Bharat Ramanathan
Bharat Ramanathan
**Patch description** This PR adds the ability to log model artifacts to [Weights & Biases](https://wandb.ai/site). Logging model artifacts allows complete reproducibility of the experiments that resulted in the trained model...
# WandbTracer This PR adds the `WandbTracer` and deprecates the existing `WandbCallbackHandler`. Added an example notebook under the docs section alongside the `LangchainTracer` Here's an example [colab](https://colab.research.google.com/drive/1pY13ym8ENEZ8Fh7nA99ILk2GcdUQu0jR?usp=sharing) with the same...
# Description This PR adds model architecture to the `WandbTracer` from the Serialized Run kwargs. This allows visualization of the calling parameters of an Agent, LLM and Tool in Weights...
Description ----------- This PR adds a simplified trace API to log prompt traces. This reduces the number of steps to log a WBTraceTree by consolidating the steps in a single...
This PR add functionality to log evaluation results to [Weight & Biases](https://wandb.ai/site). In addition to logging evaluation runs and tables we also add functionality to auto generate an easily sharable...
This PR updates the HuggingFace colab examples to include model registry and artifact info and turns on model checkpoint logging be default.
[transfer learning example](https://colab.research.google.com/drive/17u3SJ5kal0t9izo0UclrdA6Iy7f4TlHd#scrollTo=RGXFCqle8U85). 1. Update code to work with pytorch-lightning v2.0. 2. Change dataset due to https://github.com/pytorch/vision/issues/7670 3. Add and use model artifacts in example
This PR adds a guide to creating an LLM auto evaluation dashboard with Weave.
This PR implements a Tracer using weave for langchain.