slim container

Dockerfile

@@ -6,6 +6,5 @@ COPY . /app
 
 # Install any needed packages specified in requirements.txt
 RUN pip install --no-cache-dir -r requirements.txt
-RUN python initialize_models.py
 
 CMD ["python", "-m", "psl_proof"]

psl_proof/models/cargo_data.py

@@ -1,7 +1,6 @@
 from enum import Enum
 from dataclasses import dataclass, field
 from typing import Dict, List, Optional, Any
-import numpy as np
 import math
 from typing import Union
 
@@ -215,9 +214,7 @@ def to_dict(self):
 
     @staticmethod
     def convert_to_serializable(obj: Any) -> Any:
-        if isinstance(obj, np.float32):
-            return float(obj)  # Convert float32 to float
-        elif isinstance(obj, dict):
+        if isinstance(obj, dict):
             return {k: CargoData.convert_to_serializable(v) for k, v in obj.items()}  # Recursively handle dictionary values
         elif isinstance(obj, list):
             return [CargoData.convert_to_serializable(item) for item in obj]  # Recursively handle list items

psl_proof/utils/validate_data.py

@@ -1,7 +1,6 @@
 from psl_proof.models.cargo_data import CargoData, ChatData, SourceChatData, SourceData
 from psl_proof.models.proof_response import ProofResponse
 from typing import List, Dict, Any
-from psl_proof.utils.feature_extraction import get_sentiment_data, get_keywords_keybert #, get_keywords_lda
 from psl_proof.utils.submission import get_historical_chats, ChatHistory, SubmissionChat
 
 
@@ -90,18 +89,10 @@ def validate_data(
             #print(f"source_contents: {source_contents}")
             # if chat data has meaningful data...
             if quality > score_threshold and uniqueness > score_threshold:
-                chat_sentiment = get_sentiment_data(
-                    source_contents
-                )
-                chat_keywords = get_keywords_keybert(
-                    source_contents
-                )
                 # Create a ChatData instance and add it to the list
                 chat_data = ChatData(
                     chat_id=source_chat.chat_id,
-                    chat_length=contents_length,
-                    sentiment=chat_sentiment,
-                    keywords=chat_keywords
+                    chat_length=contents_length
                 )
                 #print(f"chat_data: {chat_data}")
                 cargo_data.chat_list.append(

requirements.txt

@@ -1,41 +1,12 @@
---extra-index-url https://download.pytorch.org/whl/cpu
 annotated-types==0.7.0
 bitarray==3.0.0
 certifi==2024.8.30
 charset-normalizer==3.4.0
-filelock==3.16.1
-fsspec==2024.10.0
-huggingface-hub==0.26.5
 idna==3.10
-Jinja2==3.1.4
-joblib==1.4.2
-keybert==0.8.5
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-mdurl==0.1.2
-mpmath==1.3.0
-networkx==3.4.2
-numpy==2.2.0
-packaging==24.2
-pillow==11.0.0
 pybloom_live==4.0.0
 pydantic==2.10.3
 pydantic_core==2.27.1
-Pygments==2.18.0
-PyYAML==6.0.2
-regex==2024.11.6
 requests==2.32.3
-rich==13.9.4
-safetensors==0.4.5
-scikit-learn==1.6.0
-scipy==1.14.1
-sentence-transformers==3.3.1
-sympy==1.13.1
-threadpoolctl==3.5.0
-tokenizers==0.21.0
-torch==2.5.1+cpu
-tqdm==4.67.1
-transformers==4.47.0
 typing_extensions==4.12.2
 urllib3==2.2.3
 xxhash==3.5.0