Add notebook demonstrating RAG with LlamaIndex #52
Conversation
This notebook is a "spin-off" of sorts from @MKhalusova's notebook on RAG with LangChain and Zephyr. Here, we demonstrate the use of LlamaIndex as a counterpart to LangChain, demonstrating its flexibility for RAG-specific use cases.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
Thanks in advance for the review @MKhalusova 😇 |
There was a problem hiding this comment.
Really nice notebook! Since you mention that the documents have not been chunked during loading, perhaps, it's worth mentioning when the chunking happens.
As I understand, the documents are chunked when ingested into the VectorStoreIndex (feel free to correct if that's wrong).
Maybe also worth mentioning the defaults for the chunk size and overlap.
Good catch. Added a note to that effect.
Done. |
|
Sorry about that! Accidentally commit-all'd. Will remove.
…On Mon, Mar 4, 2024, at 16:12, Maria Khalusova wrote:
***@***.**** commented on this pull request.
The notebook looks good, but I see that you added the `*.epub` files. There's no need to keep them in the repo as you give the readers instructions on how to get them. Let's remove these files.
—
Reply to this email directly, view it on GitHub <#52 (review)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAOX2I3VB3LGMPBKIKRXA3DYWTPSNAVCNFSM6AAAAABECPUCN2VHI2DSMVQWIX3LMV43YUDVNRWFEZLROVSXG5CSMV3GSZLXHMYTSMJVGM2TQMJQHE>.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
What does this PR do?
This notebook is a "spin-off" of sorts from
@MKhalusova's notebook on RAG with LangChain and
Zephyr. Here, we demonstrate the use of LlamaIndex as a counterpart to LangChain, demonstrating its
flexibility for RAG-specific use cases.
Who can review?
@MKhalusova