| [lexical_search] | |
| TOP_K = 20 | |
| SPLIT_BY = word | |
| SPLIT_LENGTH = 120 | |
| SPLIT_OVERLAP = 0 | |
| REMOVE_PUNC = 0 | |
| [semantic_search] | |
| RETRIEVER_TOP_K = 10 | |
| MAX_SEQ_LENGTH = 64 | |
| RETRIEVER = msmarco-bert-base-dot-v5 | |
| RETRIEVER_FORMAT = sentence_transformers | |
| RETRIEVER_EMB_LAYER = -1 | |
| READER = deepset/tinyroberta-squad2 | |
| READER_TOP_K = 10 | |
| THRESHOLD = 0.1 | |
| SPLIT_BY = sentence | |
| SPLIT_LENGTH = 3 | |
| SPLIT_OVERLAP = 0 | |
| RESPECT_SENTENCE_BOUNDARY = 1 | |
| REMOVE_PUNC = 0 | |
| [sdg] | |
| THRESHOLD = 0.85 | |
| MODEL = jonas/sdg_classifier_osdg | |
| SPLIT_BY = word | |
| REMOVE_PUNC = 0 | |
| SPLIT_LENGTH = 120 | |
| SPLIT_OVERLAP = 10 | |
| RESPECT_SENTENCE_BOUNDARY = 1 | |
| TOP_KEY = 15 | |
| [preprocessor] | |
| SPLIT_OVERLAP_WORD = 10 | |
| SPLIT_OVERLAP_SENTENCE = 1 | |
| [tfidf] | |
| TOP_N = 20 | |