-
Notifications
You must be signed in to change notification settings - Fork 101
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add RAG Pipeline tutorial for Haystack 2.0 #257
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall this was great! Clear explanations, quick to run through. Left one small suggestion but overall, lgtm.
I'm not sure if I'm qualified to actually approve tutorials yet - maybe you want another review from @TuanaCelik? Up to you!
"source": [ | ||
"## Overview\n", | ||
"\n", | ||
"This tutorial shows you how to create a generative question-answering pipeline using the retrieval-augmentation ([RAG](https://www.deepset.ai/blog/llms-retrieval-augmentation)) approach with Haystack 2.0. The process involves three main components: InMemoryBM25Retriever for fetching relevant documents, PromptBuilder for creating a template prompt, and GPTGenerator for generating responses.\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: it might be convenient for the reader to add links to the docs pages for these components
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
agree
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍
"id": "nenbo2SvycHd" | ||
}, | ||
"source": [ | ||
"> You can replace `GPTGenerator` in your pipeline with another `Generator`. Check out the full list of generators [here](https://docs.haystack.deepset.ai/v2.0/docs/generators)." |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's nice that you lowkey emphasized how Haystack is model-agnostic here :D
"source": [ | ||
"### Visualize the Pipeline\n", | ||
"\n", | ||
"Draw the pipeline with the `draw()` method to confirm the connections are correct. You can find the diagram in the Files section of this Colab." |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for specifying where you can find the file! That's very helpful for newbies.
"source": [ | ||
"## Overview\n", | ||
"\n", | ||
"This tutorial shows you how to create a generative question-answering pipeline using the retrieval-augmentation ([RAG](https://www.deepset.ai/blog/llms-retrieval-augmentation)) approach with Haystack 2.0. The process involves three main components: InMemoryBM25Retriever for fetching relevant documents, PromptBuilder for creating a template prompt, and GPTGenerator for generating responses.\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
agree
"source": [ | ||
"from haystack.telemetry import tutorial_running\n", | ||
"\n", | ||
"tutorial_running(27)" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We already have telemetry?
No description provided.