test

API_LOGS/log_file.log

@@ -0,0 +1,10 @@
+2024-02-13 13:57:19,153:DEBUG:pretrained.py:<module>:54:loading all models...
+2024-02-13 13:57:19,153:INFO:SentenceTransformer.py:__init__:110:Load pretrained SentenceTransformer: models--sentence-transformers--all-MiniLM-L6-v2/snapshots/1a310852cf8e58d22c5ebff537711d504ad4ad66
+2024-02-13 13:57:19,298:INFO:SentenceTransformer.py:__init__:216:Use pytorch device_name: cpu
+2024-02-13 13:57:19,302:INFO:_internal.py:_log:96:WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on all addresses (0.0.0.0)
+ * Running on http://127.0.0.1:9669
+ * Running on http://192.168.1.11:9669
+2024-02-13 13:57:19,302:INFO:_internal.py:_log:96:Press CTRL+C to quit
+2024-02-13 13:57:24,234:INFO:_internal.py:_log:96:127.0.0.1 - - [13/Feb/2024 13:57:24] "POST /match_text HTTP/1.1" 400 -
+2024-02-13 13:57:36,992:INFO:_internal.py:_log:96:127.0.0.1 - - [13/Feb/2024 13:57:36] "POST /match_text HTTP/1.1" 415 -

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.8
+
+RUN mkdir /app
+
+WORKDIR /app
+
+ADD . /app
+
+# RUN apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
+
+# RUN apt update
+
+# RUN apt install tesseract-ocr -y
+
+RUN pip install -r requirements.txt
+
+#GL_MODEL
+# https://drive.google.com/file/d/1mgO6Y5_7EpJ9LpW1koXdfkd-U70MXL_f/view?usp=sharing
+# RUN wget --no-check-certificate --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1mgO6Y5_7EpJ9LpW1koXdfkd-U70MXL_f' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1mgO6Y5_7EpJ9LpW1koXdfkd-U70MXL_f" -O GL_MODEL.zip && rm -rf /tmp/cookies.txt
+
+#UL_MODEL
+# https://drive.google.com/file/d/1XFl6DBejzZ0nlCgz71yuY1LnvNHI9wWG/view?usp=sharing
+# RUN wget --no-check-certificate --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1XFl6DBejzZ0nlCgz71yuY1LnvNHI9wWG' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1XFl6DBejzZ0nlCgz71yuY1LnvNHI9wWG" -O UL_MODEL.zip && rm -rf /tmp/cookies.txt
+
+#core classify
+# https://drive.google.com/file/d/1yHls7Z8vUaPFSuCkv59E0qcOFwK4I75N/view?usp=sharing
+# RUN wget --no-check-certificate --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=1yHls7Z8vUaPFSuCkv59E0qcOFwK4I75N' -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=1yHls7Z8vUaPFSuCkv59E0qcOFwK4I75N" -O core.zip && rm -rf /tmp/cookies.txt
+
+# RUN python -m spacy download en_core_web_md
+# RUN unzip GL_MODEL.zip
+# RUN unzip UL_MODEL.zip
+# RUN unzip core.zip
+
+EXPOSE 7860
+CMD ["python", "pretrained.py"]

pretrained.py

@@ -0,0 +1,72 @@
+from sentence_transformers import SentenceTransformer, util
+import pickle
+import pandas as pd
+import numpy as np
+import os
+import json
+from flask import Flask, request, jsonify
+from werkzeug.utils import secure_filename
+import logging
+
+
+# Set up root logger, and add a file handler to root logger
+logging.basicConfig(filename = 'API_LOGS/log_file.log',
+                    filemode='w',
+                    level = logging.DEBUG,
+                    format = '%(asctime)s:%(levelname)s:%(filename)s:%(funcName)s:%(lineno)d:%(message)s')
+
+logger = logging.getLogger()
+
+
+app = Flask(__name__)
+
+
+
+@app.route('/match_text', methods=['POST'])
+def similarity():
+
+    try:
+
+        logger.debug(f'receiving the json data')
+        data = request.get_json()
+        logger.debug(f'received the json data')
+
+        if 'text1' not in data or 'text2' not in data:
+            logger.debug(f'Error : Both text1 and text2 must be provided!')
+            return jsonify({'error': 'Both text1 and text2 must be provided.'}), 400
+
+        logger.debug(f'extracting the sentences from the request')
+        sentences1 = data['text1']
+        sentences2 = data['text2']
+        logger.debug(f'extracted the sentences from the request')
+
+        logger.debug(f'calculating the embeddings')
+        embeddings1 = model.encode(sentences1, convert_to_tensor=True)
+        embeddings2 = model.encode(sentences2, convert_to_tensor=True)
+        logger.debug(f'embeddings calculated')
+
+        logger.debug(f'calculating the cosine score')
+        cosine_scores = util.cos_sim(embeddings1, embeddings2)
+        logger.debug(f'calculated the cosine score')
+
+        print(f'{cosine_scores[0][0].item()}')
+        return jsonify({'similarity_score': cosine_scores[0][0].item()}), 200
+
+    except Exception as e:
+        logger.debug(f'Unknown error! : {e}')
+        return jsonify({'error' : str(e)}), 500
+
+
+
+if __name__ == '__main__':
+
+    logger.debug(f'loading model...')
+    print(f'loading model...')
+
+    # model = SentenceTransformer("all-MiniLM-L6-v2", cache_folder='./')
+    model = SentenceTransformer("all-MiniLM-L6-v2")#, cache_folder='./')
+    #model = SentenceTransformer("models--sentence-transformers--all-MiniLM-L6-v2/snapshots/1a310852cf8e58d22c5ebff537711d504ad4ad66")
+    model.max_seq_length = 512
+    print(f'model max lenght is :{model.max_seq_length}')
+
+    app.run(debug=False, port = 7860, host = '0.0.0.0', threaded = False)

requirements.txt

@@ -0,0 +1,56 @@
+blinker==1.7.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+filelock==3.13.1
+Flask==3.0.2
+fsspec==2024.2.0
+huggingface-hub==0.20.3
+idna==3.6
+importlib-metadata==7.0.1
+itsdangerous==2.1.2
+Jinja2==3.1.3
+joblib==1.3.2
+MarkupSafe==2.1.5
+mpmath==1.3.0
+networkx==3.1
+nltk==3.8.1
+numpy==1.24.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+packaging==23.2
+pandas==2.0.3
+pillow==10.2.0
+python-dateutil==2.8.2
+pytz==2024.1
+PyYAML==6.0.1
+regex==2023.12.25
+requests==2.31.0
+safetensors==0.4.2
+scikit-learn==1.3.2
+scipy==1.10.1
+sentence-transformers==2.3.1
+sentencepiece==0.1.99
+six==1.16.0
+sympy==1.12
+threadpoolctl==3.2.0
+tokenizers==0.15.2
+torch==2.2.0
+tqdm==4.66.2
+transformers==4.37.2
+triton==2.2.0
+typing_extensions==4.9.0
+tzdata==2024.1
+urllib3==2.2.0
+Werkzeug==3.0.1
+zipp==3.17.0