Add NVIDIA medical chatbot example #62
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
annthurium
requested review from
TuanaCelik,
bilgeyucel,
silvanocerza and
shadeMe
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
There was a problem hiding this comment.
Writing a custom component didn't work when I only had nvidia-haystack installed. I ran into some import errors. Maybe that's a bug?
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
Line #3. !pip install nvidia-haystack==0.0.1
I believe you dont need the exclamation mark here
Reply via ReviewNB
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
I dont think many users know about the userdata.get functionality (also, probably not runnable outside of Google Colab). You can replace it with getpass
Reply via ReviewNB
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
If you have the context, it would be nice to include information about the parameters you used here. What's bad,stop ,seed and why we provided None
Reply via ReviewNB
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
Line #27. keyword_llm.warm_up()
JFYI, you don't need to call warm_up if you're going to use these generators in a pipeline as Pipeline calls it when it runs but no harm keeping these calls
Reply via ReviewNB
| @@ -0,0 +1,322 @@ | |||
| { | |||
There was a problem hiding this comment.
No description provided.