Align Azure Search environment variables with langchain

[cecheta]

Please provide us with the following information:

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

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

Relates to #251

Langchain expects the following environment variables, as defined here:

• AZURESEARCH_FIELDS_ID
• AZURESEARCH_FIELDS_CONTENT
• AZURESEARCH_FIELDS_CONTENT_VECTOR
• AZURESEARCH_FIELDS_TAG

However, the application has the following environment variables defined:

• AZURE_SEARCH_FIELDS_ID
• AZURE_SEARCH_CONTENT_COLUMNS
• AZURE_SEARCH_CONTENT_VECTOR_COLUMNS
• AZURE_SEARCH_FIELDS_TAG

The env vars in the application should be updated to match those expected by langchain. Note that out of these 4 env vars, AZURE_SEARCH_CONTENT_COLUMNS appears to be the only one currently in use by the application code, and this is with Azure OpenAI, not langchain.

Additionally, the fields defined here can be updated to use the env vars, so that the index fields do not need to be manually modified in the code when using a custom index.

[github-actions[bot]]

This issue is stale because it has been open 180 days with no activity. Remove stale label or comment or this will be closed in 30 days.