Hf related changes

.gitignore

@@ -1 +1,2 @@
-*.bat
+*.bat
+__pycache__

Dockerfile

@@ -1,13 +1,13 @@
 # Use an official Python runtime as a parent image
 FROM nvidia/cuda:12.3.1-runtime-ubuntu22.04 
 # Set Python to use unbuffered mode
-ENV PYTHONUNBUFFERED 1
+ENV PYTHONUNBUFFERED=1
 RUN apt-get update && \
     apt-get install -y --no-install-recommends python3-pip python3-dev && \
     rm -rf /var/lib/apt/lists/*
 # Set the working directory in the container
 RUN mkdir /var/www
-ENV HOME /var/www
+ENV HOME=/var/www
 WORKDIR /var/www
 
 # Copy the current directory contents into the container at /app
@@ -15,18 +15,15 @@ COPY . /var/www
 
 RUN pip install -r requirements.txt
 RUN pip install torch==1.12.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
-# RUN python -c "import nltk; nltk.download('punkt')"
-# RUN python -c "import nltk; nltk.download('stopwords')"
-# RUN python -m nltk.downloader -d $HOME/nltk_data punkt stopwords
 
-EXPOSE 7866
+EXPOSE 7860
 
 RUN --mount=type=secret,id=HF_TOKEN,mode=0444,required=true \
     HF_TOKEN=$(cat /run/secrets/HF_TOKEN) && export HF_TOKEN
 
 # Define environment variable
-ENV FLASK_APP app.py \
-    HF_MODEL_NAME "muryshev/e5_large_rus_finetuned_20240120_122822_ep6"
+ENV FLASK_APP=app.py \
+    HF_MODEL_NAME="muryshev/e5_large_rus_finetuned_20240120_122822_ep6"
 
 # Run app.py when the container launches
-CMD flask run --host=0.0.0.0 --port=7869
+CMD flask run --host=0.0.0.0 --port=7860

app.py

@@ -3,10 +3,8 @@ import os
 from flask import Flask, jsonify, request
 from semantic_search import SemanticSearch
 
-print(os.environ.get("HF_TOKEN", ""))
-print(os.environ.get("HF_MODEL_NAME", ""))
 
-search = SemanticSearch('cuda')
+search = SemanticSearch()
 search.test_search()
 
 app = Flask(__name__)

semantic_search.py

@@ -16,8 +16,7 @@ from legal_info_search_utils.metrics import calculate_metrics_at_k
 
 
 global_data_path = os.environ.get("GLOBAL_DATA_PATH", "legal_info_search_data/")
-global_model_path = os.environ.get("GLOBAL_MODEL_PATH", 
-                                   "legal_info_search_model/20240120_122822_ep6/")
+global_model_path = os.environ.get("GLOBAL_MODEL_PATH", "e5_large_rus_finetuned_20240120_122822_ep6")
 
 # размеченные консультации
 data_path_consult = os.environ.get("DATA_PATH_CONSULT", 
@@ -51,7 +50,7 @@ hf_token = os.environ.get("HF_TOKEN", "")
 hf_model_name = os.environ.get("HF_MODEL_NAME", "")
 
 class SemanticSearch:
-    def __init__(self, device, index_type="IndexFlatIP", do_embedding_norm=True, 
+    def __init__(self, index_type="IndexFlatIP", do_embedding_norm=True, 
                  faiss_batch_size=8, do_normalization=True):
         self.device = device
         self.do_embedding_norm = do_embedding_norm