phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 21:48:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(telemetry): add integration and unit tests for otel provider

Browse source
This commit is contained in:
Emilio Garcia 2025-10-02 17:46:53 -04:00
parent e45e77f7b0
commit 9a0294ab4f
11 changed files with 1052 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/inline/telemetry/otel/README.md
View file

@ -10,17 +10,23 @@ First, bootstrap and install all necessary libraries for open telemtry:
uv run opentelemetry-bootstrap -a requirements | uv pip install --requirement -
```
Then, run with automatic code injection:
Make sure you export required environment variables for open telemetry:
```
uv run opentelemetry-instrument llama stack run --config myconfig.yaml
export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
export OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318"
```
### Excluded Fast API URLs
If you want certian endpoints to be ignored from the fast API telemetry, set the following environment variable:
```
export OTEL_PYTHON_FASTAPI_EXCLUDED_URLS="client/.*/info,healthcheck"
```
#### Environment Variables
Finaly, run Llama Stack with automatic code injection:
```
uv run opentelemetry-instrument llama stack run --config myconfig.yaml
```
#### Open Telemetry Configuration Environment Variables
Environment Variables: https://opentelemetry.io/docs/specs/otel/configuration/sdk-environment-variables/