def print_message(message: Message) -> None:
features = {**message.as_dict_nlu()}
seq_vecs, sen_vecs = message.get_dense_features(TEXT)
features["dense"] = {
"sequence": None if not seq_vecs else dense_message(seq_vecs.features),
"sentence": None if not sen_vecs else dense_message(sen_vecs.features),
}
seq_vecs, sen_vecs = message.get_sparse_features(TEXT)
features["sparse"] = {
"sequence":
None if not seq_vecs else sparse_message(seq_vecs.features),
"sentence":
None if not sen_vecs else sparse_message(sen_vecs.features),
}
if "text_tokens" in features.keys():
features["text_tokens"] = [t.text for t in features["text_tokens"]]
if "intent" in features.keys():
features["intent"] = {
k: v
for k, v in features["intent"].items() if "id" != k
}
if "intent_ranking" in features.keys():
features["intent_ranking"] = [{
k: v
for k, v in i.items() if "id" != k
} for i in features["intent_ranking"]]
if "diagnostic_data" in features.keys():
features["diagnostic_data"] = {
name: {k: dense_message(v)
for k, v in comp.items()}
for name, comp in features["diagnostic_data"].items()
}
print(features)
def __getitem__(self, item):
"""
Retreive a single embedding or a set of embeddings. We retreive the sentence encoding that
belongs to the entire utterance.
Arguments:
item: single string or list of strings
**Usage**
```python
from whatlies.language import DIETLanguage
lang = DIETLanguage("path/to/model.tar.gz")
lang[['hi', 'hello', 'greetings']]
```
"""
if isinstance(item, str):
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=RuntimeWarning)
msg = Message({"text": item})
for p in self.pipeline:
p.process(msg)
diagnostic_data = msg.as_dict_nlu()["diagnostic_data"]
key_of_interest = [
k for k in diagnostic_data.keys() if "DIET" in k
][0]
# It's assumed that the final token in the array here represents the __CLS__ token.
# These are also known as the "sentence embeddings"
tensors = diagnostic_data[key_of_interest]["text_transformed"]
return Embedding(item, tensors[-1][-1])
if isinstance(item, list):
return EmbeddingSet(*[self[i] for i in item])
raise ValueError(f"Item must be list of strings got {item}.")
def fetch_info_from_message(interpreter, text_input):
blob = interpreter.parse(text_input)
msg = Message({TEXT: text_input})
for i, element in enumerate(interpreter.pipeline):
element.process(msg)
nlu_dict = msg.as_dict_nlu()
tokens = [t.text for t in nlu_dict["text_tokens"]]
return blob, nlu_dict, tokens