mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-10-31 17:59:27 +00:00
77 lines
3.5 KiB
Python
Executable File
77 lines
3.5 KiB
Python
Executable File
import logging
|
|
import subprocess
|
|
import time
|
|
|
|
from haystack import Finder
|
|
from haystack.database.elasticsearch import ElasticsearchDocumentStore
|
|
from haystack.indexing.cleaning import clean_wiki_text
|
|
from haystack.indexing.utils import convert_files_to_dicts, fetch_archive_from_http
|
|
from haystack.reader.farm import FARMReader
|
|
from haystack.reader.transformers import TransformersReader
|
|
from haystack.utils import print_answers
|
|
from haystack.retriever.sparse import ElasticsearchRetriever
|
|
from haystack.retriever.dense import DensePassageRetriever
|
|
|
|
LAUNCH_ELASTICSEARCH = False
|
|
|
|
# Start an Elasticsearch server
|
|
# You can start Elasticsearch on your local machine instance using Docker. If Docker is not readily available in
|
|
# your environment (eg., in Colab notebooks), then you can manually download and execute Elasticsearch from source.
|
|
|
|
if LAUNCH_ELASTICSEARCH:
|
|
logging.info("Starting Elasticsearch ...")
|
|
status = subprocess.run(
|
|
['docker run -d -p 9200:9200 -e "discovery.type=single-node" elasticsearch:7.6.2'], shell=True
|
|
)
|
|
if status.returncode:
|
|
raise Exception("Failed to launch Elasticsearch. If you want to connect to an existing Elasticsearch instance"
|
|
"then set LAUNCH_ELASTICSEARCH in the script to False.")
|
|
time.sleep(15)
|
|
|
|
# Connect to Elasticsearch
|
|
document_store = ElasticsearchDocumentStore(host="localhost", username="", password="",
|
|
index="document", embedding_dim=768, embedding_field="embedding")
|
|
|
|
# ## Cleaning & indexing documents
|
|
# Let's first get some documents that we want to query
|
|
doc_dir = "data/article_txt_got"
|
|
s3_url = "https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt.zip"
|
|
fetch_archive_from_http(url=s3_url, output_dir=doc_dir)
|
|
|
|
# convert files to dicts containing documents that can be indexed to our datastore
|
|
dicts = convert_files_to_dicts(dir_path=doc_dir, clean_func=clean_wiki_text, split_paragraphs=True)
|
|
|
|
# Now, let's write the docs to our DB.
|
|
document_store.write_documents(dicts[:16])
|
|
|
|
|
|
### Retriever
|
|
retriever = DensePassageRetriever(document_store=document_store, embedding_model="dpr-bert-base-nq",
|
|
do_lower_case=True, gpu=True)
|
|
# Important:
|
|
# Now that after we have the DPR initialized, we need to call update_embeddings() to iterate over all
|
|
# previously indexed documents and update their embedding representation.
|
|
# While this can be a time consuming operation (depending on corpus size), it only needs to be done once.
|
|
# At query time, we only need to embed the query and compare it the existing doc embeddings which is very fast.
|
|
document_store.update_embeddings(retriever)
|
|
|
|
### Reader
|
|
# Load a local model or any of the QA models on
|
|
# Hugging Face's model hub (https://huggingface.co/models)
|
|
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
|
|
|
|
### Finder
|
|
# The Finder sticks together reader and retriever in a pipeline to answer our actual questions.
|
|
finder = Finder(reader, retriever)
|
|
|
|
### Voilà! Ask a question!
|
|
# You can configure how many candidates the reader and retriever shall return
|
|
# The higher top_k_retriever, the better (but also the slower) your answers.
|
|
prediction = finder.get_answers(question="Who is the father of Arya Stark?", top_k_retriever=10, top_k_reader=5)
|
|
|
|
|
|
# prediction = finder.get_answers(question="Who created the Dothraki vocabulary?", top_k_reader=5)
|
|
# prediction = finder.get_answers(question="Who is the sister of Sansa?", top_k_reader=5)
|
|
|
|
print_answers(prediction, details="minimal")
|