Closed jjmachan closed 3 months ago
list of issues this will address
removing HF dataset
Make embeddings faster
Hey @jjmachan ! Thanks for all your work on ragas, I really appreciate it. I am trying to use it to evaluate my chatbot created with llama-index. Has there been any workarounds discovered for issue #271 ?
These are my dependencies: `%pip install ragas==0.0.22
%pip install pypdf
%pip install llama-index==0.8.52
%pip install langchain==0.0.331rc3
%pip install openai==0.28.1`
Problem - ragas is slow and unreliable
ThreadPoolExecutor
andasyncio
modules. This is because ragas took a batching approach to evaluation ie evaluated metrics in batchesCore Components
BaseMetric
- a metric that evaluates a single score row with butscore()
andascore()
RagasLLM
that is based onlangchain-core
llmsPrompt
object with provision for instruction and demonstrations that convert to messages or prompts that is supported by both langchain chat based on completion basedLLMResult
object that supports both chat and text-based outputsExector
that runsBaseMetric
. It should also be able to run testset generators so this should be a common paradigmevaluate()
function that makes it easier toBaseMetrc
by default will havellm=None
and will take the default llm from theevaluate()
function. Ifmetric.llm != None
then the provided metric is usedBase classes
Metric
evaluation()
BaseRagasLLM