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
We are currently using DuckDB as our vector database for all unstructured data and MongoDB for pandas dataframes or structured data. I am aware that DuckDB handles parquet data very well. My request is whether it would be possible to add similar functionality (converting the DataFrame to a JSON string representation) in DuckDB, allowing us to use DuckDB as a single vector database for both unstructured and structured data. Your advice on this matter would be appreciated.
If possible, can I get a sample code with query engine please?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
We are currently using DuckDB as our vector database for all unstructured data and MongoDB for pandas dataframes or structured data. I am aware that DuckDB handles parquet data very well. My request is whether it would be possible to add similar functionality (converting the DataFrame to a JSON string representation) in DuckDB, allowing us to use DuckDB as a single vector database for both unstructured and structured data. Your advice on this matter would be appreciated.
If possible, can I get a sample code with query engine please?
Links for vector index that we are using are below:
https://docs.llamaindex.ai/en/stable/examples/vector_stores/DuckDBDemo/
https://docs.llamaindex.ai/en/stable/examples/vector_stores/MongoDBAtlasVectorSearchRAGOpenAI/
Beta Was this translation helpful? Give feedback.
All reactions