Azure-Samples / aisearch-openai-rag-audio

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
https://azure.microsoft.com/products/search
MIT License
211 stars 105 forks source link

'chunk_id' is not a filterable field #4

Closed kirkhofer closed 3 weeks ago

kirkhofer commented 3 weeks ago

If you add an index by just running the import and vectorize data the chunk_id field is not marked as filterable. Even though the application launches, you receive errors because the code for ragtools.py is trying to filter on the chunk_id field. The app just doesn't work as expected even though you can have a conversation it doesn't see the index at all.

image

pablocastro commented 3 weeks ago

Good catch, I forgot we just changed this to use less resources, all my existing test indexes had this enabled. Will fix this shortly to avoid needing chunk_id to be filterable.

pablocastro commented 3 weeks ago

Fixed in fad1672257091fcf3aa83a013892047e71229999