the OpenLIT Connections Guide.
Was this page helpful?