How to upload our own content and start query against our docs

[lotuskannan2007]

trafficstars

Please provide us with the following information:

This issue is for a: (mark with an x)

- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

Versions

Mention any other details that might be useful

---

Thanks! We'll be in touch soon.

[macalb69]

you can put your documents in the .\data folder and launch again the .\prepdocs.ps1 script which process all the new documents, chunks and index them and upload to the blob storage.

[sissimonster]

i found out that the blob can be update after changing to my own doc and run .\prepdocs.ps1 script but the search index remain the same, so when i ask question they will continue show demo doc

[george-moore]

I had the exact same issue. I was able to get around it by starting fresh: delete my local directory and all of my cloud deployments.

Steps to take after you've deleted everything:

1. Run azd init to download the current repo to my local directory.
2. go into the ./data directory, delete all of the existing docs, and copy your own.
3. run azd up to continue with the fresh deployment.

This will rebuild your search index with your new content and deploy the new index along with all of the other components.

Later, you can then modify the landing page UX to include your custom new example queries under .\app\frontend\src\pages

[vhvb1989]

This PR: https://github.com/Azure-Samples/azure-search-openai-demo/pull/35 would allow to add files directly from the web. You can also try it out.

[sissimonster]

This PR: #35 would allow to add files directly from the web. You can also try it out.

Thanks! have you pull #35 into any branch?

[dev-pawel]

while adding a new pdf, running prepdocs.ps1 works for me . How about removing some pdfs? Not only from the blob storage but also from the index etc. Any idea?

EDIT: ok there is a --remove argument. It works.

[github-actions[bot]]

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this issue will be closed.

[pamelafox]

We've documented the data ingestion process here: https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/data_ingestion.md

I'll leave this issue open as a request to upload documents from the UI, though I'm not sure that was the original question.

[pamelafox]

Closing this issue. If you're interested in user document upload, follow: https://github.com/Azure-Samples/azure-search-openai-demo/issues/1393