mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-12-29 07:59:27 +00:00
6e580e4430
* feat: implement pipeline tracing * tests: improve test setup for spying tracer * feat: implement util for type coercion * fix: trace a after checking pipeline output * docs: add release notes * docs: drop unused imports * refactor: simplify getting raw span * refactor: implement `ProxyTracer`
90 lines
3.1 KiB
YAML
90 lines
3.1 KiB
YAML
---
|
|
features:
|
|
- |
|
|
Added option to instrument pipeline and component runs.
|
|
This allows users to observe their pipeline runs and component runs in real-time via their chosen observability
|
|
tool. Out-of-the-box support for OpenTelemetry and Datadog will be added in separate contributions.
|
|
|
|
Example usage for [OpenTelemetry](https://opentelemetry.io/docs/languages/python/):
|
|
|
|
1. Install OpenTelemetry SDK and exporter:
|
|
```bash
|
|
pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
|
|
```
|
|
|
|
2. Configure OpenTelemetry SDK with your tracing provider and exporter:
|
|
```python
|
|
from opentelemetry.sdk.resources import SERVICE_NAME, Resource
|
|
|
|
from opentelemetry import trace
|
|
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from opentelemetry.sdk.trace.export import BatchSpanProcessor
|
|
|
|
# Service name is required for most backends
|
|
resource = Resource(attributes={
|
|
SERVICE_NAME: "haystack"
|
|
})
|
|
|
|
traceProvider = TracerProvider(resource=resource)
|
|
processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
|
|
traceProvider.add_span_processor(processor)
|
|
trace.set_tracer_provider(traceProvider)
|
|
|
|
tracer = traceProvider.get_tracer("my_application")
|
|
|
|
|
|
3. Create tracer
|
|
```python
|
|
import contextlib
|
|
from typing import Optional, Dict, Any, Iterator
|
|
|
|
from opentelemetry import trace
|
|
from opentelemetry.trace import NonRecordingSpan
|
|
|
|
from haystack.tracing import Tracer, Span
|
|
from haystack.tracing import utils as tracing_utils
|
|
import opentelemetry.trace
|
|
|
|
|
|
class OpenTelemetrySpan(Span):
|
|
def __init__(self, span: opentelemetry.trace.Span) -> None:
|
|
self._span = span
|
|
|
|
def set_tag(self, key: str, value: Any) -> None:
|
|
coerced_value = tracing_utils.coerce_tag_value(value)
|
|
self._span.set_attribute(key, coerced_value)
|
|
|
|
|
|
class OpenTelemetryTracer(Tracer):
|
|
def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
|
|
self._tracer = tracer
|
|
|
|
@contextlib.contextmanager
|
|
def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
|
|
with self._tracer.start_as_current_span(operation_name) as span:
|
|
span = OpenTelemetrySpan(span)
|
|
if tags:
|
|
span.set_tags(tags)
|
|
|
|
yield span
|
|
|
|
def current_span(self) -> Optional[Span]:
|
|
current_span = trace.get_current_span()
|
|
if isinstance(current_span, NonRecordingSpan):
|
|
return None
|
|
|
|
return OpenTelemetrySpan(current_span)
|
|
|
|
```
|
|
|
|
4. Use the tracer with Haystack:
|
|
```python
|
|
from haystack import tracing
|
|
|
|
haystack_tracer = OpenTelemetryTracer(tracer)
|
|
tracing.enable_tracing(haystack_tracer)
|
|
```
|
|
|
|
5. Run your pipeline
|