# IntentDetector **`class IntentDetector(config)`** Bases: [`BatchedStep`](../technical/libnlp/steps/standard.md#squirro.lib.nlp.steps.batched_step.BatchedStep) Do intent detection Parameters - `step` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"app"`) – app - `type` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"query_processing"`) – query_processing - `name` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"intent_detector"`) – intent_detector - `analyzed_input_field` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"nlp"`) – analyzed spacy Doc - `target_index_name` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``""`) – index to be searched Deprecated since version 3.10.7: Target index name is now automatically detected from the pipeline - `match_entity_as_phrase` ([`list`](https://docs.python.org/3.11/library/stdtypes.html#list)`, ``[``"PERSON"``, ``"PRODUCT"``, ``"FAC"``, ``"NORP"``,``"ORG"``, ``"GPE"``, ``"LOC"``]`) – list of NER tags that should be appended as a phrase query - `match_entity_phrase_slop` ([`int`](https://docs.python.org/3.11/library/functions.html#int)`, ``5`) – Phrase slop that is applied for those auto-detected entities - `match_entity_combine_operator` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"OR"`) – If multiple entities are detected, should all of them match? OR / AND - `label_lookup_match_ngram_field` ([`bool`](https://docs.python.org/3.11/library/functions.html#bool)`, ``False`) – [Label Retrieval] Enable matching ngram field (high recall) - `label_lookup_fuzzy` ([`bool`](https://docs.python.org/3.11/library/functions.html#bool)`, ``False`) – [Label Retrieval] Enable fuzzy search (high recall) - `label_lookup_prefix_queries` ([`bool`](https://docs.python.org/3.11/library/functions.html#bool)`, ``False`) – [Label Retrieval] Enable sub-query prefix queries (high recall) - `label_lookup_most_common_rescoring` ([`bool`](https://docs.python.org/3.11/library/functions.html#bool)`, ``True`) – [Label Retrieval] Rescore matching label values by their respective overall doc–count (how often documents are tagged with this label) - `label_match_rewrite_mode` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"filter_query"`) – How to apply the detected label match: filter, boost, or rescore - `label_match_combine_operator` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"OR"`) – How to combine multiple label matches: OR / AND - `label_match_category_weights` ([`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict)`, ``{}`) – Specify weight applied on the facet-filter, by type. Default is 10 - `label_lookup_rescore_parameters` ([`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict)`, ``{}`) – Specify rescoring parameters for ES label lookup - `date_match_on_facet` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"item_created_at"`) – What field to be used for date filtering - `date_match_rewrite_mode` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"filter_query"`) – How to apply the detected date match: filter, boost, or rescore - `date_match_recency_per_category` ([`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict)`, ``{}`) – TODO: Mapping of recency boost profile for detected category (from label-match lookup) - `source_match_rewrite_mode` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"boost_query"`) – How to apply the detected source match: filter, boost, or rescore - `path` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``"."`) – path - `client_id` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``None`) – Squirro client id - `client_secret` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``None`) – Squirro client secret - `cluster` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – Squirro cluster - `genai_api_url` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – Squirro GenAI API URL - `token` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – Squirro token Methods SummaryMethods Documentation **`process_doc(doc)`** Process a document Parameters `doc` ([`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)) – Document Returns Processed document Return type [Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document) **`process_entities(doc)`** Return type [`list`](https://docs.python.org/3.11/library/stdtypes.html#list)[`Intent`]