openinference-instrumentation-haystack
OpenInference Haystack Instrumentation
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained (release 7 days ago), production-stable, has no known vulnerabilities, and low install friction. It solves a real observability gap for Haystack users. Install it if you need to monitor or debug Haystack LLM pipelines; skip it only if you have no observability requirements or use a different instrumentation approach.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an OpenTelemetry collector endpoint (e.g., Arize Phoenix running locally or remotely) to receive and display traces.
- Low friction install with seven runtime dependencies.
- Actively maintained with a release 7 days ago and recent commits; marked Production/Stable and supports Python 3.10 through 3.14.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 (permissive): you can use, modify, and distribute this package freely in commercial and private projects, provided you include a copy of the license and state significant changes.
last release 2026-08-07 (7 days) · last repo commit 2026-08-14 · 1,147 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 333,652 downloads/mo, #7,498 on PyPI
Alternatives
Verify before relying
pip install openinference-instrumentation-haystack
from openinference.instrumentation.haystack import HaystackInstrumentor
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry import trace as trace_api
tracer_provider = trace_sdk.TracerProvider()
trace_api.set_tracer_provider(tracer_provider)
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter("http://localhost:6006/v1/traces")))
HaystackInstrumentor().instrument()- Whether instrumentation covers all Haystack component types or only a subset (e.g., PromptBuilder, OpenAIGenerator mentioned but full coverage unclear).
- Performance overhead of instrumentation on typical Haystack pipeline execution.
- Whether custom Haystack components are automatically instrumented or require manual span setup.
What it is and what it does
This package wraps Haystack pipelines and components with OpenTelemetry instrumentation, automatically capturing execution traces and sending them to an observability backend. It integrates with the OpenInference semantic conventions to standardize how LLM application traces are structured, making it easy to monitor Haystack-based LLM systems in tools like Arize Phoenix or Arize AX without modifying your application code.
The instrumentation is applied once via a single call to HaystackInstrumentor().instrument(), after which all Haystack components in your pipeline emit traces automatically. You configure where traces are sent by setting up an OpenTelemetry tracer provider with a span processor and exporter (typically OTLP HTTP to a local or remote collector). The package depends on openinference-instrumentation, opentelemetry-api, opentelemetry-instrumentation, and their semantic convention libraries to handle the tracing plumbing.
Use it for
- Monitor Haystack LLM pipeline execution in real time by sending traces to Arize Phoenix running locally on your development machine.
- Debug slow or failing Haystack components by inspecting detailed span attributes (prompts, model calls, latencies) in an observability UI.
- Track production Haystack applications by exporting traces to a centralized OpenTelemetry collector for long-term analysis and alerting.
- Correlate Haystack pipeline behavior with upstream or downstream systems by using OpenTelemetry's trace context propagation.
- Audit LLM application behavior by capturing what prompts were sent, which models were called, and how long each step took.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained (release 7 days ago), production-stable, has no known vulnerabilities, and low install friction. It solves a real observability gap for Haystack users. Install it if you need to monitor or debug Haystack LLM pipelines; skip it only if you have no observability requirements or use a different instrumentation approach.
Install
openinference-instrumentation-haystack on PyPI
Before you install
Low friction install with seven runtime dependencies. Actively maintained with a release 7 days ago and recent commits; marked Production/Stable and supports Python 3.10 through 3.14.
Requires an OpenTelemetry collector endpoint (e.g., Arize Phoenix running locally or remotely) to receive and display traces.
License in practice
Apache-2.0 (permissive): you can use, modify, and distribute this package freely in commercial and private projects, provided you include a copy of the license and state significant changes.
Quickstart
pip install openinference-instrumentation-haystack
from openinference.instrumentation.haystack import HaystackInstrumentor
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry import trace as trace_api
tracer_provider = trace_sdk.TracerProvider()
trace_api.set_tracer_provider(tracer_provider)
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter("http://localhost:6006/v1/traces")))
HaystackInstrumentor().instrument()Verify before relying
- Whether instrumentation covers all Haystack component types or only a subset (e.g., PromptBuilder, OpenAIGenerator mentioned but full coverage unclear).
- Performance overhead of instrumentation on typical Haystack pipeline execution.
- Whether custom Haystack components are automatically instrumented or require manual span setup.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesopeninference-instrumentationopeninference-semantic-conventionsopentelemetry-apiopentelemetry-instrumentationopentelemetry-semantic-conventionstyping-extensionswrapt |
| Maintenance | Actively maintained 7 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 333,652 / month, #7,498 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: openinference_instrumentation_haystack-0.1.36-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “haystack instrumentation opentelemetry”
- openinference-instrumentation-haystackAuto-instruments Haystack LLM pipelines and components to emit…
- opentelemetry-instrumentation-haystackAdds distributed tracing to Haystack LLM applications by…
- langwatchLangWatch is a Python SDK for instrumenting and monitoring LLM…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also openinference-instrumentation-anthropic · openinference-instrumentation-agno · openinference-instrumentation-llama-index · arize · openinference-instrumentation-google-genai · openinference-instrumentation-litellm · haystack-ai · farm-haystack · haystack-experimental · openinference-instrumentation-dspy