Spaces:
Sleeping
Sleeping
File size: 5,773 Bytes
d8cba91 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# PDF QA RAG App"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Importing necessary libraries "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.document_loaders import PyPDFLoader\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"\n",
"from langchain.prompts import PromptTemplate \n",
"from langchain_core.output_parsers import StrOutputParser \n",
"from operator import itemgetter\n",
"\n",
"from pinecone import Pinecone, ServerlessSpec"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Defining helper functions"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def load_split_file(file_path):\n",
" loader = PyPDFLoader(file_path)\n",
" pages = loader.load_and_split()\n",
"\n",
" \n",
" text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=10)\n",
" docs = text_splitter.split_documents(pages)\n",
"\n",
" return docs\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def create_index(index_name, PINECONE_API_KEY):\n",
" \n",
" pc = Pinecone(api_key=PINECONE_API_KEY)\n",
"\n",
" if index_name in pc.list_indexes().names():\n",
" pc.delete_index(index_name) # To avoid any conflicts in retrieval\n",
" pc.create_index(\n",
" name=index_name, \n",
" dimension=384, \n",
" metric='cosine',\n",
" spec=ServerlessSpec(\n",
" cloud=\"aws\",\n",
" region=\"us-east-1\"\n",
" )\n",
" )\n",
"\n",
" return index_name\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def final_response(index, question, model):\n",
" retriever = index.as_retriever()\n",
"\n",
" parser = StrOutputParser()\n",
"\n",
" chain = model | parser \n",
"\n",
" template = \"\"\"\n",
" You must provide an answer based strictly on the context below. The answer is highly likely to be found within the given context, so analyze it thoroughly before responding. Only if there is absolutely no relevant information, respond with \"I don't know\".\n",
"\n",
" Context: {context}\n",
"\n",
" Question: {question}\n",
" \"\"\"\n",
"\n",
"\n",
" prompt = PromptTemplate.from_template(template)\n",
" prompt.format(context=\"Here is some context\", question=\"Here is a question\")\n",
"\n",
" chain = (\n",
" {\n",
" \"context\": itemgetter(\"question\") | retriever,\n",
" \"question\": itemgetter(\"question\"),\n",
" }\n",
" | prompt\n",
" | model\n",
" | parser\n",
" )\n",
" matching_results=index.similarity_search(question,k=2)\n",
"\n",
" return f\"Answer: {chain.invoke({'question': question})}\", matching_results\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import gradio as gr\n",
"from langchain_community.embeddings import SentenceTransformerEmbeddings\n",
"from langchain_community.vectorstores import Pinecone as LangchainPinecone\n",
"from utilis import load_split_file, create_index, final_response\n",
"from langchain_mistralai.chat_models import ChatMistralAI\n",
"\n",
"import os\n",
"import shutil\n",
"from dotenv import load_dotenv"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"load_dotenv()\n",
"PINECONE_API_KEY = os.getenv(\"PINECONE_API_KEY\")\n",
"MISTRAL_API_KEY = os.getenv(\"MISTRAL_API_KEY\")\n",
"SAVE_DIR = \"/RAG-APP/data.pdf\"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"embeddings = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
"\n",
"model = ChatMistralAI(mistral_api_key=MISTRAL_API_KEY)\n",
"pinecone_index = \"index\"\n",
"index_name = create_index(pinecone_index, PINECONE_API_KEY)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"file_path = \"data/last lesson.pdf\"\n",
"docs = load_split_file(file_path)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"index = LangchainPinecone.from_documents(docs, embeddings, index_name=index_name)\n",
"question = \"What data does google collects?\"\n",
"matching_results=index.similarity_search(question,k=2)\n",
"\n",
"answer = final_response(index, question, model)\n",
"\n",
"print(f\"{answer}\\n\\n{matching_results}\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "myvenv",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|