mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-16 15:04:13 +00:00
langchain[minor], community[minor]: Implement Ontotext GraphDB QA Chain (#16019)
- **Description:** Implement Ontotext GraphDB QA Chain - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** @OntotextGraphDB
This commit is contained in:
Neli Hateva
GitHub
@@ -0,0 +1,6 @@
|
||||
FROM ontotext/graphdb:10.5.1
|
||||
RUN mkdir -p /opt/graphdb/dist/data/repositories/langchain
|
||||
COPY config.ttl /opt/graphdb/dist/data/repositories/langchain/
|
||||
COPY starwars-data.trig /
|
||||
COPY graphdb_create.sh /run.sh
|
||||
ENTRYPOINT bash /run.sh
|
||||
@@ -0,0 +1,46 @@
|
||||
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
|
||||
@prefix rep: <http://www.openrdf.org/config/repository#>.
|
||||
@prefix sr: <http://www.openrdf.org/config/repository/sail#>.
|
||||
@prefix sail: <http://www.openrdf.org/config/sail#>.
|
||||
@prefix graphdb: <http://www.ontotext.com/config/graphdb#>.
|
||||
|
||||
[] a rep:Repository ;
|
||||
rep:repositoryID "langchain" ;
|
||||
rdfs:label "" ;
|
||||
rep:repositoryImpl [
|
||||
rep:repositoryType "graphdb:SailRepository" ;
|
||||
sr:sailImpl [
|
||||
sail:sailType "graphdb:Sail" ;
|
||||
|
||||
graphdb:read-only "false" ;
|
||||
|
||||
# Inference and Validation
|
||||
graphdb:ruleset "empty" ;
|
||||
graphdb:disable-sameAs "true" ;
|
||||
graphdb:check-for-inconsistencies "false" ;
|
||||
|
||||
# Indexing
|
||||
graphdb:entity-id-size "32" ;
|
||||
graphdb:enable-context-index "false" ;
|
||||
graphdb:enablePredicateList "true" ;
|
||||
graphdb:enable-fts-index "false" ;
|
||||
graphdb:fts-indexes ("default" "iri") ;
|
||||
graphdb:fts-string-literals-index "default" ;
|
||||
graphdb:fts-iris-index "none" ;
|
||||
|
||||
# Queries and Updates
|
||||
graphdb:query-timeout "0" ;
|
||||
graphdb:throw-QueryEvaluationException-on-timeout "false" ;
|
||||
graphdb:query-limit-results "0" ;
|
||||
|
||||
# Settable in the file but otherwise hidden in the UI and in the RDF4J console
|
||||
graphdb:base-URL "http://example.org/owlim#" ;
|
||||
graphdb:defaultNS "" ;
|
||||
graphdb:imports "" ;
|
||||
graphdb:repository-type "file-repository" ;
|
||||
graphdb:storage-folder "storage" ;
|
||||
graphdb:entity-index-size "10000000" ;
|
||||
graphdb:in-memory-literal-properties "true" ;
|
||||
graphdb:enable-literal-index "true" ;
|
||||
]
|
||||
].
|
||||
@@ -0,0 +1,9 @@
|
||||
version: '3.7'
|
||||
|
||||
services:
|
||||
|
||||
graphdb:
|
||||
image: graphdb
|
||||
container_name: graphdb
|
||||
ports:
|
||||
- "7200:7200"
|
||||
@@ -0,0 +1,33 @@
|
||||
#! /bin/bash
|
||||
REPOSITORY_ID="langchain"
|
||||
GRAPHDB_URI="http://localhost:7200/"
|
||||
|
||||
echo -e "\nUsing GraphDB: ${GRAPHDB_URI}"
|
||||
|
||||
function startGraphDB {
|
||||
echo -e "\nStarting GraphDB..."
|
||||
exec /opt/graphdb/dist/bin/graphdb
|
||||
}
|
||||
|
||||
function waitGraphDBStart {
|
||||
echo -e "\nWaiting GraphDB to start..."
|
||||
for _ in $(seq 1 5); do
|
||||
CHECK_RES=$(curl --silent --write-out '%{http_code}' --output /dev/null ${GRAPHDB_URI}/rest/repositories)
|
||||
if [ "${CHECK_RES}" = '200' ]; then
|
||||
echo -e "\nUp and running"
|
||||
break
|
||||
fi
|
||||
sleep 30s
|
||||
echo "CHECK_RES: ${CHECK_RES}"
|
||||
done
|
||||
}
|
||||
|
||||
function loadData {
|
||||
echo -e "\nImporting starwars-data.trig"
|
||||
curl -X POST -H "Content-Type: application/x-trig" -T /starwars-data.trig ${GRAPHDB_URI}/repositories/${REPOSITORY_ID}/statements
|
||||
}
|
||||
|
||||
startGraphDB &
|
||||
waitGraphDBStart
|
||||
loadData
|
||||
wait
|
||||
@@ -0,0 +1,5 @@
|
||||
set -ex
|
||||
|
||||
docker compose down -v --remove-orphans
|
||||
docker build --tag graphdb .
|
||||
docker compose up -d graphdb
|
||||
@@ -0,0 +1,43 @@
|
||||
@base <https://swapi.co/resource/>.
|
||||
@prefix voc: <https://swapi.co/vocabulary/> .
|
||||
@prefix owl: <http://www.w3.org/2002/07/owl#> .
|
||||
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
|
||||
|
||||
{
|
||||
|
||||
<besalisk/71>
|
||||
a voc:Besalisk , voc:Character ;
|
||||
rdfs:label "Dexter Jettster" ;
|
||||
voc:eyeColor "yellow" ;
|
||||
voc:gender "male" ;
|
||||
voc:height 198.0 ;
|
||||
voc:mass 102.0 ;
|
||||
voc:skinColor "brown" .
|
||||
|
||||
}
|
||||
|
||||
<https://swapi.co/ontology/> {
|
||||
|
||||
voc:Character a owl:Class .
|
||||
voc:Species a owl:Class .
|
||||
|
||||
voc:Besalisk a voc:Species;
|
||||
rdfs:label "Besalisk";
|
||||
voc:averageHeight 178.0;
|
||||
voc:averageLifespan "75";
|
||||
voc:character <https://swapi.co/resource/besalisk/71>;
|
||||
voc:language "besalisk";
|
||||
voc:skinColor "brown";
|
||||
voc:eyeColor "yellow" .
|
||||
|
||||
voc:averageHeight a owl:DatatypeProperty .
|
||||
voc:averageLifespan a owl:DatatypeProperty .
|
||||
voc:character a owl:ObjectProperty .
|
||||
voc:language a owl:DatatypeProperty .
|
||||
voc:skinColor a owl:DatatypeProperty .
|
||||
voc:eyeColor a owl:DatatypeProperty .
|
||||
voc:gender a owl:DatatypeProperty .
|
||||
voc:height a owl:DatatypeProperty .
|
||||
voc:mass a owl:DatatypeProperty .
|
||||
|
||||
}
|
||||
@@ -0,0 +1,181 @@
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from langchain_community.graphs import OntotextGraphDBGraph
|
||||
|
||||
"""
|
||||
cd libs/community/tests/integration_tests/graphs/docker-compose-ontotext-graphdb
|
||||
./start.sh
|
||||
"""
|
||||
|
||||
|
||||
def test_query() -> None:
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
query_ontology="CONSTRUCT {?s ?p ?o}"
|
||||
"FROM <https://swapi.co/ontology/> WHERE {?s ?p ?o}",
|
||||
)
|
||||
|
||||
query_results = graph.query(
|
||||
"PREFIX voc: <https://swapi.co/vocabulary/> "
|
||||
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> "
|
||||
"SELECT ?eyeColor "
|
||||
"WHERE {"
|
||||
' ?besalisk rdfs:label "Dexter Jettster" ; '
|
||||
" voc:eyeColor ?eyeColor ."
|
||||
"}"
|
||||
)
|
||||
assert len(query_results) == 1
|
||||
assert len(query_results[0]) == 1
|
||||
assert str(query_results[0][0]) == "yellow"
|
||||
|
||||
|
||||
def test_get_schema_with_query() -> None:
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
query_ontology="CONSTRUCT {?s ?p ?o}"
|
||||
"FROM <https://swapi.co/ontology/> WHERE {?s ?p ?o}",
|
||||
)
|
||||
|
||||
from rdflib import Graph
|
||||
|
||||
assert len(Graph().parse(data=graph.get_schema, format="turtle")) == 19
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"rdf_format, file_extension",
|
||||
[
|
||||
("json-ld", "json"),
|
||||
("json-ld", "jsonld"),
|
||||
("json-ld", "json-ld"),
|
||||
("xml", "rdf"),
|
||||
("xml", "xml"),
|
||||
("xml", "owl"),
|
||||
("pretty-xml", "xml"),
|
||||
("n3", "n3"),
|
||||
("turtle", "ttl"),
|
||||
("nt", "nt"),
|
||||
("trig", "trig"),
|
||||
("nquads", "nq"),
|
||||
("nquads", "nquads"),
|
||||
("trix", "trix"),
|
||||
],
|
||||
)
|
||||
def test_get_schema_from_file(
|
||||
tmp_path: Path, rdf_format: str, file_extension: str
|
||||
) -> None:
|
||||
expected_number_of_ontology_statements = 19
|
||||
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
query_ontology="CONSTRUCT {?s ?p ?o}"
|
||||
"FROM <https://swapi.co/ontology/> WHERE {?s ?p ?o}",
|
||||
)
|
||||
|
||||
from rdflib import ConjunctiveGraph, Graph
|
||||
|
||||
assert (
|
||||
len(Graph().parse(data=graph.get_schema, format="turtle"))
|
||||
== expected_number_of_ontology_statements
|
||||
)
|
||||
|
||||
# serialize the ontology schema loaded with the query in a local file
|
||||
# in various rdf formats and check that this results
|
||||
# in the same number of statements
|
||||
conjunctive_graph = ConjunctiveGraph()
|
||||
ontology_context = conjunctive_graph.get_context("https://swapi.co/ontology/")
|
||||
ontology_context.parse(data=graph.get_schema, format="turtle")
|
||||
|
||||
assert len(ontology_context) == expected_number_of_ontology_statements
|
||||
assert len(conjunctive_graph) == expected_number_of_ontology_statements
|
||||
|
||||
local_file = tmp_path / ("starwars-ontology." + file_extension)
|
||||
conjunctive_graph.serialize(local_file, format=rdf_format)
|
||||
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
local_file=str(local_file),
|
||||
)
|
||||
assert (
|
||||
len(Graph().parse(data=graph.get_schema, format="turtle"))
|
||||
== expected_number_of_ontology_statements
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"rdf_format", ["json-ld", "xml", "n3", "turtle", "nt", "trig", "nquads", "trix"]
|
||||
)
|
||||
def test_get_schema_from_file_with_explicit_rdf_format(
|
||||
tmp_path: Path, rdf_format: str
|
||||
) -> None:
|
||||
expected_number_of_ontology_statements = 19
|
||||
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
query_ontology="CONSTRUCT {?s ?p ?o}"
|
||||
"FROM <https://swapi.co/ontology/> WHERE {?s ?p ?o}",
|
||||
)
|
||||
|
||||
from rdflib import ConjunctiveGraph, Graph
|
||||
|
||||
assert (
|
||||
len(Graph().parse(data=graph.get_schema, format="turtle"))
|
||||
== expected_number_of_ontology_statements
|
||||
)
|
||||
|
||||
# serialize the ontology schema loaded with the query in a local file
|
||||
# in various rdf formats and check that this results
|
||||
# in the same number of statements
|
||||
conjunctive_graph = ConjunctiveGraph()
|
||||
ontology_context = conjunctive_graph.get_context("https://swapi.co/ontology/")
|
||||
ontology_context.parse(data=graph.get_schema, format="turtle")
|
||||
|
||||
assert len(ontology_context) == expected_number_of_ontology_statements
|
||||
assert len(conjunctive_graph) == expected_number_of_ontology_statements
|
||||
|
||||
local_file = tmp_path / "starwars-ontology.txt"
|
||||
conjunctive_graph.serialize(local_file, format=rdf_format)
|
||||
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
local_file=str(local_file),
|
||||
local_file_format=rdf_format,
|
||||
)
|
||||
assert (
|
||||
len(Graph().parse(data=graph.get_schema, format="turtle"))
|
||||
== expected_number_of_ontology_statements
|
||||
)
|
||||
|
||||
|
||||
def test_get_schema_from_file_with_wrong_extension(tmp_path: Path) -> None:
|
||||
expected_number_of_ontology_statements = 19
|
||||
|
||||
graph = OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
query_ontology="CONSTRUCT {?s ?p ?o}"
|
||||
"FROM <https://swapi.co/ontology/> WHERE {?s ?p ?o}",
|
||||
)
|
||||
|
||||
from rdflib import ConjunctiveGraph, Graph
|
||||
|
||||
assert (
|
||||
len(Graph().parse(data=graph.get_schema, format="turtle"))
|
||||
== expected_number_of_ontology_statements
|
||||
)
|
||||
|
||||
conjunctive_graph = ConjunctiveGraph()
|
||||
ontology_context = conjunctive_graph.get_context("https://swapi.co/ontology/")
|
||||
ontology_context.parse(data=graph.get_schema, format="turtle")
|
||||
|
||||
assert len(ontology_context) == expected_number_of_ontology_statements
|
||||
assert len(conjunctive_graph) == expected_number_of_ontology_statements
|
||||
|
||||
local_file = tmp_path / "starwars-ontology.trig"
|
||||
conjunctive_graph.serialize(local_file, format="nquads")
|
||||
|
||||
with pytest.raises(ValueError):
|
||||
OntotextGraphDBGraph(
|
||||
query_endpoint="http://localhost:7200/repositories/langchain",
|
||||
local_file=str(local_file),
|
||||
)
|
||||
Reference in New Issue
Block a user