mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-07-17 17:21:02 +02:00
137 lines
3.7 KiB
Python
Executable file
137 lines
3.7 KiB
Python
Executable file
|
|
"""
|
|
Simple decoder, accepts text chunks input, applies entity analysis to
|
|
get topics which are output as graph edges.
|
|
"""
|
|
|
|
import urllib.parse
|
|
import json
|
|
|
|
from .... schema import Chunk, Triple, Triples, Metadata, Value
|
|
from .... schema import chunk_ingest_queue, triples_store_queue
|
|
from .... schema import prompt_request_queue
|
|
from .... schema import prompt_response_queue
|
|
from .... log_level import LogLevel
|
|
from .... clients.prompt_client import PromptClient
|
|
from .... rdf import TRUSTGRAPH_ENTITIES, DEFINITION
|
|
from .... base import ConsumerProducer
|
|
|
|
DEFINITION_VALUE = Value(value=DEFINITION, is_uri=True)
|
|
|
|
module = ".".join(__name__.split(".")[1:-1])
|
|
|
|
default_input_queue = chunk_ingest_queue
|
|
default_output_queue = triples_store_queue
|
|
default_subscriber = module
|
|
|
|
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)
|
|
pr_request_queue = params.get(
|
|
"prompt_request_queue", prompt_request_queue
|
|
)
|
|
pr_response_queue = params.get(
|
|
"prompt_response_queue", prompt_response_queue
|
|
)
|
|
|
|
super(Processor, self).__init__(
|
|
**params | {
|
|
"input_queue": input_queue,
|
|
"output_queue": output_queue,
|
|
"subscriber": subscriber,
|
|
"input_schema": Chunk,
|
|
"output_schema": Triples,
|
|
"prompt_request_queue": pr_request_queue,
|
|
"prompt_response_queue": pr_response_queue,
|
|
}
|
|
)
|
|
|
|
self.prompt = PromptClient(
|
|
pulsar_host=self.pulsar_host,
|
|
input_queue=pr_request_queue,
|
|
output_queue=pr_response_queue,
|
|
subscriber = module + "-prompt",
|
|
)
|
|
|
|
def to_uri(self, text):
|
|
|
|
part = text.replace(" ", "-").lower().encode("utf-8")
|
|
quoted = urllib.parse.quote(part)
|
|
uri = TRUSTGRAPH_ENTITIES + quoted
|
|
|
|
return uri
|
|
|
|
def get_topics(self, chunk):
|
|
|
|
return self.prompt.request_topics(chunk)
|
|
|
|
def emit_edge(self, metadata, s, p, o):
|
|
|
|
t = Triples(
|
|
metadata=metadata,
|
|
triples=[Triple(s=s, p=p, o=o)],
|
|
)
|
|
self.producer.send(t)
|
|
|
|
def handle(self, msg):
|
|
|
|
v = msg.value()
|
|
print(f"Indexing {v.metadata.id}...", flush=True)
|
|
|
|
chunk = v.chunk.decode("utf-8")
|
|
|
|
try:
|
|
|
|
defs = self.get_topics(chunk)
|
|
|
|
for defn in defs:
|
|
|
|
s = defn.name
|
|
o = defn.definition
|
|
|
|
if s == "": continue
|
|
if o == "": continue
|
|
|
|
if s is None: continue
|
|
if o is None: continue
|
|
|
|
s_uri = self.to_uri(s)
|
|
|
|
s_value = Value(value=str(s_uri), is_uri=True)
|
|
o_value = Value(value=str(o), is_uri=False)
|
|
|
|
self.emit_edge(v. metadata, s_value, DEFINITION_VALUE, o_value)
|
|
|
|
except Exception as e:
|
|
print("Exception: ", e, flush=True)
|
|
|
|
print("Done.", flush=True)
|
|
|
|
@staticmethod
|
|
def add_args(parser):
|
|
|
|
ConsumerProducer.add_args(
|
|
parser, default_input_queue, default_subscriber,
|
|
default_output_queue,
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--prompt-request-queue',
|
|
default=prompt_request_queue,
|
|
help=f'Prompt request queue (default: {prompt_request_queue})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'--prompt-completion-response-queue',
|
|
default=prompt_response_queue,
|
|
help=f'Prompt response queue (default: {prompt_response_queue})',
|
|
)
|
|
|
|
def run():
|
|
|
|
Processor.start(module, __doc__)
|
|
|