mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-09-28 09:35:42 +00:00
6790eaf7d8
* update packaging * fix author metadata * add newline * add empty readme * fix path to pipeline files * fix pylint job * fix metadata
54 lines
1.6 KiB
YAML
54 lines
1.6 KiB
YAML
# To allow your IDE to autocomplete and validate your YAML pipelines, name them as <name of your choice>.haystack-pipeline.yml
|
|
|
|
version: ignore
|
|
|
|
components: # define all the building-blocks for Pipeline
|
|
- name: DocumentStore
|
|
type: ElasticsearchDocumentStore
|
|
params:
|
|
host: localhost
|
|
- name: Retriever
|
|
type: BM25Retriever
|
|
params:
|
|
document_store: DocumentStore # params can reference other components defined in the YAML
|
|
top_k: 5
|
|
- name: Reader # custom-name for the component; helpful for visualization & debugging
|
|
type: FARMReader # Haystack Class name for the component
|
|
params:
|
|
model_name_or_path: deepset/roberta-base-squad2
|
|
context_window_size: 500
|
|
return_no_answer: true
|
|
- name: TextFileConverter
|
|
type: TextConverter
|
|
- name: PDFFileConverter
|
|
type: PDFToTextConverter
|
|
- name: Preprocessor
|
|
type: PreProcessor
|
|
params:
|
|
split_by: word
|
|
split_length: 1000
|
|
- name: FileTypeClassifier
|
|
type: FileTypeClassifier
|
|
|
|
pipelines:
|
|
- name: query # a sample extractive-qa Pipeline
|
|
nodes:
|
|
- name: Retriever
|
|
inputs: [Query]
|
|
- name: Reader
|
|
inputs: [Retriever]
|
|
- name: indexing
|
|
nodes:
|
|
- name: FileTypeClassifier
|
|
inputs: [File]
|
|
- name: TextFileConverter
|
|
inputs: [FileTypeClassifier.output_1]
|
|
- name: PDFFileConverter
|
|
inputs: [FileTypeClassifier.output_2]
|
|
- name: Preprocessor
|
|
inputs: [PDFFileConverter, TextFileConverter]
|
|
- name: Retriever
|
|
inputs: [Preprocessor]
|
|
- name: DocumentStore
|
|
inputs: [Retriever]
|