Add documentation about reset index of dataset (#175)

* add documentation for reset index * add documentation at troubleshooting.md --------- Co-authored-by: jeffrey <[email protected]>
Marker-Inc-Korea · Feb 16, 2024 · 8ded58d · 8ded58d
1 parent c6e9224
commit 8ded58d
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 0 deletions.
diff --git a/docs/source/data_creation/data_format.md b/docs/source/data_creation/data_format.md
@@ -134,6 +134,11 @@ If you don't have any metadata, you can put an empty dictionary.
 It will create a default metadata for you. (like `last_modified_datetime` with `datetime.now()`)
 ```
 
+```{attention}
+Please check that you reset the indicies of your dataset files.
+If not, it can occur unexpected behavior.
+```
+
 ## Samples
 
 Looking for an example of dataset? 

diff --git a/docs/source/troubleshooting.md b/docs/source/troubleshooting.md
@@ -94,3 +94,12 @@ In our experiment, it occurred rate limit error when the batch size was 4.
 (Check out your tier and limit error at [here](https://platform.openai.com/account/limits).)
 ```
 
+### The length or row is different from the original data
+
+When the length of result is different from the original data, it is often caused by the index.
+
+You must reset the index of your dataset before running AutoRAG.
+
+```python
+df = df.reset_index(drop=True)
+```