feat(llms.json_load): Recursively load json lists (explodinggradients…

…#593)

Slightly broken json are protected against by the function
`ragas.llms.json_load.JsonLoader._find_outermost_json`. However, I've
found that for many metrics, gpt4 can often return slightly broken json
lists, for which this function returns only the first valid json. Here
we wrap `_find_outermost_json` with `_load_all_jsons` which calls it
recursively to load the full json list.

I.e. expected output for `'{"1":"2"}, ,, {"3":"4"}]'` is `[{'1': '2'},
{'3': '4'}]`

---------

Co-authored-by: jjmachan <[email protected]>

fix: raise `ExceptionInRunner` if executor faces any issues (explodin…

…ggradients#569)

fix: answer_correctness embedding (explodinggradients#513)

fix: handle edge cases in prompt processing (explodinggradients#374)

Make testgenerator output compatible with evaluate (explodinggradient…

…s#302)

* Changed context from str to List[str] so that it is consistent with
eval. Now output of TestDataset can be used for evaluation.
*  Changed typo in _generate_doc_nodes_map
* Changed TestDataset class to reflect the changes in test set
generation. Drawback is episode_done will be True in all cases as data
is changed at the level above.

chore: pin OpenAI to >1 (explodinggradients#285)

Fix typos in langfuse.ipynb (explodinggradients#237)

fix: remove limit on pydantic 2.0 (explodinggradients#209)

testset generation: bug fixes (explodinggradients#185)

Fixes 

- [x] issues with multi-context question generation  
- [x] Error in doc filtering

Testset generation: documentation (explodinggradients#158)