aws-samples / aws-samples/rag-workshop-amazon-bedrock-knowledge-bases

Cannot download tornadoes_report.pdf

Open
#4 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
64
Forks
34
PR merge metrics
No merged PRs in 30d

Description

In `04-multi-modal-rag/text-images-rag-using-kb/text_images_rag_using_kb.ipynb` cannot download the source file `https://sgp.fas.org/crs/misc/IF12695.pdf` as the request returns HTTP code 202 Accepted.

I tried with wget and received a 0 bytes file:

```
!wget https://sgp.fas.org/crs/misc/IF12695.pdf --no-check-certificate -O ./mm-data/tornadoes_report.pdf
--2025-09-29 05:18:43-- https://sgp.fas.org/crs/misc/IF12695.pdf
Resolving sgp.fas.org (sgp.fas.org)... 99.84.66.25, 99.84.66.23, 99.84.66.92, ...
Connecting to sgp.fas.org (sgp.fas.org)|99.84.66.25|:443... connected.
HTTP request sent, awaiting response... 202 Accepted
Length: 0 [text/html]
Saving to: ‘./mm-data/tornadoes_report.pdf’

./mm-data/tornadoes [ <=> ] 0 --.-KB/s in 0s

2025-09-29 05:18:43 (0.00 B/s) - ‘./mm-data/tornadoes_report.pdf’ saved [0/0]
```

I was able to download the file using a browser, but not programmatically.

Contributor guide

Open the contributing guide

Research direction

Inspect 04-multi-modal-rag/text-images-rag-using-kb/text_images_rag_using_kb.ipynb and locate the cell that downloads IF12695.pdf into mm-data/tornadoes_report.pdf. Reproduce the 202 Accepted response, then test a reliable retrieval approach for the same source; done means the notebook obtains a nonempty PDF at the expected path.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
data
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.