dspy
dspy copied to clipboard
DSPy: The framework for programming—not prompting—language models
Migrated OpenAI GPT3 LM client to v1's OpenAI/AzureOpenAI clients. The previous version, had kwarg inconsistencies with Azure calls. Fixes #377
Updates the dependencies of the `qdrant` extra to latest.
https://github.com/stanfordnlp/dspy/blob/ed8613ffdc4bc6f48a71142557da29d286047b36/dspy/primitives/program.py#L86 Can I have examples of different types of inputs of this function? It's called here (the only place I found) ```python def map_named_predictors(self, func): """Applies a function to all...
``` from dspy.datasets import DataLoader dl = DataLoader() json_dataset = dl.from_json("/home/path-to/sample_responses.json", fields=["question", "answer", "context"]) # joy ensues... ```
Adds a new vectorizer for [Cohere's Embed models](https://docs.cohere.com/reference/embed) analogous to OpenAIVectorizer. Details on the performance of the Embed 3 model can be found [here](https://txt.cohere.com/introducing-embed-v3/) Of note, the Vectorizer interface doesn't...
For workflows using aws profiles other than the default one.
## How it currently works In line 151 of `BootstrapFewShot` we currently check examples with: `success = (self.metric is None) or self.metric(example, prediction, trace)` If success == True, we then...
I get the sense that DSPy isn't telling the model enough about itself in order to properly react to the prompts being given. As a simple example let's take the...
Adding items discussed in #397