# "Ask a table a question" token usage and feature request **URL:** https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922 **Category:** Ask for Help **Created:** [August 11, 2023, 12:24pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922 "2023-08-11T12:24:33Z") **Posts on this page:** 6 **Page:** 1
### Author: ![Connor\_Finlayson](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/connor_finlayson/32/79079_2.png) [@Connor\_Finlayson](https://community.glideapps.com/u/Connor_Finlayson) #### Post date: [August 11, 2023, 12:24pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/1 "2023-08-11T12:24:33Z")
Hi, I want to quickly clarify how tokens are being used when using the “Ask a table a question” feature. I am guessing here, but is that way that it works that you load the entire table in your prompt and then ask GPT-4 to identify what record likely contains the answer, and then responds with the corresponding values in the answer field. **If this is the case, won’t use a lot of tokens the larger your dataset is, because it will have to read the entire dataset in its entirety each time?** Following on from this: I love the use case of using Glide to create a Q&A databank etc. Given the progress made on AI features, are there any consideration to allow for embeddings and to potentially allow for adding a vector database such as Pinecone as a source. This would solve the token issue and allow for some interesting use cases when it comes to building your own LLMs. ---
### Author: ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david) #### Post date: [August 11, 2023, 7:32pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/2 "2023-08-11T19:32:52Z")
We’re going to build the vector features directly into Glide. ---
### Author: ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh) #### Post date: [August 11, 2023, 11:40pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/3 "2023-08-11T23:40:34Z")
Thanks for the post, I really would love the ability to have vector features within Glide. In one of my apps, I’m feeding all historical data to do some sort of a chatbot. I definitely would love to have more control over that. ---
### Author: ![Connor\_Finlayson](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/connor_finlayson/32/79079_2.png) [@Connor\_Finlayson](https://community.glideapps.com/u/Connor_Finlayson) #### Post date: [August 14, 2023, 4:01pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/4 "2023-08-14T16:01:59Z")
👏 ---
### Author: ![HJ\_MOON](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/hj_moon/32/62890_2.png) [@HJ\_MOON](https://community.glideapps.com/u/HJ_MOON) #### Post date: [September 15, 2023, 7:58am UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/5 "2023-09-15T07:58:58Z")
That’s awesome news ---
### Author: ![metamads](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/metamads/32/61990_2.png) [@metamads](https://community.glideapps.com/u/metamads) #### Post date: [October 27, 2023, 2:05pm UTC](https://community.glideapps.com/t/ask-a-table-a-question-token-usage-and-feature-request/64922/6 "2023-10-27T14:05:15Z")
Hey David, Great to hear! Any update concerning a timeline for the implementation of vector features? Thanks