mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-28 11:19:58 +00:00

* Files moved, imports all broken * Fix most imports and docstrings into * Fix the paths to the modules in the API docs * Add latest docstring and tutorial changes * Add a few pipelines that were lost in the inports * Fix a bunch of mypy warnings * Add latest docstring and tutorial changes * Create a file_classifier module * Add docs for file_classifier * Fixed most circular imports, now the REST API can start * Add latest docstring and tutorial changes * Tackling more mypy issues * Reintroduce from FARM and fix last mypy issues hopefully * Re-enable old-style imports * Fix some more import from the top-level package in an attempt to sort out circular imports * Fix some imports in tests to new-style to prevent failed class equalities from breaking tests * Change document_store into document_stores * Update imports in tutorials * Add latest docstring and tutorial changes * Probably fixes summarizer tests * Improve the old-style import allowing module imports (should work) * Try to fix the docs * Remove dedicated KnowledgeGraph page from autodocs * Remove dedicated GraphRetriever page from autodocs * Fix generate_docstrings.sh with an updated list of yaml files to look for * Fix some more modules in the docs * Fix the document stores docs too * Fix a small issue on Tutorial14 * Add latest docstring and tutorial changes * Add deprecation warning to old-style imports * Remove stray folder and import Dict into dense.py * Change import path for MLFlowLogger * Add old loggers path to the import path aliases * Fix debug output of convert_ipynb.py * Fix circular import on BaseRetriever * Missed one merge block * re-run tutorial 5 * Fix imports in tutorial 5 * Re-enable squad_to_dpr CLI from the root package and move get_batches_from_generator into document_stores.base * Add latest docstring and tutorial changes * Fix typo in utils __init__ * Fix a few more imports * Fix benchmarks too * New-style imports in test_knowledge_graph * Rollback setup.py * Rollback squad_to_dpr too Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
50 lines
2.6 KiB
Python
50 lines
2.6 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from haystack.nodes import Text2SparqlRetriever
|
|
from haystack.document_stores import GraphDBKnowledgeGraph
|
|
from haystack.utils import fetch_archive_from_http
|
|
|
|
@pytest.mark.graphdb
|
|
def test_graph_retrieval(graphdb_fixture):
|
|
# TODO rename doc_dir
|
|
graph_dir = "../data/tutorial10_knowledge_graph/"
|
|
s3_url = "https://fandom-qa.s3-eu-west-1.amazonaws.com/triples_and_config.zip"
|
|
fetch_archive_from_http(url=s3_url, output_dir=graph_dir)
|
|
|
|
# Fetch a pre-trained BART model that translates natural language questions to SPARQL queries
|
|
model_dir = "../saved_models/tutorial10_knowledge_graph/"
|
|
s3_url = "https://fandom-qa.s3-eu-west-1.amazonaws.com/saved_models/hp_v3.4.zip"
|
|
fetch_archive_from_http(url=s3_url, output_dir=model_dir)
|
|
|
|
kg = GraphDBKnowledgeGraph(index="tutorial_10_index")
|
|
kg.delete_index()
|
|
kg.create_index(config_path=Path(graph_dir+"repo-config.ttl"))
|
|
kg.import_from_ttl_file(index="tutorial_10_index",
|
|
path=Path(graph_dir+"triples.ttl"))
|
|
triple = {'p': {'type': 'uri', 'value': 'https://deepset.ai/harry_potter/_paternalgrandfather'}, 's': {'type': 'uri', 'value': 'https://deepset.ai/harry_potter/Melody_fawley'}, 'o': {'type': 'uri', 'value': 'https://deepset.ai/harry_potter/Marshall_fawley'}}
|
|
triples = kg.get_all_triples()
|
|
assert len(triples) > 0
|
|
assert triple in triples
|
|
|
|
# Define prefixes for names of resources so that we can use shorter resource names in queries
|
|
prefixes = """PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
|
|
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
|
|
PREFIX hp: <https://deepset.ai/harry_potter/>
|
|
"""
|
|
kg.prefixes = prefixes
|
|
|
|
kgqa_retriever = Text2SparqlRetriever(knowledge_graph=kg,
|
|
model_name_or_path=model_dir+"hp_v3.4")
|
|
|
|
result = kgqa_retriever.retrieve(query="In which house is Harry Potter?")
|
|
assert result[0] == {'answer': ['https://deepset.ai/harry_potter/Gryffindor'], 'prediction_meta': {'model': 'Text2SparqlRetriever', 'sparql_query': 'select ?a { hp:Harry_potter hp:house ?a . }'}}
|
|
|
|
result = kgqa_retriever._query_kg(sparql_query="select distinct ?sbj where { ?sbj hp:job hp:Keeper_of_keys_and_grounds . }")
|
|
assert result[0][0] == "https://deepset.ai/harry_potter/Rubeus_hagrid"
|
|
|
|
result = kgqa_retriever._query_kg(
|
|
sparql_query="select distinct ?obj where { <https://deepset.ai/harry_potter/Hermione_granger> <https://deepset.ai/harry_potter/patronus> ?obj . }")
|
|
assert result[0][0] == "https://deepset.ai/harry_potter/Otter"
|