async def handle_query(
self, query: NluQuery
) -> typing.AsyncIterable[typing.Union[NluIntentParsed, typing.Tuple[
NluIntent, TopicArgs], NluIntentNotRecognized, NluError, ]]:
"""Do intent recognition."""
original_input = query.input
try:
if not self.intent_graph and self.graph_path and self.graph_path.is_file(
):
# Load graph from file
_LOGGER.debug("Loading %s", self.graph_path)
with open(self.graph_path, mode="rb") as graph_file:
self.intent_graph = rhasspynlu.gzip_pickle_to_graph(
graph_file)
if self.intent_graph:
def intent_filter(intent_name: str) -> bool:
"""Filter out intents."""
if query.intent_filter:
return intent_name in query.intent_filter
return True
# Replace digits with words
if self.replace_numbers:
# Have to assume whitespace tokenization
words = rhasspynlu.replace_numbers(query.input.split(),
self.language)
query.input = " ".join(words)
input_text = query.input
# Fix casing for output event
if self.word_transform:
input_text = self.word_transform(input_text)
if self.failure_token and (self.failure_token
in query.input.split()):
# Failure token was found in input
recognitions = []
else:
# Pass in raw query input so raw values will be correct
recognitions = recognize(
query.input,
self.intent_graph,
intent_filter=intent_filter,
word_transform=self.word_transform,
fuzzy=self.fuzzy,
extra_converters=self.extra_converters,
)
else:
_LOGGER.error("No intent graph loaded")
recognitions = []
if NluHermesMqtt.is_success(recognitions):
# Use first recognition only.
recognition = recognitions[0]
assert recognition is not None
assert recognition.intent is not None
intent = Intent(
intent_name=recognition.intent.name,
confidence_score=recognition.intent.confidence,
)
slots = [
Slot(
entity=(e.source or e.entity),
slot_name=e.entity,
confidence=1.0,
value=e.value_dict,
raw_value=e.raw_value,
range=SlotRange(
start=e.start,
end=e.end,
raw_start=e.raw_start,
raw_end=e.raw_end,
),
) for e in recognition.entities
]
if query.custom_entities:
# Copy user-defined entities
for entity_name, entity_value in query.custom_entities.items(
):
slots.append(
Slot(
entity=entity_name,
confidence=1.0,
value={"value": entity_value},
))
# intentParsed
yield NluIntentParsed(
input=recognition.text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=intent,
slots=slots,
)
# intent
yield (
NluIntent(
input=recognition.text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=intent,
slots=slots,
asr_tokens=[
NluIntent.make_asr_tokens(recognition.tokens)
],
asr_confidence=query.asr_confidence,
raw_input=original_input,
wakeword_id=query.wakeword_id,
lang=(query.lang or self.lang),
custom_data=query.custom_data,
),
{
"intent_name": recognition.intent.name
},
)
else:
# Not recognized
yield NluIntentNotRecognized(
input=query.input,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
custom_data=query.custom_data,
)
except Exception as e:
_LOGGER.exception("handle_query")
yield NluError(
site_id=query.site_id,
session_id=query.session_id,
error=str(e),
context=original_input,
)
async def recognize(args: argparse.Namespace, core: Voice2JsonCore) -> None:
"""Recognize intent from sentence(s)."""
import networkx as nx
import rhasspynlu
from .train import WordCasing
# Make sure profile has been trained
assert core.check_trained(), "Not trained"
# Load settings
language_code = pydash.get(core.profile, "language.code", "en-US")
word_casing = WordCasing(
pydash.get(core.profile, "training.word-casing", "ignore").lower())
intent_graph_path = core.ppath("training.intent-graph", "intent.pickle.gz")
converters_dir = core.ppath("training.converters-directory", "converters")
stop_words_path = core.ppath("intent-recognition.stop-words",
"stop_words.txt")
fuzzy = pydash.get(core.profile, "intent-recognition.fuzzy", True)
# Load stop words
stop_words: typing.Optional[typing.Set[str]] = None
if stop_words_path and stop_words_path.is_file():
stop_words = set()
with open(stop_words_path, "r") as stop_words_file:
for line in stop_words_file:
line = line.strip()
if line:
stop_words.add(line)
# Load converters
extra_converters: typing.Optional[typing.Dict[str, typing.Any]] = {}
if converters_dir:
extra_converters = load_converters(converters_dir)
# Case transformation for input words
word_transform = None
if word_casing == WordCasing.UPPER:
word_transform = str.upper
elif word_casing == WordCasing.LOWER:
word_transform = str.lower
if args.sentence:
sentences = args.sentence
else:
if os.isatty(sys.stdin.fileno()):
print("Reading sentences from stdin", file=sys.stderr)
sentences = sys.stdin
# Whitelist function for intents
if args.intent_filter:
args.intent_filter = set(args.intent_filter)
def intent_filter(intent_name: str) -> bool:
"""Filter out intents."""
if args.intent_filter:
return intent_name in args.intent_filter
return True
# Load intent graph
_LOGGER.debug("Loading %s", intent_graph_path)
with gzip.GzipFile(intent_graph_path, mode="rb") as graph_gzip:
intent_graph = nx.readwrite.gpickle.read_gpickle(graph_gzip)
# Process sentences
try:
for sentence in sentences:
if args.text_input:
# Input is plain text
text = sentence
sentence_object = {"text": text}
else:
# Input is JSON
sentence_object = json.loads(sentence)
text = sentence_object.get(args.transcription_property, "")
# Tokenize
text = text.strip()
tokens = text.split()
if args.replace_numbers:
tokens = list(
rhasspynlu.replace_numbers(tokens, language=language_code))
# Recognize intent
recognitions = rhasspynlu.recognize(
tokens,
intent_graph,
fuzzy=fuzzy,
stop_words=stop_words,
word_transform=word_transform,
extra_converters=extra_converters,
intent_filter=intent_filter,
)
if recognitions:
# Use first recognition
recognition = recognitions[0]
else:
# Recognition failure
recognition = rhasspynlu.intent.Recognition.empty()
result = dataclasses.asdict(recognition)
# Add slots
result["slots"] = {e.entity: e.value for e in recognition.entities}
# Merge with input object
for key, value in result.items():
if (key not in sentence_object) or (value is not None):
sentence_object[key] = value
if not sentence_object["text"]:
sentence_object["text"] = text
# Keep text from transcription
sentence_object["raw_text"] = text
if args.perplexity:
# Compute perplexity of input text for one or more language
# models (stored in FST binary format).
perplexity = {}
for lm_fst_path in args.perplexity:
try:
perplexity[
lm_fst_path] = rhasspynlu.arpa_lm.get_perplexity(
text, lm_fst_path, debug=args.debug)
except Exception:
_LOGGER.exception(lm_fst_path)
sentence_object["perplexity"] = perplexity
print_json(sentence_object)
except KeyboardInterrupt:
pass
async def handle_query(
self, query: NluQuery
) -> typing.AsyncIterable[typing.Union[
NluIntentParsed, NluIntentNotRecognized, NluError, ]]:
"""Do intent recognition."""
try:
# Replace digits with words
if self.replace_numbers:
# Have to assume whitespace tokenization
words = rhasspynlu.replace_numbers(query.input.split(),
self.number_language)
query.input = " ".join(words)
input_text = query.input
# Fix casing for output event
if self.word_transform:
input_text = self.word_transform(input_text)
parse_url = urljoin(self.rasa_url, "model/parse")
_LOGGER.debug(parse_url)
async with self.http_session.post(
parse_url,
json={
"text": input_text,
"project": self.rasa_project
},
ssl=self.ssl_context,
) as response:
response.raise_for_status()
intent_json = await response.json()
intent = intent_json.get("intent", {})
intent_name = intent.get("name", "")
if intent_name and (query.intent_filter is None
or intent_name in query.intent_filter):
confidence_score = float(intent.get("confidence", 0.0))
slots = [
Slot(
entity=e.get("entity", ""),
slot_name=e.get("entity", ""),
confidence=float(e.get("confidence", 0.0)),
value={
"kind": "Unknown",
"value": e.get("value", ""),
"additional_info":
e.get("additional_info", {}),
"extractor": e.get("extractor", None),
},
raw_value=e.get("value", ""),
range=SlotRange(
start=int(e.get("start", 0)),
end=int(e.get("end", 1)),
raw_start=int(e.get("start", 0)),
raw_end=int(e.get("end", 1)),
),
) for e in intent_json.get("entities", [])
]
# intentParsed
yield NluIntentParsed(
input=input_text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=Intent(intent_name=intent_name,
confidence_score=confidence_score),
slots=slots,
)
else:
# Not recognized
yield NluIntentNotRecognized(
input=query.input,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
)
except Exception as e:
_LOGGER.exception("nlu query")
yield NluError(
site_id=query.site_id,
session_id=query.session_id,
error=str(e),
context=query.input,
)
async def handle_query(
self, query: NluQuery
) -> typing.AsyncIterable[typing.Union[NluIntentParsed, typing.Tuple[
NluIntent, TopicArgs], NluIntentNotRecognized, NluError, ]]:
"""Do intent recognition."""
# Check intent graph
try:
if (not self.intent_graph and self.intent_graph_path
and self.intent_graph_path.is_file()):
_LOGGER.debug("Loading %s", self.intent_graph_path)
with open(self.intent_graph_path, mode="rb") as graph_file:
self.intent_graph = rhasspynlu.gzip_pickle_to_graph(
graph_file)
# Check examples
if (self.intent_graph and self.examples_path
and self.examples_path.is_file()):
def intent_filter(intent_name: str) -> bool:
"""Filter out intents."""
if query.intent_filter:
return intent_name in query.intent_filter
return True
original_text = query.input
# Replace digits with words
if self.replace_numbers:
# Have to assume whitespace tokenization
words = rhasspynlu.replace_numbers(query.input.split(),
self.language)
query.input = " ".join(words)
input_text = query.input
# Fix casing
if self.word_transform:
input_text = self.word_transform(input_text)
recognitions: typing.List[rhasspynlu.intent.Recognition] = []
if input_text:
recognitions = rhasspyfuzzywuzzy.recognize(
input_text,
self.intent_graph,
str(self.examples_path),
intent_filter=intent_filter,
extra_converters=self.extra_converters,
)
else:
_LOGGER.error("No intent graph or examples loaded")
recognitions = []
# Use first recognition only if above threshold
if (recognitions and recognitions[0] and recognitions[0].intent
and (recognitions[0].intent.confidence >=
self.confidence_threshold)):
recognition = recognitions[0]
assert recognition.intent
intent = Intent(
intent_name=recognition.intent.name,
confidence_score=recognition.intent.confidence,
)
slots = [
Slot(
entity=(e.source or e.entity),
slot_name=e.entity,
confidence=1.0,
value=e.value_dict,
raw_value=e.raw_value,
range=SlotRange(
start=e.start,
end=e.end,
raw_start=e.raw_start,
raw_end=e.raw_end,
),
) for e in recognition.entities
]
if query.custom_entities:
# Copy user-defined entities
for entity_name, entity_value in query.custom_entities.items(
):
slots.append(
Slot(
entity=entity_name,
confidence=1.0,
value={"value": entity_value},
))
# intentParsed
yield NluIntentParsed(
input=recognition.text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=intent,
slots=slots,
)
# intent
yield (
NluIntent(
input=recognition.text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=intent,
slots=slots,
asr_tokens=[
NluIntent.make_asr_tokens(recognition.tokens)
],
asr_confidence=query.asr_confidence,
raw_input=original_text,
wakeword_id=query.wakeword_id,
lang=(query.lang or self.lang),
custom_data=query.custom_data,
),
{
"intent_name": recognition.intent.name
},
)
else:
# Not recognized
yield NluIntentNotRecognized(
input=query.input,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
custom_data=query.custom_data,
)
except Exception as e:
_LOGGER.exception("handle_query")
yield NluError(
site_id=query.site_id,
session_id=query.session_id,
error=str(e),
context=original_text,
)
async def handle_query(
self, query: NluQuery
) -> typing.AsyncIterable[typing.Union[NluIntentParsed, typing.Tuple[
NluIntent, TopicArgs], NluIntentNotRecognized, NluError, ]]:
"""Do intent recognition."""
try:
original_input = query.input
# Replace digits with words
if self.replace_numbers:
# Have to assume whitespace tokenization
words = rhasspynlu.replace_numbers(query.input.split(),
self.number_language)
query.input = " ".join(words)
input_text = query.input
# Fix casing for output event
if self.word_transform:
input_text = self.word_transform(input_text)
parse_url = urljoin(self.rasa_url, "model/parse")
_LOGGER.debug(parse_url)
async with self.http_session.post(
parse_url,
json={
"text": input_text,
"project": self.rasa_project
},
ssl=self.ssl_context,
) as response:
response.raise_for_status()
intent_json = await response.json()
intent = intent_json.get("intent", {})
intent_name = intent.get("name", "")
if intent_name and (query.intent_filter is None
or intent_name in query.intent_filter):
confidence_score = float(intent.get("confidence", 0.0))
slots = [
Slot(
entity=e.get("entity", ""),
slot_name=e.get("entity", ""),
confidence=float(e.get("confidence", 0.0)),
value={
"kind": "Unknown",
"value": e.get("value", "")
},
raw_value=e.get("value", ""),
range=SlotRange(
start=int(e.get("start", 0)),
end=int(e.get("end", 1)),
raw_start=int(e.get("start", 0)),
raw_end=int(e.get("end", 1)),
),
) for e in intent_json.get("entities", [])
]
if query.custom_entities:
# Copy user-defined entities
for entity_name, entity_value in query.custom_entities.items(
):
slots.append(
Slot(
entity=entity_name,
confidence=1.0,
value={"value": entity_value},
))
# intentParsed
yield NluIntentParsed(
input=input_text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=Intent(intent_name=intent_name,
confidence_score=confidence_score),
slots=slots,
)
# intent
yield (
NluIntent(
input=input_text,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
intent=Intent(
intent_name=intent_name,
confidence_score=confidence_score,
),
slots=slots,
asr_tokens=[
NluIntent.make_asr_tokens(input_text.split())
],
asr_confidence=query.asr_confidence,
raw_input=original_input,
lang=(query.lang or self.lang),
custom_data=query.custom_data,
),
{
"intent_name": intent_name
},
)
else:
# Not recognized
yield NluIntentNotRecognized(
input=query.input,
id=query.id,
site_id=query.site_id,
session_id=query.session_id,
custom_data=query.custom_data,
)
except Exception as e:
_LOGGER.exception("nlu query")
yield NluError(
site_id=query.site_id,
session_id=query.session_id,
error=str(e),
context=query.input,
)