Feature/pkgsplit (#83)

* Starting to spawn base package
* More package hacking
* Bedrock and VertexAI
* Parquet split
* Updated templates
* Utils
This commit is contained in:
cybermaggedon 2024-09-30 19:36:09 +01:00 committed by GitHub
parent 3fb75c617b
commit 9b91d5eee3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
262 changed files with 630 additions and 420 deletions

View file

@ -0,0 +1,173 @@
"""
Triples query service. Input is a (s, p, o) triple, some values may be
null. Output is a list of triples.
"""
from .... direct.cassandra import TrustGraph
from .... schema import TriplesQueryRequest, TriplesQueryResponse, Error
from .... schema import Value, Triple
from .... schema import triples_request_queue
from .... schema import triples_response_queue
from .... base import ConsumerProducer
module = ".".join(__name__.split(".")[1:-1])
default_input_queue = triples_request_queue
default_output_queue = triples_response_queue
default_subscriber = module
default_graph_host='localhost'
class Processor(ConsumerProducer):
def __init__(self, **params):
input_queue = params.get("input_queue", default_input_queue)
output_queue = params.get("output_queue", default_output_queue)
subscriber = params.get("subscriber", default_subscriber)
graph_host = params.get("graph_host", default_graph_host)
super(Processor, self).__init__(
**params | {
"input_queue": input_queue,
"output_queue": output_queue,
"subscriber": subscriber,
"input_schema": TriplesQueryRequest,
"output_schema": TriplesQueryResponse,
"graph_host": graph_host,
}
)
self.tg = TrustGraph([graph_host])
def create_value(self, ent):
if ent.startswith("http://") or ent.startswith("https://"):
return Value(value=ent, is_uri=True)
else:
return Value(value=ent, is_uri=False)
def handle(self, msg):
try:
v = msg.value()
# Sender-produced ID
id = msg.properties()["id"]
print(f"Handling input {id}...", flush=True)
triples = []
if v.s is not None:
if v.p is not None:
if v.o is not None:
resp = self.tg.get_spo(
v.s.value, v.p.value, v.o.value,
limit=v.limit
)
triples.append((v.s.value, v.p.value, v.o.value))
else:
resp = self.tg.get_sp(
v.s.value, v.p.value,
limit=v.limit
)
for t in resp:
triples.append((v.s.value, v.p.value, t.o))
else:
if v.o is not None:
resp = self.tg.get_os(
v.o.value, v.s.value,
limit=v.limit
)
for t in resp:
triples.append((v.s.value, t.p, v.o.value))
else:
resp = self.tg.get_s(
v.s.value,
limit=v.limit
)
for t in resp:
triples.append((v.s.value, t.p, t.o))
else:
if v.p is not None:
if v.o is not None:
resp = self.tg.get_po(
v.p.value, v.o.value,
limit=v.limit
)
for t in resp:
triples.append((t.s, v.p.value, v.o.value))
else:
resp = self.tg.get_p(
v.p.value,
limit=v.limit
)
for t in resp:
triples.append((t.s, v.p.value, t.o))
else:
if v.o is not None:
resp = self.tg.get_o(
v.o.value,
limit=v.limit
)
for t in resp:
triples.append((t.s, t.p, v.o.value))
else:
resp = self.tg.get_all(
limit=v.limit
)
for t in resp:
triples.append((t.s, t.p, t.o))
triples = [
Triple(
s=self.create_value(t[0]),
p=self.create_value(t[1]),
o=self.create_value(t[2])
)
for t in triples
]
print("Send response...", flush=True)
r = TriplesQueryResponse(triples=triples, error=None)
self.producer.send(r, properties={"id": id})
print("Done.", flush=True)
except Exception as e:
print(f"Exception: {e}")
print("Send error response...", flush=True)
r = TriplesQueryResponse(
error=Error(
type = "llm-error",
message = str(e),
),
response=None,
)
self.producer.send(r, properties={"id": id})
self.consumer.acknowledge(msg)
@staticmethod
def add_args(parser):
ConsumerProducer.add_args(
parser, default_input_queue, default_subscriber,
default_output_queue,
)
parser.add_argument(
'-g', '--graph-host',
default="localhost",
help=f'Graph host (default: localhost)'
)
def run():
Processor.start(module, __doc__)