files for docker

.gitignore

@@ -0,0 +1,128 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+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/

Dockerfile

@@ -0,0 +1,30 @@
+# Choose our version of Python
+FROM python:3.9-slim
+
+# Set up a working directory
+WORKDIR /code
+
+
+# Copy just the requirements into the working directory so it gets cached by itself
+COPY ./requirements.txt /code/requirements.txt
+
+# Install the dependencies from the requirements file
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# RUN pip install pydantic==1.10.8
+# RUN pip install typing-inspect==0.8.0 typing_extensions==4.5.
+# RUN pip install --force-reinstall typing-extensions==4.5
+# RUN pip install --force-reinstall openai==1.8
+
+# Copy the code into the working directory
+COPY ./app /code/app
+
+ENV PORT=8000
+EXPOSE 8000
+
+# execute the command python main.py (in the WORKDIR) to start the app
+CMD ["python", "app/main.py"]
+
+# Tell uvicorn to start spin up our code, which will be running inside the container now
+# CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "80"]
+# uvicorn app.main:app --host 0.0.0.0 --port 80

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Rowan Lea
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

app/.env

@@ -0,0 +1,3 @@
+MONGODB_ATLAS_CLUSTER_URI="mongodb+srv://devixgamer:JvUeeCdFvUgyn8sn@quran.z83sfpu.mongodb.net/?retryWrites=true&w=majority&appName=quran"
+API_TOKEN="aQgdqCHYmga7sxDPqT8YCrtNmAZYZp5T4Adv4xEj2C2nDyNEjacKET9vzcUjkRS9"
+PORT=8000

app/main.py

@@ -0,0 +1,76 @@
+from fastapi import FastAPI, HTTPException, Header, Depends
+from pydantic import BaseModel
+import os
+from pymongo import MongoClient
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain_community.vectorstores import MongoDBAtlasVectorSearch
+import uvicorn
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# MongoDB connection and Langchain setup (as provided)
+MONGODB_ATLAS_CLUSTER_URI = os.getenv("MONGODB_ATLAS_CLUSTER_URI", None)
+client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)
+DB_NAME = "quran_db"
+COLLECTION_NAME = "tafsir"
+ATLAS_VECTOR_SEARCH_INDEX_NAME = "langchain_index"
+MONGODB_COLLECTION = client[DB_NAME][COLLECTION_NAME]
+
+
+embeddings = SentenceTransformerEmbeddings(model_name="BAAI/bge-m3")
+
+vector_search = MongoDBAtlasVectorSearch.from_connection_string(
+    MONGODB_ATLAS_CLUSTER_URI,
+    DB_NAME + "." + COLLECTION_NAME,
+    embeddings,
+    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
+)
+
+
+# FastAPI application setup
+app = FastAPI()
+
+# Existing API endpoints
+@app.get("/")
+async def read_root():
+    return {"message": "Welcome to our app"}
+
+# New Query model for the POST request body
+class Item(BaseModel):
+    question: str
+
+EXPECTED_TOKEN = os.getenv("API_TOKEN")
+
+def verify_token(authorization: str = Header(None)):
+    """
+    Dependency to verify the Authorization header contains the correct Bearer token.
+    """
+    # Prefix for bearer token in the Authorization header
+    prefix = "Bearer "
+    
+    # Check if the Authorization header is present and correctly formatted
+    if not authorization or not authorization.startswith(prefix):
+        raise HTTPException(status_code=401, detail="Unauthorized: Missing or invalid token")
+
+    # Extract the token from the Authorization header
+    token = authorization[len(prefix):]
+
+    # Compare the extracted token to the expected token value
+    if token != EXPECTED_TOKEN:
+        raise HTTPException(status_code=401, detail="Unauthorized: Incorrect token")
+
+# New API endpoint to get an answer using the chain
+@app.post("/get_answer")
+async def get_answer(item: Item, token: str = Depends(verify_token)):
+    try:
+        # Perform the similarity search with the provided question
+        matching_docs = vector_search.similarity_search(item.question, k=3)
+
+        return {"answers": [doc.page_content for doc in matching_docs]}
+    except Exception as e:
+        # If there's an error, return a 500 error with the error's details
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    uvicorn.run("main:app", host="0.0.0.0", port=8080, reload=False)

requirements.txt

@@ -0,0 +1,13 @@
+fastapi>=0.68.0,<0.69.0
+pydantic>=1.8.0,<2.0.0
+uvicorn>=0.15.0,<0.16.0
+openai==1.13.3
+langchain==0.1.9
+sentence-transformers==2.5.1
+unstructured==0.12.5
+pypdf==4.0.2
+pymongo>=3.11
+tiktoken==0.6.0
+langchain-openai==0.0.8
+python-dotenv
+upstash-redis