Douglas Blank
Douglas Blank
This PR is an example of speeding up Gramps by creating a "Business Logic" layer. The Business Logic layer is composed of functions largely moved out of filters and rules....
This PR adds a new column, "json_data" to all primary tables consisting of JSON data (just TEXT) encoded from the pickled blobs. It doesn't remove the blob_data from existing databases,...
### Willingness to contribute Yes. I can contribute a fix for this bug independently. ### What component(s) are affected? - [X] Python SDK - [ ] Opik UI - [...
WIP: Updating some items based on feedback from discourse. 1. Be able to iter over NoneData 2. added references 3. added back_references 4. added back_references_recursively
### What feature would you like to see? I'd like to have the ability for online monitoring of an optimizer. I guess I could add a logger, but that seems...
### What happened? When I use the following from the https://dspy.ai/tutorials/agents/ example: ```python instructions = "Find all Wikipedia titles relevant to verifying (or refuting) the claim." signature = dspy.Signature("claim ->...
## Details This PR adds documentation for the DSPy callback to allow logging the graph for each module. ## Documentation Added this image: 
## Details We did not allow setting the MIRPO num_trials. This PR does that.
## Details This is WIP for creating a new agent optimization foundation.
This PR adds methods designed to be implemented in a low-level DB system, like SQL. The human-facing code is all Python, and gets parsed into SQL. All of the code...