Skip to content

Commit

Permalink
Update README.md for data links
Browse files Browse the repository at this point in the history
  • Loading branch information
chtlp authored Apr 14, 2024
1 parent 1b9adf0 commit 36ba6a6
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,15 +53,15 @@ with open("some-file-name-to-store-result.jsonl", "w") as f:

1. RAG with FAISS

- Download the index for wikipedia (around 26G). (index is still uploading)
- Download the index file for wikipedia [here](https://myscale-datasets.s3.ap-southeast-1.amazonaws.com/RQA/IVFSQ_IP.index) (around 26G).
- Download dataset from huggingface with our code (around 140G). It will automatically download the dataset for the first time.
- Set the index path to the download index.


2. RAG with MyScale

- Download the data for wikipedia in parquet. (data is still uploading)
- Insert the data and create vector index
- Download the data for wikipedia in parquet [here](https://myscale-datasets.s3.ap-southeast-1.amazonaws.com/wiki_abstract_with_vector.parquet).
- Insert the data and create vector index. You can also directly use our free pod hosting the Wikipedia data as described [here](https://github.com/myscale/ChatData?tab=readme-ov-file#data-schema).


## Result with Simple RAG pipeline
Expand Down Expand Up @@ -310,4 +310,4 @@ with open("some-file-name-to-store-result.jsonl", "w") as f:
</td>
</tr>
</tfoot>
</table>
</table>

0 comments on commit 36ba6a6

Please sign in to comment.