OSS Observability for Instructor - Langf...
llmql should work via decorator, no dedicated integration planned yet, please add to langfuse.com/ideas to help track the overall interest for this
jxnl/instructor wraps the openai sdk, this it should be easy to monitor with the openai integration + decorator. See a very brief example here (not using the decorator though): https://langfuse.com/docs/integrations/instructor
PrefectHQ/marvin does not seem to support custom openai clients, I'd start with tracking it vai the decorator and please add to langfuse.com/ideas if you have an idea for a more native implementation
OSS Observability for Instructor - Langfuse
Open-source observability for Instructor, a popular library to get structured (JSON, Pydantic) LLM outputs.
6 Replies
then a related question, what does dedicated integration add (such as one for Mirascope) as compared to decorator?
And what about support for DSPy?
it adds that it auaotmatically uses the langfuse wrapped openai if used with
with_langfuse as well as adding the langfuse decorator to a couple of classmethods automatically (e.g. to extract the model name and token counts)has been on the backlog for quite some time but not yet planned as we currently put a lot of effort into shipping v3: https://github.com/orgs/langfuse/discussions/1902
GitHub
Upcoming architecture changes for Langfuse 3.0 · langfuse · Discuss...
Hi all, Langfuse is growing a lot, both in feature scope as well as in usage on single instances. Thus we plan for a couple of changes that will be released in Langfuse v3. We are currently require...
would love to build the integration but do not have time right now, are you interested in contributing to this?
Outlines
Structured text generation with LLMs
it does not seem like it exposes the openai client. please add all intgerations that you'd like to see here in order to track overall itnerest for this: langfuse.com/ideas