lhr0909

import csv
import json
import datetime

events = []

# Open the CSV
with open("portable_user_history-2024-06-02-csv.csv", "r") as f:
    reader = csv.DictReader(
        f,

lhr0909

📄 Document: 390ade4aa6f98236224082851331c670
╭───────────┬──────────────────────────────────────────────────────────────────╮
│ Attribute │ Value                                                            │
├───────────┼──────────────────────────────────────────────────────────────────┤
│ text      │ Naw man                                                          │
│ embedding │ ▄▄▄                                                              │
╰───────────┴──────────────────────────────────────────────────────────────────╯
└── 🔶 Matches
    ├── 📄 Document: 626c8c7ed40279b4152aae627223e253
    │   ╭───────────┬──────────────────────────────────────────────────────────────────╮

lhr0909

from jina import Flow
from docarray import DocumentArray, Document

from executor import DIETClassifierExecutor

f = Flow().add(
    uses='jinahub+docker://ConveRTFeaturizer/latest'
).add(
    uses=DIETClassifierExecutor, uses_with={ 'model_path': './lightning_logs/version_4/checkpoints/epoch=999-step=1000.ckpt' }
)

lhr0909

from typing import Any, Dict, List
import yaml
from pathlib import Path
from jina import Executor, requests
from docarray import DocumentArray, Document
from docarray.score import NamedScore
import torch
import torch.nn.functional as F

from diet_classifier.config import DIETClassifierConfig

lhr0909

nlu:
  - intent: greet
    examples:
      - Hello
      - Hi
      - Hey
  - intent: affirm
    examples:
      - "Yes"
      - "Yes, that's right"

lhr0909

from typing import Dict, Any, List
from pathlib import Path
import yaml
import torch
import pytorch_lightning as pl
from torch.utils.data import DataLoader
from jina import Flow
from docarray import DocumentArray, Document

lhr0909

from conversational_sentence_encoder.vectorizers import SentenceEncoder
from jina import Executor, requests
from docarray import DocumentArray

class ConveRTFeaturizer(Executor):
    def __init__(self, multiple_contexts=False, **kwargs):
        super(ConveRTFeaturizer, self).__init__(**kwargs)
        self.sentence_encoder = SentenceEncoder(multiple_contexts=multiple_contexts)

    @requests

lhr0909

import torch
from torch import optim, nn, Tensor
import torch.nn.functional as F
import pytorch_lightning as pl

from .config import DIETClassifierConfig
from .models import IntentClassifier

class DIETClassifier(pl.LightningModule):
    def __init__(self, config: DIETClassifierConfig):

lhr0909

import torch
from torch import nn, Tensor

from .config import DIETClassifierConfig

class IntentClassifier(nn.Module):
    def __init__(self, config: DIETClassifierConfig):
        super().__init__()
        # Rasa's embedding layer is actually a "dense embedding layer" which is just a Keras dense layer
        # equivalent to a PyTorch Linear layer.

lhr0909

Keybase proof

I hereby claim:

• I am lhr0909 on github.
• I am lhr0909 (https://keybase.io/lhr0909) on keybase.
• I have a public key ASBuOVwpHfFIg-c6qEl2uyn_ANt93FTFtv_XTVkSJ2bkeAo

To claim this, I am signing this object: