feat: Add notebook for RAG eval harness

[shadeMe]

Proposed Changes:

Add a notebook to showcase the RAG evaluation harness.

Notes for the reviewer

Depends on the following: deepset-ai/haystack#7818

Without the above PR, the execution of the harness will break since it attempts to serialize the evaluation pipeline. To test it locally, either pull the above PR and build haystack-ai locally or remove the answer faithfulness metric from the harness.

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.
• I documented my code
• I ran pre-commit hooks and fixed any issue

[coveralls]

Pull Request Test Coverage Report for Build 9401655773

Details

• 20 of 22 (90.91%) changed or added relevant lines in 1 file are covered.
• No unchanged relevant lines lost coverage.
• Overall coverage remained the same at 97.764%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
haystack_experimental/evaluation/harness/rag/harness.py	20	22	90.91%

Totals
Change from base Build 9352626696:	0.0%
Covered Lines:	612
Relevant Lines:	626

---

💛 - Coveralls

[TuanaCelik]

PSA, you can view the notebook here: https://colab.research.google.com/github/shadeMe/haystack-experimental/blob/feat/rag-eval-harness-notebook/examples/rag_eval_harness.ipynb

[davidsbatista]

I think the code is already there, and it shows how to use it. Nevertheless, this notebook needs some improvement regarding "documentation" and the code's organisation. Here are my comments:

• Create an intro section shortly describing what the notebook is about
  Do not assume anything is installed; explicitly state what dependencies are needed and the commands to install them. (I think you have most of it already there.)
• Add textual descriptions/instructions to each section/snippet (i.e.: dataset prep., indexing, retrieval, eval., results analysis), instead of just the title
• Make sure to have any relevant links to Documentation and/or blog posts related to the snippets/sections if needed
• Move the imports to their related sections/snippets of code instead of having everything at the beginning
• See some of the tutorials here for guidance: https://github.com/deepset-ai/haystack-tutorials?tab=readme-ov-file
• One example: https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/39_Embedding_Metadata_for_Improved_Retrieval.ipynb

[davidsbatista]

just noticed that the keyword_eval_harness is not used anywhere

[davidsbatista]

PSA, you can view the notebook here: https://colab.research.google.com/github/shadeMe/haystack-experimental/blob/feat/rag-eval-harness-notebook/examples/rag_eval_harness.ipynb

@TuanaCelik, did you manage to run this collab/notebook?

[davidsbatista]

@shadeMe can you open another PR only with the pytoml ?

[coveralls]

Pull Request Test Coverage Report for Build 9498393193

Details

• 20 of 22 (90.91%) changed or added relevant lines in 1 file are covered.
• No unchanged relevant lines lost coverage.
• Overall coverage remained the same at 97.764%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
haystack_experimental/evaluation/harness/rag/harness.py	20	22	90.91%

Totals
Change from base Build 9465387731:	0.0%
Covered Lines:	612
Relevant Lines:	626

---

💛 - Coveralls