Upload 75 files

.dockerignore

@@ -0,0 +1,9 @@
+.git
+*.log
+*.pyc
+__pycache__/
+template.py
+rsys/
+logs/
+artifact/
+try.py

.gitattributes

@@ -0,0 +1,4 @@
+chromadb_anime_data_7490_e5largev2_1.5K_batch filter=lfs diff=lfs merge=lfs -text
+chromadb/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+chromadb/d51dabe8-c547-49cd-8dde-bc9590ea4b56/data_level0.bin filter=lfs diff=lfs merge=lfs -text
+chromadb/d51dabe8-c547-49cd-8dde-bc9590ea4b56/index_metadata.pickle filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,181 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# project files
+template.py
+rsys/
+logs/
+artifact/
+try.py

Dockerfile

@@ -0,0 +1,26 @@
+# Use official Python image
+FROM python:3.13-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy all files to the containedocker rmi recommendation-system
+COPY . .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt -c constraints.txt
+
+# Optional: install as a local package (important!)
+RUN pip install -e .
+
+# Expose Streamlit default port
+EXPOSE 8501
+
+# Run your app in both FastAPI and Streamlit
+#CMD ["python", "run_both.py", "run"]
+
+
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+
+

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Satkar Sarvankar
+
+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.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import pandas as pd
+import pickle
+
+#------------------------------------RAG BASED CHATBOT ---------------------------------------
+
+import sys
+import os
+sys.path.append(os.path.abspath("src"))
+
+from recommendationSystem.chatbot.client_module.utils import chatbot
+
+chatbot()
+#render_history_download()
+
+#----------------------------------- RECOMMEDATION SYSTEM -----------------------------------------
+
+from utils import fetch_transformed_data, anime_info
+ 
+st.title("Anime Recommender System")
+
+data_path, matrix_path = fetch_transformed_data()
+
+anime_data = pd.read_csv(data_path)
+similarity_matrix = pickle.load(open(file=matrix_path,mode='rb'))
+
+select_anime_name = st.selectbox(
+    "Choose Anime Name : ",
+    anime_data['title'].values,
+    index=None,
+    placeholder="Select the anime for recommendation..."
+)
+
+anime_info(anime_name=select_anime_name,anime_data=anime_data,similarity_matrix=similarity_matrix)

chromadb/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d162cc7bc68f7c91bbf4dfe6512879f4e271945a716693ba632605e683a77d
+size 98844672

chromadb/d51dabe8-c547-49cd-8dde-bc9590ea4b56/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2715e5c7896dcfb5a4f87f33d40a203783d63405f7be69010fdf6acf706cffa1
+size 42360000

chromadb/d51dabe8-c547-49cd-8dde-bc9590ea4b56/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9f0724d8d13813a585a4381c5ff5e1068a9759b89f9a92ac5873b9d415551d
+size 372160

constraints.txt

@@ -0,0 +1,6 @@
+# Not required but getting installed due to langchain & Huggingface
+tensorflow==0.0.0
+tensorflow-intel==0.0.0
+keras==0.0.0
+ml-dtypes==0.0.0
+tensorboard==0.0.0

predict_trial.py

@@ -0,0 +1,21 @@
+import sys
+#import pandas as pd
+#import pickle
+import os
+
+from recommendationSystem.components.data_ingestion import DataIngestion
+from recommendationSystem.components.data_transformation import DataTransformation
+from recommendationSystem.utils.common import CustomException
+
+class return_data:
+    def __init__(self):
+        pass
+
+    def predict(self):
+        try:
+            obj = DataIngestion().initiate_data_ingestion()
+            matrix_path, data_path = DataTransformation().initiate_data_transformation_obj(obj)
+            return matrix_path,data_path
+
+        except Exception as e:
+            raise CustomException(e,sys)

requirements.txt

@@ -0,0 +1,44 @@
+numpy
+pandas
+matplotlib
+seaborn
+scikit-learn
+nltk
+streamlit
+ipykernel
+docker
+dill
+
+# chatbot requirements
+
+# Web Framework
+fastapi
+uvicorn[standard]
+
+# LangChain & Ecosystem
+langchain
+langchain-community
+langchain-core
+langchain-groq
+langchain-huggingface
+
+# Vectorstore
+chromadb
+
+protobuf==3.20.3
+
+# Embeddings
+sentence-transformers
+
+# Environment Variables
+python-dotenv
+
+# Typing & Utilities
+pydantic
+requests
+
+# Logging (optional but recommended)
+#loguru
+python-multipart
+
+#-e.

research/trials.ipynb

@@ -0,0 +1,616 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "253d3df7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "66bcd730",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'C:\\\\Users\\\\satka\\\\OneDrive\\\\Desktop\\\\recommendation-system\\\\data'"
+      ]
+     },
+     "execution_count": 74,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%pwd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b4ed7319",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.chdir(\"C:/Users/satka/OneDrive/Desktop/recommendation-system/data\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0c897fa0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"anime_data_24.csv\")\n",
+    "df_links = pd.read_csv('anime_links.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ec96f943",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime = df.merge(df_links,on='name')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6500fbb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime = anime[['name','sypnopsis','image','type','episodes','status','studios','source','genres','demographic','links']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "c28abf0f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Two years after the Summit War in which Straw Hat pirate Luffy lost his brother Ace, the story takes place on the Sabaody Archipelago. The protagonist, a young girl who has a strong admiration for Nami, sets off on a small adventure. This is an ensemble drama that focuses on people who do not \"pursue\" ONE PIECE, depicting the reunion of the Straw Hat Pirates from their perspective.\\n\\n(Source: Official site, translated)'"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'\\n'.join(anime[anime.name ==\"One Piece Fan Letter\"].sypnopsis.to_list())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "e0f37141",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#anime = anime.iloc[0:8000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "196a74c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['name', 'sypnopsis', 'image', 'type', 'episodes', 'status', 'studios',\n",
+       "       'source', 'genres', 'demographic', 'links'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 80,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "anime.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "id": "c895f232",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 13501 entries, 0 to 13500\n",
+      "Data columns (total 11 columns):\n",
+      " #   Column       Non-Null Count  Dtype \n",
+      "---  ------       --------------  ----- \n",
+      " 0   name         13501 non-null  object\n",
+      " 1   sypnopsis    13499 non-null  object\n",
+      " 2   image        13492 non-null  object\n",
+      " 3   type         13501 non-null  object\n",
+      " 4   episodes     13501 non-null  object\n",
+      " 5   status       13501 non-null  object\n",
+      " 6   studios      13501 non-null  object\n",
+      " 7   source       13501 non-null  object\n",
+      " 8   genres       11823 non-null  object\n",
+      " 9   demographic  13466 non-null  object\n",
+      " 10  links        13501 non-null  object\n",
+      "dtypes: object(11)\n",
+      "memory usage: 1.1+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "anime.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "id": "dc7662fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime.dropna(inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "edc035da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime['sypnopsis_length'] = [len(i) for i in anime.sypnopsis]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "id": "99183feb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime = anime[anime['sypnopsis_length'] > 300]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "id": "a932d424",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime['tags'] = anime['sypnopsis']+\" \" + anime['type']+\" \" + anime['episodes']+\" \" + anime['status'] +\" \"+ anime['studios'] +\" \"+ anime['source']+\" \" + anime['genres']+\" \" + anime['demographic']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "id": "f76e7a39",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime_1 = anime.copy()\n",
+    "anime_1 = anime_1[['image','name','tags','links']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "id": "8ab84681",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime_1 = anime_1.reset_index(drop=True)\n",
+    "anime_1 = anime_1.rename({'name':'title'},axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "521b43bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "\n",
+    "cv = CountVectorizer(max_features=5000,stop_words='english')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 120,
+   "id": "bb0e6617",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from nltk.stem.porter import PorterStemmer\n",
+    "ps = PorterStemmer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92d8d53e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics.pairwise import cosine_similarity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 126,
+   "id": "8c101543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def removing_blank_lines(text):\n",
+    "    return text.replace('\\n',\" \")\n",
+    "\n",
+    "def removing_pre_suff_ix(text):\n",
+    "    y = []\n",
+    "    \n",
+    "    for i in text.split():\n",
+    "        y.append(ps.stem(i))\n",
+    "    \n",
+    "    return \" \".join(y)\n",
+    "\n",
+    "def converting_into_vectors(text):\n",
+    "    vec = cv.fit_transform(text).toarray()\n",
+    "    return vec\n",
+    "\n",
+    "def finding_similarity(vec):\n",
+    "    similarity = cosine_similarity(vec)\n",
+    "    return similarity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "id": "01e8e16b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "anime_1.tags = anime_1.tags.apply(removing_blank_lines)\n",
+    "anime_1.tags = anime_1.tags.apply(removing_blank_lines)\n",
+    "vectors = converting_into_vectors(anime_1.tags)\n",
+    "similarity = finding_similarity(vectors)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "id": "c7b531b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>image</th>\n",
+       "      <th>title</th>\n",
+       "      <th>tags</th>\n",
+       "      <th>links</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/12/89...</td>\n",
+       "      <td>Gintama.: Shirogane no Tamashii-hen</td>\n",
+       "      <td>after the fierc battl on rakuyou, the untold p...</td>\n",
+       "      <td>https://myanimelist.net/anime/36838/Gintama__S...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>31</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1170/...</td>\n",
+       "      <td>Vinland Saga Season 2</td>\n",
+       "      <td>after hi father' death and the destruct of hi ...</td>\n",
+       "      <td>https://myanimelist.net/anime/49387/Vinland_Sa...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1741/...</td>\n",
+       "      <td>Monogatari Series: Off &amp; Monster Season</td>\n",
+       "      <td>koyomi araragi spent hi last year of high scho...</td>\n",
+       "      <td>https://myanimelist.net/anime/57864/Monogatari...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1792/...</td>\n",
+       "      <td>Jujutsu Kaisen 2nd Season</td>\n",
+       "      <td>the year is 2006, and the hall of tokyo prefec...</td>\n",
+       "      <td>https://myanimelist.net/anime/51009/Jujutsu_Ka...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1918/...</td>\n",
+       "      <td>Mob Psycho 100 II</td>\n",
+       "      <td>shigeo \"mob\" kageyama is now matur and underst...</td>\n",
+       "      <td>https://myanimelist.net/anime/37510/Mob_Psycho...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1643/...</td>\n",
+       "      <td>Boku no Kokoro no Yabai Yatsu 2nd Season</td>\n",
+       "      <td>after an event winter break, kyoutar ichikawa ...</td>\n",
+       "      <td>https://myanimelist.net/anime/55690/Boku_no_Ko...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>36</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1000/...</td>\n",
+       "      <td>Shingeki no Kyojin: The Final Season</td>\n",
+       "      <td>gabi braun and falco grice have been train the...</td>\n",
+       "      <td>https://myanimelist.net/anime/40028/Shingeki_n...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1084/...</td>\n",
+       "      <td>Kizumonogatari III: Reiketsu-hen</td>\n",
+       "      <td>after help reviv the legendari vampir kiss-sho...</td>\n",
+       "      <td>https://myanimelist.net/anime/31758/Kizumonoga...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/1448/...</td>\n",
+       "      <td>Bocchi the Rock!</td>\n",
+       "      <td>yearn to make friend and perform live with a b...</td>\n",
+       "      <td>https://myanimelist.net/anime/47917/Bocchi_the...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39</th>\n",
+       "      <td>https://cdn.myanimelist.net/images/anime/7/819...</td>\n",
+       "      <td>Haikyuu!! Karasuno Koukou vs. Shiratorizawa Ga...</td>\n",
+       "      <td>after the victori against aoba jousai high, ka...</td>\n",
+       "      <td>https://myanimelist.net/anime/32935/Haikyuu_Ka...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                image  \\\n",
+       "30  https://cdn.myanimelist.net/images/anime/12/89...   \n",
+       "31  https://cdn.myanimelist.net/images/anime/1170/...   \n",
+       "32  https://cdn.myanimelist.net/images/anime/1741/...   \n",
+       "33  https://cdn.myanimelist.net/images/anime/1792/...   \n",
+       "34  https://cdn.myanimelist.net/images/anime/1918/...   \n",
+       "35  https://cdn.myanimelist.net/images/anime/1643/...   \n",
+       "36  https://cdn.myanimelist.net/images/anime/1000/...   \n",
+       "37  https://cdn.myanimelist.net/images/anime/1084/...   \n",
+       "38  https://cdn.myanimelist.net/images/anime/1448/...   \n",
+       "39  https://cdn.myanimelist.net/images/anime/7/819...   \n",
+       "\n",
+       "                                                title  \\\n",
+       "30                Gintama.: Shirogane no Tamashii-hen   \n",
+       "31                              Vinland Saga Season 2   \n",
+       "32            Monogatari Series: Off & Monster Season   \n",
+       "33                          Jujutsu Kaisen 2nd Season   \n",
+       "34                                  Mob Psycho 100 II   \n",
+       "35           Boku no Kokoro no Yabai Yatsu 2nd Season   \n",
+       "36               Shingeki no Kyojin: The Final Season   \n",
+       "37                   Kizumonogatari III: Reiketsu-hen   \n",
+       "38                                   Bocchi the Rock!   \n",
+       "39  Haikyuu!! Karasuno Koukou vs. Shiratorizawa Ga...   \n",
+       "\n",
+       "                                                 tags  \\\n",
+       "30  after the fierc battl on rakuyou, the untold p...   \n",
+       "31  after hi father' death and the destruct of hi ...   \n",
+       "32  koyomi araragi spent hi last year of high scho...   \n",
+       "33  the year is 2006, and the hall of tokyo prefec...   \n",
+       "34  shigeo \"mob\" kageyama is now matur and underst...   \n",
+       "35  after an event winter break, kyoutar ichikawa ...   \n",
+       "36  gabi braun and falco grice have been train the...   \n",
+       "37  after help reviv the legendari vampir kiss-sho...   \n",
+       "38  yearn to make friend and perform live with a b...   \n",
+       "39  after the victori against aoba jousai high, ka...   \n",
+       "\n",
+       "                                                links  \n",
+       "30  https://myanimelist.net/anime/36838/Gintama__S...  \n",
+       "31  https://myanimelist.net/anime/49387/Vinland_Sa...  \n",
+       "32  https://myanimelist.net/anime/57864/Monogatari...  \n",
+       "33  https://myanimelist.net/anime/51009/Jujutsu_Ka...  \n",
+       "34  https://myanimelist.net/anime/37510/Mob_Psycho...  \n",
+       "35  https://myanimelist.net/anime/55690/Boku_no_Ko...  \n",
+       "36  https://myanimelist.net/anime/40028/Shingeki_n...  \n",
+       "37  https://myanimelist.net/anime/31758/Kizumonoga...  \n",
+       "38  https://myanimelist.net/anime/47917/Bocchi_the...  \n",
+       "39  https://myanimelist.net/anime/32935/Haikyuu_Ka...  "
+      ]
+     },
+     "execution_count": 131,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "anime_1[30:40]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "163acbb5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#from sklearn.metrics.pairwise import cosine_similarity\n",
+    "#similarity = cosine_similarity(vectors)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 141,
+   "id": "404a1f15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def recommend(anime):\n",
+    "    anime_index = anime_1[anime_1['title']== anime].index[0]\n",
+    "    distances = np.around(similarity[anime_index],2)\n",
+    "    anime_list = sorted(list(enumerate(distances)),reverse=True,key=lambda x:x[1])[1:8]\n",
+    "\n",
+    "    for i in anime_list:\n",
+    "        #print(' index no. ', '|', ' title ', '|', ' similarity score ')\n",
+    "        print(i[0], '|', anime_1.iloc[i[0]].title, '|', i[1])\n",
+    "        print(anime_1.iloc[i[0]].links, '\\n')\n",
+    "        \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 142,
+   "id": "bfa64fd5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3720 | Radiant | 0.28\n",
+      "https://myanimelist.net/anime/37202/Radiant \n",
+      "\n",
+      "6790 | Dokyuu Hentai HxEros | 0.28\n",
+      "https://myanimelist.net/anime/40623/Dokyuu_Hentai_HxEros \n",
+      "\n",
+      "100 | Jujutsu Kaisen | 0.27\n",
+      "https://myanimelist.net/anime/40748/Jujutsu_Kaisen \n",
+      "\n",
+      "169 | Jujutsu Kaisen 0 Movie | 0.25\n",
+      "https://myanimelist.net/anime/48561/Jujutsu_Kaisen_0_Movie \n",
+      "\n",
+      "666 | Dead Dead Demons Dededede Destruction (OVA) | 0.25\n",
+      "https://myanimelist.net/anime/58883/Dead_Dead_Demons_Dededede_Destruction_OVA \n",
+      "\n",
+      "1651 | Dead Dead Demons Dededede Destruction | 0.25\n",
+      "https://myanimelist.net/anime/51358/Dead_Dead_Demons_Dededede_Destruction \n",
+      "\n",
+      "2390 | True Tears | 0.25\n",
+      "https://myanimelist.net/anime/2129/True_Tears \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommend('Jujutsu Kaisen 2nd Season')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "id": "791c8dca",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[(720, np.float64(0.4583333333333335)),\n",
+       " (123, np.float64(0.37709985557577297)),\n",
+       " (42, np.float64(0.32076651393589245)),\n",
+       " (26, np.float64(0.3051285766293647)),\n",
+       " (110, np.float64(0.29120520167670094))]"
+      ]
+     },
+     "execution_count": 100,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sorted(list(enumerate(similarity[anime_1[anime_1['title']== 'Shingeki no Kyojin Season 3 Part 2'].index[0]])),reverse=True,key=lambda x:x[1])[1:6]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "id": "1564ee97",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "image    https://cdn.myanimelist.net/images/anime/1710/...\n",
+       "title    Shingeki no Kyojin Season 2 Movie: Kakusei no ...\n",
+       "tags     eren yeager and other of the 104th train corp ...\n",
+       "links    https://myanimelist.net/anime/36702/Shingeki_n...\n",
+       "Name: 720, dtype: object"
+      ]
+     },
+     "execution_count": 101,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "anime_1.iloc[720]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "438daaf5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

setup.py

@@ -0,0 +1,48 @@
+# Importing Libraries
+from setuptools import find_packages, setup
+#from typing import List
+
+
+# Decription of the local package 
+with open("README.md","r",encoding="utf-8") as f:
+    long_description = f.read()
+
+# Define metadata variables
+__version__ = '0.0.1'
+src_name = 'recommendation-system'
+author_name = 'Satkar'
+author_user_name = 'Zenith40'
+src_repo = 'recommendationSystem'      # name of folder inside  the src
+author_email = '[email protected]'
+
+# Function to read requirements.txt file
+'''HYPEN_E_DOT = '-e.'
+def get_requirements(file_path:str) -> List[str]:
+    requirements = []
+
+    with open(file_path) as file_obj:
+        requirements = file_obj.readlines()
+        requirements = [req.replace("\n","") for req in requirements]
+
+        if HYPEN_E_DOT in requirements:
+            requirements.remove(HYPEN_E_DOT)
+'''
+
+
+# Package Information
+setup(
+    name = src_repo,
+    version = __version__,
+    author = author_name,
+    author_email = '[email protected]',
+    description = 'Recommendation system + RAG Chatbot',
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    url = f"https://github.com/{author_user_name}/{src_name}",
+    project_urls={
+        "Bug Tracker" : f"https://github.com/{author_user_name}/{src_name}/issues"
+    },
+    package_dir={'':'src'},
+    packages = find_packages(where='src'),
+    #install_requires = get_requirements('requirements.txt')
+)

src/recommendationSystem.egg-info/PKG-INFO

@@ -0,0 +1,98 @@
+Metadata-Version: 2.1
+Name: recommendationSystem
+Version: 0.0.1
+Summary: Recommendation system + RAG Chatbot
+Home-page: https://github.com/Zenith40/recommendation-system
+Author: Satkar
+Author-email: [email protected]
+Project-URL: Bug Tracker, https://github.com/Zenith40/recommendation-system/issues
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# 🎌 Anime Recommendation System
+
+This project is an anime recommendation engine that suggests similar anime based on the storyline using **cosine similarity**. It processes and analyzes a dataset of over **7,000+ anime** titles collected through web scraping, and applies **natural language processing (NLP)** techniques to generate meaningful recommendations.
+
+The application is containerized using **Docker** for consistent deployment across environments.
+
+---
+
+## 🚀 Features
+
+- Recommends animes based on **storyline similarity**
+- Built using **CountVectorizer + Porter Stemmer + Cosine Similarity**
+- Cleaned and preprocessed data pipeline from raw scraped sources
+- Fast, scalable recommendation system
+- Dockerized for smooth deployment
+
+---
+
+## 🛠 Tech Stack
+
+- **Python 3.9+**
+- **scikit-learn** for CountVectorizer & Cosine Similarity
+- **NLTK** for text preprocessing (PorterStemmer)
+- **Flask/FastAPI** (in `app.py`)
+- **Docker** for containerization
+- **BeautifulSoup / Scrapy** (for scraping, if applicable)
+
+---
+
+## 📊 Methodology
+
+1. **Data Collection**  
+   - Scraped storyline and metadata for 12,000+ animes.
+   - Structured data in a tabular format and removed duplicates, nulls, and irrelevant entries.
+
+2. **Text Preprocessing**  
+   - Converted to lowercase
+   - Removed special characters and stop words
+   - Applied **Porter Stemming** to normalize tokens
+
+3. **Feature Extraction**  
+   - Used **CountVectorizer** to convert text into token count vectors
+   - Removed high-dimensional noise with feature filtering
+
+4. **Similarity Calculation**  
+   - Used **Cosine Similarity** to compute similarity scores between anime storylines
+
+5. **Recommendation**  
+   - Returned the top N animes with the highest similarity to a selected title
+
+---
+
+## 📦 Docker Deployment
+
+* To run the app using Docker: https://hub.docker.com/r/zenith40/recommendation-system
+
+### Pull the Image
+* docker pull zenith40/recommendation-system:Ver-0.0.1
+
+### Run the container
+* docker run -p 8501:8501 zenith40/recommendation-system:Ver-0.0.1
+* Then, open your browser and navigate to http://localhost:8501
+
+---
+
+## 🌱 Future Improvements
+🔍 Integrate TF-IDF or Word2Vec/Doc2Vec for deeper context awareness
+
+🧠 Experiment with transformer-based models (e.g., BERT embeddings)
+
+🌐 Deploy with a front-end UI for better user interaction
+
+⚡ Implement caching for faster response times on repeated queries
+
+📱 Build a mobile app version with React Native or Flutter
+
+📊 Add filters based on genre, year, popularity, or user ratings
+
+👥 Integrate with collaborative filtering or hybrid recommendation systems
+
+📄 License
+This project is licensed under the MIT License
+
+🙌 Acknowledgements
+* NLTK
+
+* scikit-learn

src/recommendationSystem.egg-info/SOURCES.txt

@@ -0,0 +1,23 @@
+LICENSE
+README.md
+setup.py
+src/recommendationSystem/__init__.py
+src/recommendationSystem.egg-info/PKG-INFO
+src/recommendationSystem.egg-info/SOURCES.txt
+src/recommendationSystem.egg-info/dependency_links.txt
+src/recommendationSystem.egg-info/top_level.txt
+src/recommendationSystem/chatbot/__init__.py
+src/recommendationSystem/chatbot/client_module/__init__.py
+src/recommendationSystem/chatbot/client_module/utils.py
+src/recommendationSystem/chatbot/server_modules/__init__.py
+src/recommendationSystem/chatbot/server_modules/llm.py
+src/recommendationSystem/chatbot/server_modules/load_vector_store.py
+src/recommendationSystem/chatbot/server_modules/query_handler.py
+src/recommendationSystem/components/__init__.py
+src/recommendationSystem/components/data_ingestion.py
+src/recommendationSystem/components/data_transformation.py
+src/recommendationSystem/config/__init__.py
+src/recommendationSystem/config/configuration.py
+src/recommendationSystem/logging/__init__.py
+src/recommendationSystem/utils/__init__.py
+src/recommendationSystem/utils/common.py

src/recommendationSystem.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

src/recommendationSystem.egg-info/top_level.txt

@@ -0,0 +1 @@
+recommendationSystem

src/recommendationSystem/chatbot/client_module/utils.py

@@ -0,0 +1,56 @@
+# --------------------------------------- CHATBOT------------------------------------------------
+
+import streamlit as st
+
+def cache_clear(x):
+    if st.sidebar.button("Reset Chat History",use_container_width=True):
+        x.clear()
+
+#from recommendationSystem.chatbot.client_module.api import ask_question
+from recommendationSystem.chatbot.server_modules.llm import get_llm_chain
+from recommendationSystem.chatbot.server_modules.load_vector_store import use_vectorstore
+from recommendationSystem.chatbot.server_modules.query_handler import query_chain
+
+
+def chatbot():
+    vectorstore = use_vectorstore()
+    chain = get_llm_chain(vectorstore)
+    url = "https://raw.githubusercontent.com/Zenith40/Recommendation-system/refs/heads/main/data/anime_data_7490.txt"
+
+    if "messages" not in st.session_state:
+            st.session_state.messages = []
+            
+    with st.sidebar:
+        
+        st.title("🍥 RARE AT YOUR SERVICE ")
+        st.write("RAG-based Anime Recommendation Engine")
+
+        # Input and response
+        user_input = st.chat_input(placeholder="Ask Anything")
+        cache_clear(st.session_state.messages)
+        
+        if user_input:
+            #response = ask_question(user_input)
+            #if response.status_code == 200:
+            response=query_chain(chain,user_input=user_input)
+            #data = response.json()
+            answer = response["response"]
+            #sources = response.get("sources",[])
+            #st.chat_message("assistant").markdown(answer)
+            st.session_state.messages.insert(0,{"role": "assistant", "content": answer})
+            st.session_state.messages.insert(0,{"role": "user", "content": user_input})
+            st.markdown(f"📄 Source : [Anime_Data.txt](%s)" %url)
+            #else:
+                #st.error(f"Error: {response.text}")
+
+            # Render existing chat history
+            for msg in st.session_state.messages:
+                st.chat_message(msg["role"]).markdown(msg["content"])
+         
+
+# History Downloader
+
+def render_history_download():
+    if st.session_state.get("message"):
+        chat_text="\n\n".join([f"{m['role'].upper()}: {m['content']}" for m in st.session_state.messages])
+        st.download_button("Download Chat History",chat_text,file_name="chat_history.txt",mime="text/plain")

src/recommendationSystem/chatbot/server_modules/llm.py

@@ -0,0 +1,30 @@
+import os
+from dotenv import load_dotenv
+from langchain_groq import ChatGroq
+from langchain.chains import RetrievalQA
+
+load_dotenv()
+
+api_key = os.getenv("GROQ_API_KEY")
+
+
+def get_llm_chain(vectorstore):
+    llm=ChatGroq(
+        groq_api_key=api_key,
+        model_name="llama3-70b-8192"
+    )
+
+    retriever=vectorstore.as_retriever(
+        search_kwargs={
+            "k":8,
+            #"lambda_mult": 0.5
+        }
+    )
+
+
+    return RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=retriever,
+        return_source_documents=True
+    )

src/recommendationSystem/chatbot/server_modules/load_vector_store.py

@@ -0,0 +1,19 @@
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+import os
+
+save_path = os.path.join("chromadb")
+
+def use_vectorstore():
+  
+  embeddings = HuggingFaceEmbeddings(
+    model_name="intfloat/e5-large-v2",
+    #encode_kwargs={'batch_size': 32, 'normalize_embeddings': True}
+  )
+
+  vectorstore = Chroma(
+      persist_directory=save_path,
+      embedding_function=embeddings
+  )
+
+  return vectorstore

src/recommendationSystem/chatbot/server_modules/query_handler.py

@@ -0,0 +1,9 @@
+# Query Chain
+
+def query_chain(chain,user_input:str):
+  result = chain({"query": user_input})
+  response = {
+      "response":result["result"],
+      #"sources":[doc.metadata.get('source','') for doc in result["source_documents"]]
+      }
+  return response