-
Suppose we have a BERT NLI model trained to zero-shot classify texts given a prompt such as, for example, 'This text relates to cars.' Is it possible to use DSPy to optimise the prompt for such a mode…
-
Hello !
Great project, so much easy to understand/hack than the microsoft one
Is there any plan to support the prompt tuning feature ? https://microsoft.github.io/graphrag/posts/prompt_tuning/ov…
-
A few members of the community have been asking for support for streaming LM output in DSPy.
@sutyum and @detaos have discussed this extensively before.
One of the challenges is that it's not ev…
-
## Description
**Context**
Currently, the Pydantic model schema used in the pipeline is statically defined in the repo. This limits flexibility for users who may need to customize the schema w…
-
see [dspy](https://github.com/Meiye-lj/Dockerfiles/tree/master/dspy)
-
Implement a `DspyMetricAdapter` (or similar name) that allows users to utilize metrics defined as DSPy modules. This adapter will serve as a bridge, converting DSPy metrics a metric compatible with co…
-
I tried to run the DSpy module inside the thread it's not working...
I have used
`dspy.Module`
there I used a custom retriever module.
`elastic_rm(dspy.Retrieve)`
Can anyone give me a …
-
**Project description**
> DSPy is a framework for algorithmically optimizing LM prompts and weights
Its a python package
would really appreciate someone putting a package together, or helping…
-
https://github.com/stanfordnlp/dspy
-
In the avatar example notebook there is a comment about max_iters "is used to control the number of iterations in multi step execution". With my agent instance (max_iters=10)
```
self.avatar = Av…