Store Message Toxicity in database (#553)

* [NEW] MessageToxicity table

* [NEW] Alembic message Toxicity

* [NEW] Model name enum

* [NEW] Refactor Enum HF

* [NEW] Settings: DEBUT_SKIP_TOXICITY_CALCULATION

* [NEW] Store toxicity values

* [FIX] Merge conflict

* [FIX] Documentation

* [NEW] save_toxicity: function

* [FIX] Formatted string

* [NEW] DEBUG_SKIP_TOXICITY_CALCULATION=True

* [FIX] HfClassificationModel

* [FIX] Alembic merge heads

* [NEW] Refactor save_toxicity

* [NEW] Separating score/label

* [NEW] Store score and label

* [FIX] Cleaning Alembic

* [NEW] Clean HF names

* [NEW] Not type hinting

* [NEW] Update alembic versions

* [NEW] Revert the changes

* [NEW] Type hinting label & score

* Updated down_revision in migration script

Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>

backend/oasst_backend/api/v1/hugging_face.py

@@ -4,7 +4,7 @@ from fastapi import APIRouter, Depends
 from oasst_backend.api import deps
 from oasst_backend.models import ApiClient
 from oasst_backend.schemas.hugging_face import ToxicityClassification
-from oasst_backend.utils.hugging_face import HfUrl, HuggingFaceAPI
+from oasst_backend.utils.hugging_face import HfClassificationModel, HfUrl, HuggingFaceAPI
 
 router = APIRouter()
 
@@ -25,7 +25,8 @@ async def get_text_toxicity(
         ToxicityClassification: the score of toxicity of the message.
     """
 
-    api_url: str = HfUrl.HUGGINGFACE_TOXIC_ROBERTA.value
+    api_url: str = HfUrl.HUGGINGFACE_TOXIC_CLASSIFICATION.value + "/" + HfClassificationModel.TOXIC_ROBERTA.value
+
     hugging_face_api = HuggingFaceAPI(api_url)
     response = await hugging_face_api.post(msg)