different structure

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+__pycache__

Dockerfile

@@ -1,33 +1,23 @@
-# Use the official Python image from the Docker Hub
-FROM python:3.10-slim
+# Use the official Docker image with Docker and Docker Compose
+FROM docker:latest
 
-# Set environment variables
-ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH
+# Install Docker Compose
+RUN apk add --no-cache \
+    py3-pip \
+    && pip install docker-compose
 
-# Set up a new user named "user" with user ID 1000
-RUN useradd -m -u 1000 user
+# Set the working directory to /app
+WORKDIR /app
 
-# Switch to the "user" user
-USER user
+# Copy the docker-compose.yml file into the container at /app
+COPY docker-compose.yml .
 
-# Set the working directory to the user's home directory
-WORKDIR $HOME/app
+# Copy the frontend and backend directories into the container
+COPY frontend ./frontend
+COPY backend ./backend
 
-# Install pip
-RUN pip install --no-cache-dir --upgrade pip
+# Expose ports (adjust if necessary)
+EXPOSE 8501 8080
 
-# Copy only the requirements file and install dependencies
-COPY --chown=user requirements.txt .
-
-# Install the application dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the application code to the working directory
-COPY --chown=user . .
-
-# Expose the port FastAPI will run on
-EXPOSE 7860
-
-# Command to run the FastAPI application
-CMD ["python", "run.py"]
+# Run docker-compose up when the container starts
+CMD ["docker-compose", "up"]

README.md

@@ -1,12 +1,39 @@
----
-title: Prompt Engine
-emoji: 💻
-colorFrom: green
-colorTo: green
-sdk: docker
-pinned: false
-license: apache-2.0
-app_file: run.py
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+### Installation
+
+This project uses [poetry](https://python-poetry.org/) as dependency management tool.
+
+After setting up poetry, run the following command to install the project along with its dependencies:
+
+```bash
+poetry install
+```
+
+The project also uses of [poethepoet](https://poethepoet.natn.io/index.html) for defining project tasks, such as running local applications for development.
+
+These "_poe tasks_" are defined in the `pyproject.toml` file.
+
+### Code quality and typing checks
+
+This project enforces code quality and typing checks using [ruff](https://docs.astral.sh/ruff/), [mypy](https://mypy.readthedocs.io/en/stable/) and [black](https://black.readthedocs.io/en/stable/).
+
+To format the code, run the following command:
+
+```bash
+poetry run poe format
+```
+
+To run the checks locally, run the following command:
+
+```bash
+poetry run poe check
+```
+
+You can also use poe task to run the tests, namely:
+
+```bash
+poetry run poe test
+```
+
+docker build -t prompt-search-engine .
+
+docker run -d -p 8000:8000 prompt-search-engine

backend/Dockerfile

@@ -0,0 +1,23 @@
+# Use the official Python image from the Docker Hub
+FROM python:3.10-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install Poetry
+RUN pip install poetry
+
+# Copy only the pyproject.toml and poetry.lock files to install dependencies first
+COPY pyproject.toml poetry.lock ./
+
+# Install dependencies using Poetry
+RUN poetry config virtualenvs.create false && poetry install --only=main
+
+# Copy the rest of the application code to the working directory
+COPY . .
+
+# Expose the port FastAPI will run on
+EXPOSE 8000
+
+# Command to run the FastAPI application
+CMD ["poetry", "run", "uvicorn", "run:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

backend/poe/common-tasks.toml

@@ -0,0 +1,52 @@
+# This file defines common tasks that most python projects can benefit from
+
+[tool.poe.tasks.format-isort]
+help = "Format code with isort"
+cmd  = "isort ."
+
+[tool.poe.tasks.format-black]
+help = "Format code with black"
+cmd  = "black ."
+
+[tool.poe.tasks.format]
+help = "Run code formating tools"
+sequence  = ["format-isort", "format-black"]
+
+[tool.poe.tasks.style-black]
+help = "Validate black code style"
+cmd  = "black . --check --diff"
+
+[tool.poe.tasks.style-isort]
+help = "Validate isort code style"
+cmd  = "isort . --check --diff"
+
+[tool.poe.tasks.style]
+help = "Validate code style"
+sequence = ["style-isort", "style-black"]
+
+[tool.poe.tasks.types]
+help = "Run the type checker"
+cmd  = "mypy . --ignore-missing-imports --check-untyped-defs --install-types --non-interactive"
+
+[tool.poe.tasks.lint]
+help = "Evaluate ruff rules"
+cmd  = "ruff check ."
+
+[tool.poe.tasks.test]
+help = "Run unit tests"
+cmd  = "pytest -p no:cacheprovider"
+
+[tool.poe.tasks.clean]
+help = "Remove automatically generated files"
+cmd  = """
+  rm -rf dist
+         .mypy_cache
+         .pytest_cache
+         .ruff_cache
+         ./**/__pycache__/
+         ./**/*.pyc
+"""
+
+[tool.poe.tasks.check]
+help     = "Run all checks on the code base"
+sequence = ["style", "types", "lint", "clean"]

backend/pyproject.toml

@@ -0,0 +1,27 @@
+[tool.poetry]
+name = "smart-cat-assignment-backend"
+version = "0.0.1"
+description = "SmartCat Assignment"
+authors     = ["Lazar Radojevic <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+mypy = "^1.8.0"
+ruff = "^0.3.2"
+datasets = "^2.20.0"
+sentence-transformers = "^3.0.1"
+numpy = "1.26.4"
+fastapi = "^0.111.1"
+uvicorn = "^0.30.3"
+
+[tool.poetry.group.dev.dependencies]
+black = "^24.1.1"
+poethepoet = "^0.24.4"
+isort = "^5.13.2"
+
+[tool.isort]
+profile = "black"
+
+[tool.poe]
+include = "./poe/common-tasks.toml"

backend/run.py

@@ -0,0 +1,49 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import List
+from src.search_engine import PromptSearchEngine
+from src.prompt_loader import PromptLoader
+
+# Constants
+SEED = 42
+DATA_SIZE = 100
+
+# Initialize the prompt loader and search engine
+prompts = PromptLoader(seed=SEED).load_data(size=DATA_SIZE)
+engine = PromptSearchEngine(prompts)
+
+# Initialize FastAPI
+app = FastAPI()
+
+
+# Request and Response Models
+class QueryRequest(BaseModel):
+    query: str
+    n: int = 5
+
+
+class SimilarPrompt(BaseModel):
+    score: float
+    prompt: str
+
+
+class QueryResponse(BaseModel):
+    similar_prompts: List[SimilarPrompt]
+
+
+# API endpoint
+@app.post("/most_similar", response_model=QueryResponse)
+async def get_most_similar(query_request: QueryRequest):
+    try:
+        similar_prompts = engine.most_similar(
+            query=query_request.query, n=query_request.n
+        )
+        response = QueryResponse(
+            similar_prompts=[
+                SimilarPrompt(score=score, prompt=prompt)
+                for score, prompt in similar_prompts
+            ]
+        )
+        return response
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

docker-compose.yml

@@ -0,0 +1,16 @@
+version: "3"
+
+services:
+  frontend:
+    build: frontend
+    ports:
+      - 8501:8501
+    depends_on:
+      - backend
+    environment:
+      - API_URL=http://backend:8000/
+
+  backend:
+    build: backend
+    ports:
+      - 8000:8000

frontend/Dockerfile

@@ -0,0 +1,22 @@
+
+# Use the official Python image from the Docker Hub
+FROM python:3.10-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install Poetry
+RUN pip install poetry
+
+# Copy only the pyproject.toml and poetry.lock files to install dependencies first
+COPY pyproject.toml poetry.lock ./
+
+# Install dependencies using Poetry
+RUN poetry config virtualenvs.create false && poetry install --only=main
+
+# Copy the rest of the application code to the working directory
+COPY . .
+
+EXPOSE 8501
+
+CMD ["streamlit", "run", "run.py"]

frontend/poe/common-tasks.toml

@@ -0,0 +1,52 @@
+# This file defines common tasks that most python projects can benefit from
+
+[tool.poe.tasks.format-isort]
+help = "Format code with isort"
+cmd  = "isort ."
+
+[tool.poe.tasks.format-black]
+help = "Format code with black"
+cmd  = "black ."
+
+[tool.poe.tasks.format]
+help = "Run code formating tools"
+sequence  = ["format-isort", "format-black"]
+
+[tool.poe.tasks.style-black]
+help = "Validate black code style"
+cmd  = "black . --check --diff"
+
+[tool.poe.tasks.style-isort]
+help = "Validate isort code style"
+cmd  = "isort . --check --diff"
+
+[tool.poe.tasks.style]
+help = "Validate code style"
+sequence = ["style-isort", "style-black"]
+
+[tool.poe.tasks.types]
+help = "Run the type checker"
+cmd  = "mypy . --ignore-missing-imports --check-untyped-defs --install-types --non-interactive"
+
+[tool.poe.tasks.lint]
+help = "Evaluate ruff rules"
+cmd  = "ruff check ."
+
+[tool.poe.tasks.test]
+help = "Run unit tests"
+cmd  = "pytest -p no:cacheprovider"
+
+[tool.poe.tasks.clean]
+help = "Remove automatically generated files"
+cmd  = """
+  rm -rf dist
+         .mypy_cache
+         .pytest_cache
+         .ruff_cache
+         ./**/__pycache__/
+         ./**/*.pyc
+"""
+
+[tool.poe.tasks.check]
+help     = "Run all checks on the code base"
+sequence = ["style", "types", "lint", "clean"]

frontend/pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "smart-cat-assignment-frontend"
+version = "0.0.1"
+description = "SmartCat Assignment"
+authors     = ["Lazar Radojevic <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+mypy = "^1.8.0"
+ruff = "^0.3.2"
+streamlit = "^1.37.0"
+
+[tool.poetry.group.dev.dependencies]
+black = "^24.1.1"
+poethepoet = "^0.24.4"
+isort = "^5.13.2"
+
+[tool.isort]
+profile = "black"
+
+[tool.poe]
+include = "./poe/common-tasks.toml"

frontend/run.py

@@ -0,0 +1,37 @@
+import streamlit as st
+import requests
+from typing import List, Tuple
+import os
+
+API_URL = os.getenv("API_URL")
+
+
+def get_similar_prompts(query: str, n: int) -> List[Tuple[float, str]]:
+    try:
+        response = requests.post(f"{API_URL}/most_similar", json={"query": query, "n": n})
+        if response.status_code == 200:
+            return response.json().get("similar_prompts", [])
+        else:
+            st.error(f"Error: {response.status_code} - {response.text}")
+            return []
+    except requests.exceptions.RequestException as e:
+        st.error(f"Request error: {e}")
+        return []
+
+
+st.title("Prompt Search Engine")
+
+query = st.text_input("Enter a prompt:")
+n = st.slider("Number of similar prompts to retrieve:", 1, 20, 5)
+
+if st.button("Search"):
+    if query:
+        response = get_similar_prompts(query, n)
+        if response:
+            st.write(f"Top {n} similar prompts:")
+            for query_response in response:
+                st.write(
+                    f"**Score:** {query_response['score']:.4f} | **Prompt:** {query_response['prompt']}"
+                )
+    else:
+        st.warning("Please enter a prompt to search.")

main.py

@@ -1,27 +0,0 @@
-from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
-
-app = FastAPI(title="Deploying FastAPI Apps on Huggingface")
-
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-@app.get("/", tags=["Home"])
-def api_home():
-    return {"detail": "Welcome to FastAPI TextGen Tutorial!"}
-
-
-@app.post(
-    "/api/generate",
-    summary="Generate text from prompt",
-    tags=["Generate"],
-)
-def inference(input_prompt: str):
-    return "Hello"

requirements.txt

@@ -1,8 +0,0 @@
-mypy==1.8.0
-ruff==0.3.2
-datasets==2.20.0
-sentence-transformers==3.0.1
-numpy==1.26.4
-fastapi==0.111.1
-uvicorn==0.30.3
-streamlit==1.37.0

run.py

@@ -1,4 +0,0 @@
-import uvicorn
-
-if __name__ == "__main__":
-    uvicorn.run("main:app", host="0.0.0.0", port=7860, reload=True)