Repository navigation
Weaviate + FeatureBase Mashup #5
Description
This example would show how to integrate FeatureBase into a Weaviate project.
- determine how to accelerate weaviate searches using a lookup in FB
- determine a data set that may be vectorized (embeddings on GPT-3 for example) as well as indexed by FB for speed increase
- determine which types of data sets are likely to be larger for this project
- establish other integrations, such as with Solr or other indexing technologies
Activity
kordless commentedon Jan 25, 2023
Limiting this to weaviate integration.
This prototype should take inputs, with authors and recipients of message, and insert them into Weaviate, along with their dense vectors. Once inserted, the document is also inserted into FeatureBase.
When a new input is indexed, or an old one found, it should also return matching documents from Weaviate and FeatureBase. Those documents are then sent into FeatureBase, along with the certainty and distance to the new document.
If a flag is set, certainty is altered within FeatureBase such that subsequent queries returning that document will reflect a delta in certainty.
This prototype will be added to slothbot when it is ready.