-
Hello DSPy Team,
I am working on a pipeline in `DSPy` to process Amazon product descriptions by shortening them and classifying them into one of 30 categories. While I understand how to implement t…
-
Any plans to integrate Gemini and Bedrock? Independent of DSPy I'm working on testing different models, similar to what anyscale is doing in [Building RAG-based LLM Applications for Production](https:…
-
Hi. In the notebooks, we can use a pre-set server for colbert model that works on wikipedia data. But I want to know how to use the same for my own set of documents. Can anybody please help?
-
### Details
### Details
All the documentation should be written back to the `docs` folder. If a documentation section is already present, modify, it, do not add a new one.
Ensure the documentatio…
-
### Details
Please add the contents of `/readme.md` to the documentation. A skeleton of this change is present in `docs/source/index.rst`, but you may refactor it how you please, keeping in mind futur…
-
What is best way to deploy the compiled model ? Do we need to run the compilation pipeline for every input or we just take the compiled model and deploy this in production environment? Any kind of gui…
vp999 updated
9 months ago
-
I am building my own `Example` objects using the following:
```
trainset = [dspy.Example(**{'field1': row['x'], 'field2': row['y']}).with_inputs('field1') for index, row in train_df.iterrows()]
```…
-
Add Support for Neo4j as a VectorDB
-
#teleprompeter to optimize the weights of this program using a metric defined validate_Pred_Imp_words
from dspy.teleprompt import BootstrapFewShot,Ensemble
# Validation logic: check that the pred…
-
### Details
Please ensure index.rst properly indexes and uses the documentation converted from the markdown files:
- `./docs/language_models_client.rst`
- `./docs/retrieval_models_client.rst`
- …