mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-10-31 01:39:45 +00:00
6354528336
* Add endpoint to get documents by filter * Add test for /documents/get_by_filter and extend the delete documents test * Add rest_api/file-upload to .gitignore * Make sure the document store is empty for each test * Improve docstrings of delete_documents_by_filters and get_documents_by_filters Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
70 lines
1.5 KiB
YAML
70 lines
1.5 KiB
YAML
version: '0.7'
|
|
|
|
components:
|
|
- name: Reader
|
|
type: FARMReader
|
|
params:
|
|
no_ans_boost: -10
|
|
model_name_or_path: deepset/roberta-base-squad2
|
|
- name: ESRetriever
|
|
type: ElasticsearchRetriever
|
|
params:
|
|
document_store: DocumentStore
|
|
custom_query: null
|
|
- name: DocumentStore
|
|
type: ElasticsearchDocumentStore
|
|
params:
|
|
index: haystack_test
|
|
label_index: haystack_test_label
|
|
- name: PDFConverter
|
|
type: PDFToTextConverter
|
|
params:
|
|
remove_numeric_tables: false
|
|
- name: Preprocessor
|
|
type: PreProcessor
|
|
params:
|
|
clean_whitespace: true
|
|
|
|
|
|
pipelines:
|
|
- name: query_pipeline
|
|
type: Pipeline
|
|
nodes:
|
|
- name: ESRetriever
|
|
inputs: [Query]
|
|
- name: Reader
|
|
inputs: [ESRetriever]
|
|
|
|
- name: ray_query_pipeline
|
|
type: RayPipeline
|
|
nodes:
|
|
- name: ESRetriever
|
|
replicas: 2
|
|
inputs: [ Query ]
|
|
- name: Reader
|
|
inputs: [ ESRetriever ]
|
|
|
|
- name: indexing_pipeline
|
|
type: Pipeline
|
|
nodes:
|
|
- name: PDFConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [PDFConverter]
|
|
- name: ESRetriever
|
|
inputs: [Preprocessor]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|
|
|
|
- name: indexing_text_pipeline
|
|
type: Pipeline
|
|
nodes:
|
|
- name: TextConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [TextConverter]
|
|
- name: ESRetriever
|
|
inputs: [Preprocessor]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|