From the course: LLMOps in Practice: A Deep Dive
Unlock the full course today
Join today to access over 24,900 courses taught by industry experts.
Hands-on logging - Python Tutorial
From the course: LLMOps in Practice: A Deep Dive
Hands-on logging
So to this point, we've now created the fully RAGable version of our application, our chatbot. We were able to take a Chroma DB, take a book, slice it up, store it in the Chroma DB, and then change our chatbot to be able to search that for context that would add to our chat message so that we were getting great information back. So now, as we move on in the app's journey, we've been looking at logging metrics and version management. Previously, we looked at logging and I want to now start getting hands-on and showing you the code for logging. This is going to be using Winston, and we're going to start by taking a look at the logger.js file that we spoke about in the slides and how to implement that in Winston. So if you're working from the start directory which we provided in the GitHub, your logger.js is going to look like this. So I've done some of the environment for you, for example, showing what to do if it's in production, creating the stream object, and outputting it. But…
Contents
-
-
-
-
-
-
(Locked)
Extending RAG with ops2m 9s
-
(Locked)
Logging3m 38s
-
(Locked)
Hands-on logging10m 23s
-
(Locked)
Metrics5m 28s
-
(Locked)
Hands-on metrics10m 20s
-
(Locked)
Version management4m 50s
-
(Locked)
Hands-on version management13m 32s
-
(Locked)
RAG Ops: Updating the data4m 37s
-
(Locked)
Hands-on RAG ops9m 22s
-
(Locked)
RAG in action: Exercise1m 4s
-
(Locked)
-