| | from haystack.document_stores import FAISSDocumentStore |
| | document_store = FAISSDocumentStore(faiss_index_factory_str="Flat", embedding_dim=1024) |
| |
|
| | |
| | from haystack.utils import clean_wiki_text, convert_files_to_docs |
| | doc_dir = "test" |
| | docs = convert_files_to_docs(dir_path=doc_dir, clean_func=clean_wiki_text, split_paragraphs=True) |
| | document_store.write_documents(docs) |
| |
|
| | from haystack.nodes import EmbeddingRetriever |
| | |
| | retriever = EmbeddingRetriever( |
| | document_store=document_store, |
| | embedding_model="AlexKay/xlm-roberta-large-qa-multilingual-finedtuned-ru" |
| | ) |
| | document_store.update_embeddings(retriever) |
| |
|
| | from haystack.nodes import FARMReader |
| | |
| | reader = FARMReader(model_name_or_path="AlexKay/xlm-roberta-large-qa-multilingual-finedtuned-ru", use_gpu=False) |
| |
|
| | from haystack.pipelines import ExtractiveQAPipeline |
| | pipe = ExtractiveQAPipeline(reader, retriever) |
| |
|
| | |
| | query = "директор Института электроэнергетики и электроники?" |
| | prediction = pipe.run( |
| | query=query, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 10}} |
| | ) |
| | print(prediction) |
| |
|