mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-03 14:18:46 +00:00
d470b9d0bd
* Fist attempt at using setup.cfg for dependency management * Trying the new package on the CI and in Docker too * Add composite extras_require * Add the safe_import function for document store imports and add some try-catch statements on rest_api and ui imports * Fix bug on class import and rephrase error message * Introduce typing for optional modules and add type: ignore in sparse.py * Include importlib_metadata backport for py3.7 * Add colab group to extra_requires * Fix pillow version * Fix grpcio * Separate out the crawler as another extra * Make paths relative in rest_api and ui * Update the test matrix in the CI * Add try catch statements around the optional imports too to account for direct imports * Never mix direct deps with self-references and add ES deps to the base install * Refactor several paths in tests to make them insensitive to the execution path * Include tstadel review and re-introduce Milvus1 in the tests suite, to fix * Wrap pdf conversion utils into safe_import * Update some tutorials and rever Milvus1 as default for now, see #2067 * Fix mypy config Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
104 lines
2.4 KiB
YAML
104 lines
2.4 KiB
YAML
version: '0.7'
|
|
|
|
components:
|
|
- name: Reader
|
|
type: FARMReader
|
|
params:
|
|
no_ans_boost: -10
|
|
model_name_or_path: deepset/roberta-base-squad2
|
|
num_processes: 0
|
|
- 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
|
|
- name: IndexTimeDocumentClassifier
|
|
type: TransformersDocumentClassifier
|
|
params:
|
|
batch_size: 16
|
|
use_gpu: -1
|
|
- name: QueryTimeDocumentClassifier
|
|
type: TransformersDocumentClassifier
|
|
params:
|
|
use_gpu: -1
|
|
|
|
|
|
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: query_pipeline_with_document_classifier
|
|
type: Pipeline
|
|
nodes:
|
|
- name: ESRetriever
|
|
inputs: [Query]
|
|
- name: QueryTimeDocumentClassifier
|
|
inputs: [ESRetriever]
|
|
- name: Reader
|
|
inputs: [QueryTimeDocumentClassifier]
|
|
|
|
- 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]
|
|
|
|
- name: indexing_pipeline_with_classifier
|
|
type: Pipeline
|
|
nodes:
|
|
- name: PDFConverter
|
|
inputs: [File]
|
|
- name: Preprocessor
|
|
inputs: [PDFConverter]
|
|
- name: IndexTimeDocumentClassifier
|
|
inputs: [Preprocessor]
|
|
- name: ESRetriever
|
|
inputs: [IndexTimeDocumentClassifier]
|
|
- name: DocumentStore
|
|
inputs: [ESRetriever]
|