Corporate-reputation

Fix

* **pipeline:** Replace find_similar_docs_ac with find_similar_docs_by_clustering in datasets, change column names in datasets-similar.yaml ([`78ad328`](https://github.com/entelecheia/corporate-reputation/commit/78ad3284dcd656e36e3dfbd4879501d5358812b8))
* **pipeline:** Update tokenizer parameter name ([`f96b9b1`](https://github.com/entelecheia/corporate-reputation/commit/f96b9b1af799675a21b2115e07cdf41d364c4630))

Fix

* **tokenizer:** Update stopwords path in kakao config ([`8158062`](https://github.com/entelecheia/corporate-reputation/commit/815806279beecd43f1a1909edafa577f0283fabe))
* **pipeline:** Increase sample size and adjust worker count, remove specific columns from removal list ([`28529da`](https://github.com/entelecheia/corporate-reputation/commit/28529da1a766a44993e97601e8616d2a3c75a8cd))
* **workflow:** Enable noun and similar pipelines ([`f242a63`](https://github.com/entelecheia/corporate-reputation/commit/f242a63172bad13521fc5fcc0e38ee0a92b16042))
* **pipeline:** Update filter_dataset to filter_and_sample_data ([`1e97c46`](https://github.com/entelecheia/corporate-reputation/commit/1e97c4655d40221105fb81392c3b20ae4fedb9b6))
* **pipeline:** Change num_samples to sample_size in datasets-test.yaml ([`c9ba5cb`](https://github.com/entelecheia/corporate-reputation/commit/c9ba5cbe76d3911a7518956091e6aedcad51833b))
* **pipeline:** Rename num_samples to sample_size in datasets-similar config ([`2cdc541`](https://github.com/entelecheia/corporate-reputation/commit/2cdc5413420042ec0f55167212a383c594fc21c7))
* **pipeline:** Change num_samples to sample_size in datasets-noun configuration ([`5c32059`](https://github.com/entelecheia/corporate-reputation/commit/5c32059407d8d71d35b4ff257290fcfbabfa61c9))
* **pipeline:** Add sample filename in datasets filter config ([`b0609d0`](https://github.com/entelecheia/corporate-reputation/commit/b0609d0ac71de93f81df14c25f3d6c4e14b2d33b))

Feature

* **corprep:** Add revision1 for more detailed sentiment task description ([`03edfb2`](https://github.com/entelecheia/corporate-reputation/commit/03edfb2c669cb691927b5bcd66c10e32839e4185))

Feature

* **config/runner:** Add new configuration files for GPT3 and GPT4 ([`6d83abc`](https://github.com/entelecheia/corporate-reputation/commit/6d83abc7d1ed48ce088c8fa135355f1359faf6e2))
* **pipeline:** Add new dataset filter and load steps ([`441e063`](https://github.com/entelecheia/corporate-reputation/commit/441e063c7d8ab923fcf5e017a04bc6cb2b0dfddd))
* **corprep:** Add filter pipeline in config and comment out noun and similar pipelines ([`6bbd818`](https://github.com/entelecheia/corporate-reputation/commit/6bbd818c635303a07a6a979513ce94e847867d75))
* **filter:** Add verbose print statements. ([`08cf03e`](https://github.com/entelecheia/corporate-reputation/commit/08cf03ea14cf5d17856c87ea1d6bd222e785faae))
* **corprep:** Add filter_dataset configuration files ([`6edb66f`](https://github.com/entelecheia/corporate-reputation/commit/6edb66f6f1462703a8dbc26efa8c5b19f19cb69f))
* **corprep/datasets:** Add filter functionality to datasets ([`3a2835a`](https://github.com/entelecheia/corporate-reputation/commit/3a2835ab2e10b6bb3fccdf0c1e7bb7fc8dc55cc1))

Feature

* **config/runner:** Add new gpt3 and gpt4 test configuration files ([`be6e168`](https://github.com/entelecheia/corporate-reputation/commit/be6e168ec944d8634b697c40e5f7e2692551341f))
* **corprep-conf-runner:** Add corprep-gpt3 and corprep-gpt4 configuration files ([`c82df5e`](https://github.com/entelecheia/corporate-reputation/commit/c82df5e068236c1eba8a6920a2a18d71ddd2ed69))
* **corprep:** Add gpt3 and gpt4 agent configurations ([`b2a52cd`](https://github.com/entelecheia/corporate-reputation/commit/b2a52cdb0227da2f011fdeda2e36d68a9e23a1b3))
* **corprep:** Add config for TRIPLE and QUAD tasks in prompts ([`cd8d7e4`](https://github.com/entelecheia/corporate-reputation/commit/cd8d7e42df41ea8a079873b2e51904f400422a10))

Fix

* **corprep:** Add secrets directory initialization ([`0bce74f`](https://github.com/entelecheia/corporate-reputation/commit/0bce74ffede7569b36b51760a8b53738648120e9))
* **pipeline:** Replace dataframe_save with save_dataframes, remove redundant dataframe_save and save_dataframes files ([`666226a`](https://github.com/entelecheia/corporate-reputation/commit/666226a430272cbcc9f38c776fb360e298411020))
* **dependencies:** Upgrade hyfi to 1.13.0 ([`41eb5e8`](https://github.com/entelecheia/corporate-reputation/commit/41eb5e8ac93c7da18c1353284707f9d7b4c355b9))