…r feedback and Langchain observability. Adjusted paths in existing documentation to reflect new file structure.

…atalayer/results path.

This commit introduces a new guide on managing testsets, including creating, listing, retrieving, and upserting testsets using the Agenta SDK. Additionally, a Jupyter notebook is added to demonstrate these functionalities with practical examples.

…entation and examples related to evaluation processes in Agenta.

This commit introduces a comprehensive guide on creating custom evaluators and utilizing built-in evaluators to assess application outputs. The new documentation covers the structure, inputs, return values, and practical examples for both custom and built-in evaluators, enhancing the overall understanding of evaluation processes in Agenta.

This commit introduces a new guide on defining and configuring applications for evaluation with the Agenta SDK. It covers the basic application structure, input handling, return values, and provides practical examples, enhancing user understanding of application setup and usage.

This commit introduces a new guide on running evaluations using the Agenta SDK. It provides an overview of the process, enhancing user understanding of programmatic evaluation execution.

…-judge evaluator and refine testset description. This enhances clarity for users configuring evaluations with the Agenta SDK.

…arameters in the Agenta SDK. This update improves clarity for users running evaluations and ensures proper configuration of evaluation details.

…ameter and updating example outputs. This enhances clarity and consistency in the Jupyter notebook and markdown files related to testset creation.