Batch processing optimization (#66)

* Update lab_initialization.py
* Update pre_install.py
* Update zero_shot.py
* Update tag.py
* Update Dockerfile
* Update models.py


Removes a large zero shot model used until now, for a smaller, more efficient, with similar accuracy model.
We now are able to add it to the batch processing data pipeline and remove it from inter-item processing, accelerating the process & lot, reducing RAM usage over time.

The image will now be 1.2Gb smaller or so, and will have very fast item processing time, with all models loaded in RAM beforehand.

Dockerfile

@@ -14,8 +14,7 @@ RUN pip3.10 install --no-cache-dir \
         'git+https://github.com/exorde-labs/exorde_data.git' \
         'git+https://github.com/exorde-labs/exorde-client.git'\
         selenium==4.2.0 \
-        wtpsplit==1.3.0 \
-    && pip3.10 install --no-cache-dir --upgrade 'git+https://github.com/JustAnotherArchivist/snscrape.git'
+        wtpsplit==1.3.0
 
 # Clean cache now that we have installed everything
 RUN rm -rf /root/.cache/* \

exorde/lab_initialization.py

@@ -4,18 +4,13 @@
 import torch
 from transformers import pipeline
 from argostranslate import translate as _translate
+from exorde.tag import initialize_models
 
 
 def lab_initialization():
     device = torch.cuda.current_device() if torch.cuda.is_available() else -1
-    classifier = pipeline(
-        "zero-shot-classification",
-        model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",
-        device=device,
-        batch_size=16,
-        top_k=None,
-        max_length=64,
-    )
+    # initalize models
+    models = initialize_models(device)
     labels = requests.get(
         "https://raw.githubusercontent.com/exorde-labs/TestnetProtocol/main/targets/class_names.json"
     ).json()
@@ -34,7 +29,7 @@ def lab_initialization():
     installed_languages = _translate.get_installed_languages()
     return {
         "device": device,
-        "classifier": classifier,
+        "models": models,
         "labeldict": labels,
         "mappings": mappings,
         "nlp": nlp,

exorde/models.py

@@ -155,6 +155,7 @@ class Age(dict, metaclass=MadType):
 class Analysis(dict, metaclass=MadType):
     language_score: LanguageScore
     sentiment: Sentiment
+    classification: Classification
     embedding: Embedding
     gender: Gender
     text_type: TextType

exorde/pre_install.py

@@ -16,12 +16,10 @@
 test_lang_detect = ft_test_detect("test")
 
 models = [
-    "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",
+    "MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33",
     "SamLowe/roberta-base-go_emotions",
     "cardiffnlp/twitter-roberta-base-irony",
-    "salesken/query_wellformedness_score",
     "marieke93/MiniLM-evidence-types",
-    "alimazhar-110/website_classification",
     "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
     "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
     "bert-large-uncased"

exorde/process_batch.py

@@ -258,7 +258,7 @@ async def process_batch(
         completed: ProcessedItem = ProcessedItem(
             item=prot_item,
             analysis=ProtocolAnalysis(
-                classification=processed.classification,
+                classification=analysis.classification,
                 top_keywords=processed.top_keywords,
                 language_score=analysis.language_score,
                 gender=analysis.gender,