You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have searched the EvaDB issues and found no similar feature requests.
Description
Currently, it is not clear whether we can access EvaDB tables using a different query engine like Postgres. This will be useful when we want to leverage Postgres features like window functions and string_agg on the output of EvaDB tables. One concrete workflow that benefits from this is RAG-based question-answering:
Create vector index of a document in EvaDB.
Use similarity to retrieve top-5 similar chunks to the user question.
Concatenate all the retrieved chunks in Postgres using group by and string_agg.
Run an LLM function on the concatenated output.
If this is not possible, we would need to add support for STRING_AGG and GROUP BY 'chunks' natively in EvaDB.
Use case
No response
Are you willing to submit a PR?
Yes I'd like to help by submitting a PR!
The text was updated successfully, but these errors were encountered:
Search before asking
Description
Currently, it is not clear whether we can access EvaDB tables using a different query engine like Postgres. This will be useful when we want to leverage Postgres features like window functions and string_agg on the output of EvaDB tables. One concrete workflow that benefits from this is RAG-based question-answering:
Postgres
using group by and string_agg.If this is not possible, we would need to add support for
STRING_AGG
andGROUP BY 'chunks'
natively in EvaDB.Use case
No response
Are you willing to submit a PR?
The text was updated successfully, but these errors were encountered: