Added all files from first attempt

.env.example

@@ -0,0 +1,6 @@
+DATABASE_URL=postgresql://postgres:cocoon@localhost:5432/cocoon
+HASURA_SECRET_HEADER_VALUE=secret
+HASURA_EVENTS_HEADER=x-hasura-event-secret
+DISCORD_WEBHOOK_URL=https://discord.com/api/webhooks/1234567890/secret
+TOKENIZERS_PARALLELISM=false
+HF_TOKEN=

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+.venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+playground/dumps/
+api/tokenizer
+.DS_STORE

Dockerfile

@@ -0,0 +1,35 @@
+# Use an official Python runtime as a parent image
+FROM python:3.12-slim-bookworm
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+
+# Ensure HF_TOKEN is picked up from the environment
+ENV HF_TOKEN=${HUGGINGFACE_TOKEN}
+
+# Set work directory in the container
+WORKDIR /code
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    default-libmysqlclient-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create the cache directory
+RUN mkdir -p /models/cache
+
+# Ensure the directory is writable
+RUN chmod -R 777 /models/cache
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the current directory contents into the container at /code
+COPY ./api /code/api
+
+# Run the command to start uWSGI
+# Run Huggingface CLI login during runtime
+CMD ["sh", "-c", "huggingface-cli login --token $HF_TOKEN --add-to-git-credential && gunicorn -b 0.0.0.0:7860 api.app:app"]

README.md

@@ -1,10 +1,12 @@
 ---
-title: VectorSearch
-emoji: 📚
+title: GenerateEmbeddings
+emoji: 💻
 colorFrom: green
-colorTo: pink
+colorTo: yellow
 sdk: docker
 pinned: false
+license: mit
+short_description: Used to generate embeddings of subsidy text/queries
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

api/app.py

@@ -0,0 +1,54 @@
+from flask import Flask, request, jsonify, Blueprint
+import os
+from dotenv import load_dotenv
+from api.embed import get_embeddings
+# from huggingface_hub import login
+
+load_dotenv()
+
+app = Flask(__name__)
+
+hf_token = os.environ.get("HF_TOKEN", "")
+
+# login(hf_token)
+
+HASURA_SECRET_HEADER_VALUE = os.getenv("HASURA_SECRET_HEADER_VALUE", "secret")
+HASURA_EVENTS_HEADER = os.getenv("HASURA_EVENTS_HEADER", "x-hasura-event-secret")
+
+@app.route("/health", methods=["GET"])
+def health_check():
+    return jsonify({"status": "OK"}), 200
+
+# Create a blueprint for the routes that require middleware
+api_bp = Blueprint("api", __name__)
+
+# @api_bp.before_request
+# def verify_hasura_secret():
+#     secret = request.headers.get(HASURA_EVENTS_HEADER)
+#     if not secret or secret != HASURA_SECRET_HEADER_VALUE:
+#         return jsonify({"message": "Invalid secret"}), 401
+
+@api_bp.route("/get_embedding", methods=["post"])
+def get_embedding():
+    try:
+        data = request.get_json()
+        query = data.get("query")
+        if not query:
+            return jsonify({"message": "Query is required"}), 400
+        embeddings = get_embeddings(query)
+        return (
+            jsonify(
+                {
+                    "query": query,
+                    "embeddings": embeddings,
+                }
+            ),
+            200,
+        )
+    except Exception as e:
+        return jsonify({"message": f"Error: {str(e)}"}), 500
+
+app.register_blueprint(api_bp)
+
+if __name__ == "__main__":
+    app.run(debug=True)

api/embed.py

@@ -0,0 +1,45 @@
+import os
+from dotenv import load_dotenv
+import torch
+# from huggingface_hub import login
+from transformers import AutoTokenizer, AutoModel
+
+load_dotenv()
+
+huggingface_token = os.environ.get("HF_TOKEN", "")
+
+print(huggingface_token)
+
+# login(huggingface_token)
+
+auto_tokenizer = AutoTokenizer.from_pretrained(
+    "CocoonBusiness/VectorSearch", token=huggingface_token, low_cpu_mem_usage=True
+)
+model = AutoModel.from_pretrained(
+    "jegorkitskerkin/robbert-v2-dutch-base-mqa-finetuned", low_cpu_mem_usage=True
+)
+
+
+def get_embeddings(text_list):
+    encoded_input = auto_tokenizer(
+        text_list,
+        padding=True,
+        truncation=True,
+        max_length=500,
+        return_tensors="pt",
+        add_special_tokens=True,
+    )
+    model_output = model(**encoded_input)
+    embeddings = mean_pooling(model_output, encoded_input["attention_mask"])
+    # Make 1D vector
+    return embeddings.detach().numpy().flatten().tolist()
+
+
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]
+    input_mask_expanded = (
+        attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    )
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(
+        input_mask_expanded.sum(1), min=1e-9
+    )