uptrain
uptrain copied to clipboard
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform ro...
Hey Can we include AWS bedrock LLM support as well. Claude models on Bedrock cannot be used otherwise.
Can you please add support for Google Cloud Vertex AI platform? Thanks!
Take up any use case where Uptrain can be used to evaluate the pipeline and create a descriptive Python notebook with code for the same. You can create a folder...
MT-Bench (Multi-Turn Benchmark) is the benchmark to evaluate multi-turn dialogues, typically between a user and an LLM.
Allow users to use the Mamba LLM architecture to generate responses and perform evaluations
**Describe the bug** After creating a New Project with a bad key for OpenAI GPT-3.5-Turbo, the results are returned as Null. I was expecting to get a bad key response...
**Describe the bug** Followed the steps for the Dashboard outlined in [Getting Started](https://docs.uptrain.ai/dashboard/getting_started) and successfully built the project and hosted it locally through docker. (Great work, the script went smooth!)...
MMLU (Massive Multitask Language Understanding) is a benchmark designed to measure knowledge acquired during pretraining by evaluating models exclusively in zero-shot and few-shot settings.
Add tests for checking if all the managed evals are working fine or not
There is a lot of repetition in the operator classes in 'uptrain/operators'. Create a common super class.