Description
Traceloop would like to offer the donation of OpenLLMetry instrumentation packages to the OpenTelemetry project.
OpenLLMetry is an open-source project that pioneered the use of OpenTelemetry to instrument and monitor GenAI-based applications and workloads. With over 40 instrumentations ranging from foundation model providers like OpenAI, Anthropic, Bedrock and others; through frameworks like LangChain, LlamaIndex and CrewAI; to vector databases like Pinecone, Chroma and others.
As we standardize GenAI semantic conventions we'd like to gradually donate mature instrumentations back to the OpenTelemetry eco-system where they can be co-maintained by us and the rest of the community/
Benefits to the OpenTelemetry community
The donation of the OpenLLMetry instrumentations would fill the gap in OpenTelemetry's GenAI instrumentations: from foundation models, to vector databases to frameworks.
In addition, with this donation, the OpenTelemetry community would gain a team of GenAI domain experts to (co-)maintain and advance OpenTelemetry's GenAI efforts.
Reasons for donation
Traceloop is dedicated to OpenTelemetry's vision to make it the single, ubiquitous standard and framework for Observability. With this donation, we strive to help OpenTelemetry to successfully expand into the area of generative AI by donating one of the industry's leading GenAI open-source projects to OpenTelemetry's ecosystem.
Repository
https://github.com/traceloop/openllmetry
Existing usage
The instrumentations and the SDK is being used by tens of thousands of users (large and small scale) in production environments since its launch on October 2023.
Maintenance
In case of a successful donation Traceloop team is dedicated to further (co-)maintain and evolve OTel's GenAI instrumentations and help drive its adoption as an industry standard for collecting profiling data in production.
Licenses
All code is licensed with Apache 2.0
Trademarks
The name "Traceloop" and "OpenLLMetry" name may be used throughout the repository.
Other notes
No response
Description
Traceloop would like to offer the donation of OpenLLMetry instrumentation packages to the OpenTelemetry project.
OpenLLMetry is an open-source project that pioneered the use of OpenTelemetry to instrument and monitor GenAI-based applications and workloads. With over 40 instrumentations ranging from foundation model providers like OpenAI, Anthropic, Bedrock and others; through frameworks like LangChain, LlamaIndex and CrewAI; to vector databases like Pinecone, Chroma and others.
As we standardize GenAI semantic conventions we'd like to gradually donate mature instrumentations back to the OpenTelemetry eco-system where they can be co-maintained by us and the rest of the community/
Benefits to the OpenTelemetry community
The donation of the OpenLLMetry instrumentations would fill the gap in OpenTelemetry's GenAI instrumentations: from foundation models, to vector databases to frameworks.
In addition, with this donation, the OpenTelemetry community would gain a team of GenAI domain experts to (co-)maintain and advance OpenTelemetry's GenAI efforts.
Reasons for donation
Traceloop is dedicated to OpenTelemetry's vision to make it the single, ubiquitous standard and framework for Observability. With this donation, we strive to help OpenTelemetry to successfully expand into the area of generative AI by donating one of the industry's leading GenAI open-source projects to OpenTelemetry's ecosystem.
Repository
https://github.com/traceloop/openllmetry
Existing usage
The instrumentations and the SDK is being used by tens of thousands of users (large and small scale) in production environments since its launch on October 2023.
Maintenance
In case of a successful donation Traceloop team is dedicated to further (co-)maintain and evolve OTel's GenAI instrumentations and help drive its adoption as an industry standard for collecting profiling data in production.
Licenses
All code is licensed with Apache 2.0
Trademarks
The name "Traceloop" and "OpenLLMetry" name may be used throughout the repository.
Other notes
No response