dspy

dspy copied to clipboard

feat: Exploring global caching for LM calls

2

I took a look into how we can integrate global joblib Memory caching into the `BaseLM` class. It takes a little bit of misdirection, but the below `BaseLM` class will...

KCaverly

Minor changes to enable the evaluator to accept any callable objects as metrics.

lzjever

How to use Mıstral API

2

How to use Mıstral API as an llm for mistral medium model? Can I get an example code. I am using it like that: llm = dspy.OpenAI(api_base='https://api.mistral.ai/v1/', api_key='MY_API_KEY', model='mistral-medium', model_type='chat')...

codelauncher444

how to connect to llama-2-7b.ggmlv3.q4_K_S.bin

4

Hi, I am trying to connect llama-2-7b.ggmlv3.q4_K_S.bin from DSPy code and i am not able to find right way to do this. Can someone please explain or guide me to...

deepuak

Hi 👋 I was trying to run the attached (below) DSPy program zero-shot through Mistral7B, locally hosted with Ollama (first time). However it does not work as it crashes at...

neoxelox

Can I use a model loaded with the Llama cpp for python library to power DSPy?

MrMondragon

Introduction of incremental mypy compatibility via static typing (where possible)?

3

Before I dedicate any time to this, I'd like to gauge enthusiasm for introducing static typing (incrementally) to this project. I'd start by type-annotating the external, user-facing API to increase...

mgbvox

Bug: Unable to run tests locally

2

Bug: Getting Unable to import dspy when trying to run the new tests Steps to reproduce: 1. Clone main branch 2. python -m venv .env 3. source .env/bin/activate 4. pip...

isaacbmiller

Save kwargs in HFClientVLLM

1

It's not possible to override max_tokens without doing this.

vikhyat

How to serve a dspy model

4

Have a simple model all configured but cannot get it to work on a Flask/FastAPI server. I have looked at similar issues brought up but nothing conclusive on if the...

ctyler9