Getting error while running data preparation script to crack and ingest PDF documents

[kagoolastha23]

Describe the bug Unable to create index using Optional: Crack PDFs to Text

To Reproduce Steps to reproduce the behavior:

1. Go to repo
2. Click on 'scripts'
3. Scroll down to 'read.me' and follow the steps to prepare data locally. I want to crack pdfs to text to create an index
4. I created config.json to include the details
5. See error

Expected behavior The code should execute and index should be created.

Screenshots

Configuration: Please provide the following

• Azure OpenAI model name and version (e.g. 'gpt -4')
• Is chat history enabled? No
• Are you using data? If so, what data source? (e.g. Azure AI Search.) I have given blob url as data path in config.json

Additional context I don't know how to resolve the above error. Please give me step -by-step instructions to resolve it.

[abhahn]

Hi @kagoolastha23 , it looks like maybe there is an issue with your config.json on line 9. Are you missing a quote somewhere on that line? It might help to open it in an IDE with JSON support to see the issue more clearly.

[kagoolastha23]

Hi @kagoolastha23 , it looks like maybe there is an issue with your config.json on line 9. Are you missing a quote somewhere on that line? It might help to open it in an IDE with JSON support to see the issue more clearly.

Once I add the double quotes in config.json.I saved it. How to deploy that change? I can't run start.cmd on Azure CLoud shell.

[kagoolastha23]

I am getting this error after running the data preparation script

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.