Initial commit

.gitignore

+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

.python-version

+3.10

0-DataingestParsing/1-dataingestion.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c87bf196",
+   "metadata": {},
+   "source": [
+    "Introduction to Data Ingestion"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d2917c49",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from typing import List, Dict, Any\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5a55f7a9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\RagProject\\.venv\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.documents import Document\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter, CharacterTextSplitter, TokenTextSplitter\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cd5b00e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc = Document(\n",
+    "    page_content=\"This is the main text content that will be embedded and searched.\",\n",
+    "    metadata={\n",
+    "        \"source\": \"example.txt\",\n",
+    "        \"page\": 1,\n",
+    "        \"author\": \"Krish Naik\",\n",
+    "        \"date_created\": \"2024-01-01\",\n",
+    "        \"custom_field\": \"any_value\"\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d763dbf7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "langchain_core.documents.base.Document"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(doc)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "RagProject",
+   "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": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

main.py

+def main():
+    print("Hello from ragproject!")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

+[project]
+name = "ragproject"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "chromadb>=1.4.0",
+    "faiss-cpu>=1.13.2",
+    "ipykernel>=7.1.0",
+    "langchain>=1.2.0",
+    "langchain-community>=0.4.1",
+    "langchain-groq>=1.1.1",
+    "langchain-openai>=1.1.6",
+    "pandas>=2.3.3",
+    "pypdf>=6.5.0",
+    "python-dotenv>=1.2.1",
+    "sentence-transformers>=5.2.0",
+    "tiktoken>=0.12.0",
+]

requirements.txt

+langchain
+langchain-groq
+faiss-cpu
+tiktoken
+langchain-community
+langchain-openai
+chromadb
+sentence-transformers
+pypdf
+python-dotenv