PyPI · #1768 most downloaded on PyPI

opentelemetry-util-genai

5.0M downloads/moopen-telemetry/opentelemetry-python-contrib ↗New releases in your daily digest, changelog included.

OpenTelemetry GenAI Utils

Last release 10 days ago
24 Sep 2026
Ships fairly regularly
a new release about every 2 months
Unknown
no stable releases
Nothing withdrawn
no release was ever pulled
1 years old
7 releases · first in 2025

Release timeline

7 releases since 2025

20252026

One column per month.

Releases

1.2b024 Sept 2026pre-release
Nothing published for this version
1.1b020 Aug 2026pre-release
Nothing published for this version
1.0b09 Jul 2026pre-release
Nothing published for this version
0.4b01 May 2026pre-releaseBreaking

From the same repository

open-telemetry/opentelemetry-python-contrib

Add AgentInvocation type with invoke_agent span lifecycle (#4274)
Add metrics support for EmbeddingInvocation (#4377)
Add support for workflow in genAI utils handler. (#4366)
Enrich ToolCall type, breaking change: usage of ToolCall class renamed to ToolCallRequest (#4218)
Add EmbeddingInvocation span lifecycle support (#4219)
Populate schema_url on metrics (#4320)
Add workflow invocation type to genAI utils (#4310)
Check if upload works at startup in initializer of the UploadCompletionHook, instead of repeatedly failing on every upload (#4390).
Refactor public API: add factory methods (start_inference, start_embedding, start_tool, start_workflow) and invocation-owned lifecycle (invocation.stop() / invocation.fail(exc)); rename LLMInvocation → InferenceInvocation and ToolCall → ToolInvocation. Existing usages remain fully functional via deprecated aliases. (#4391)
TelemetryHandler now accepts a completion_hook parameter and calls it after each LLM invocation, passing inputs, outputs, the active span, and the log record. Content capture is enabled automatically when a real hook is configured. (#4315)
Add metrics to ToolInvocations (#4443)
Wrap completion hooks loaded via load_completion_hook so exceptions raised by on_completion are logged and swallowed instead of propagating to instrumentation call sites.

Open source →

Additional notes

opentelemetry-util-genai 0.4b0

Compare

Choose a tag to compare

Open source →

0.3b020 Feb 2026pre-release

Add gen_ai.tool_definitions to completion hook

Add gen_ai.tool_definitions to completion hook (#4181)
Add support for emitting inference events and enrich message types. (#3994)
Add support for server.address, server.port on all signals and additional metric-only attributes (#4069)
Log error when fsspec fails to be imported instead of silently failing (#4037).
Minor change to check LRU cache in Completion Hook before acquiring semaphore/thread (#3907).
Add environment variable for genai upload hook queue size (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3943)
Add more Semconv attributes to LLMInvocation spans. (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3862)
Limit the upload hook thread pool to 64 workers (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3944)
Add metrics to LLMInvocation traces (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3891)
Add parent class genAI invocation (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3889)

Open source →

Additional notes

Added

opentelemetry-opamp-client: support non-JSON effective config bodies (#4536)

Open source →

Additional notes

Add gen_ai.tool_definitions to completion hook (#4181)
Add support for emitting inference events and enrich message types. (#3994)
Add support for server.address, server.port on all signals and additional metric-only attributes (#4069)
Log error when fsspec fails to be imported instead of silently failing (#4037).
Minor change to check LRU cache in Completion Hook before acquiring semaphore/thread (#3907).
Add environment variable for genai upload hook queue size (#3943)
Add more Semconv attributes to LLMInvocation spans. (#3862)
Limit the upload hook thread pool to 64 workers (#3944)
Add metrics to LLMInvocation traces (#3891)
Add parent class genAI invocation (#3889)

Open source →

Additional notes

opentelemetry-opamp-client 0.3b0

Compare

Choose a tag to compare

Open source →

0.2b015 Oct 2025pre-release

Add jsonlines support to fsspec uploader

Add jsonlines support to fsspec uploader (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3791)
Rename "fsspec_upload" entry point and classes to more generic "upload" (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3798)
Record content-type and use canonical paths in fsspec genai uploader (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3795)
Make inputs / outputs / system instructions optional params to on_completion, (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3802). - Use a SHA256 hash of the system instructions as it's upload filename, and check if the file exists before re-uploading it, (https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3814).

Open source →

Additional notes

Add jsonlines support to fsspec uploader (#3791)
Rename "fsspec_upload" entry point and classes to more generic "upload" (#3798)
Record content-type and use canonical paths in fsspec genai uploader (#3795)
Make inputs / outputs / system instructions optional params to on_completion, (#3802).
Use a SHA256 hash of the system instructions as it's upload filename, and check if the file exists before re-uploading it, (#3814).

Open source →

0.1b025 Sept 2025pre-release

Add completion hook to genai utils to implement semconv v1.37.

Add completion hook to genai utils to implement semconv v1.37.

Includes a hook implementation using fsspec to support uploading to various pluggable backends.

(#3780) (#3752) (#3759) (#3763)
Add a utility to parse the OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT environment variable. Add gen_ai_latest_experimental as a new value to the Sem Conv stability flag (#3716).

Open source →

Additional notes

Add completion hook to genai utils to implement semconv v1.37.

Includes a hook implementation using fsspec to support uploading to various pluggable backends.

(#3780) (#3752) (#3759) (#3763)
Add a utility to parse the OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT environment variable. Add gen_ai_latest_experimental as a new value to the Sem Conv stability flag (#3716).

Added

Generate Spans for LLM invocations
Helper functions for starting and finishing LLM invocations

Open source →