Tracing LLM Inference With Phoenix For DSPy | An Intro To OpenTelemetry & Observability
Observability becomes important in the API driven ecosystem. There are multiple systems involved, and learning about a system that is not developed by your team can be daunting. Observability through Phoenix Server makes it easy.
Observability also becomes key when creating DSPy modules and Metrics. While developing the metrics for F1 Score for a company called Simply Discover, I had harnessed the power of observability and tracing.
Chapter Navigation:
0:00 Intro
0:15 Why Phoenix & Dspy
0:52 Necessity of Telemetry
1:40 Phoenix Intro
2:25 What to Expect
2:55 Purpose and Parts of Telemetry
4:20 Explaining part of Telemetry
7:50 Explaining parts of OTLP framework
9:30 Ways of Setting up Phoenix Server
16:40 Reviewing the Server UI
17:10 Instrumenting the DSPy in notebook
19:10 AI Integration to Phoenix
22:50 Sending, Seeing and Updating traces
26:20 Conclusion
27:10 Outro
The code for supporting notebook is present in the below git repo
https://github.com/insightbuilder/cod...
I believe you will like this video, and subscribe to the channel. Further uploads related to Big Data, Large Language models and Artificial Intelligence will be shared to your Youtube Dashboard Directly.
PS: Got a question or have a feedback on my content. Get in touch
By leaving a Comment in the video
Want to connect with me? https://cal.com/insight-kamalraj
@mail [email protected]
@medium / about
@github https://github.com/Kamalabot
Смотрите видео Tracing LLM Inference With Phoenix For DSPy | An Intro To OpenTelemetry & Observability онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь Kamalraj M M 19 Август 2024, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 132 раз и оно понравилось 1 людям.