mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-10-31 17:59:27 +00:00
59857cb492
* Use a smaller reader where possible * Change scope to module of reader to get faster load times
91 lines
2.2 KiB
YAML
91 lines
2.2 KiB
YAML
version: ignore
|
|
|
|
components:
|
|
- name: Reader
|
|
type: FARMReader
|
|
params:
|
|
no_ans_boost: -10
|
|
model_name_or_path: deepset/bert-medium-squad2-distilled
|
|
num_processes: 0
|
|
- name: ESRetriever
|
|
type: BM25Retriever
|
|
params:
|
|
document_store: DocumentStore
|
|
- name: DocumentStore
|
|
type: ElasticsearchDocumentStore
|
|
params:
|
|
index: haystack_test
|
|
label_index: haystack_test_label
|
|
- name: PDFConverter
|
|
type: PDFToTextConverter
|
|
params:
|
|
remove_numeric_tables: false
|
|
- name: TextConverter
|
|
type: TextConverter
|
|
- name: Preprocessor
|
|
type: PreProcessor
|
|
params:
|
|
clean_whitespace: true
|
|
- name: IndexTimeDocumentClassifier
|
|
type: TransformersDocumentClassifier
|
|
params:
|
|
batch_size: 16
|
|
use_gpu: false
|
|
- name: QueryTimeDocumentClassifier
|
|
type: TransformersDocumentClassifier
|
|
params:
|
|
use_gpu: false
|
|
|
|
|
|
pipelines:
|
|
- name: query_pipeline
|
|
nodes:
|
|
- name: ESRetriever
|
|
inputs: [Query]
|
|
- name: Reader
|
|
inputs: [ESRetriever]
|
|
|
|
- name: query_pipeline_with_document_classifier
|
|
nodes:
|
|
- name: ESRetriever
|
|
inputs: [Query]
|
|
- name: QueryTimeDocumentClassifier
|
|
inputs: [ESRetriever]
|
|
- name: Reader
|
|
inputs: [QueryTimeDocumentClassifier]
|
|
|
|
- name: indexing_pipeline
|
|
nodes:
|
|
- name: PDFConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [PDFConverter]
|
|
- name: ESRetriever
|
|
inputs: [Preprocessor]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|
|
|
|
- name: indexing_text_pipeline
|
|
nodes:
|
|
- name: TextConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [TextConverter]
|
|
- name: ESRetriever
|
|
inputs: [Preprocessor]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|
|
|
|
- name: indexing_pipeline_with_classifier
|
|
nodes:
|
|
- name: PDFConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [PDFConverter]
|
|
- name: IndexTimeDocumentClassifier
|
|
inputs: [Preprocessor]
|
|
- name: ESRetriever
|
|
inputs: [IndexTimeDocumentClassifier]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|