File size: 4,205 Bytes
bea947b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "import os\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from langchain.vectorstores import FAISS\n",
    "from langchain_core.output_parsers import StrOutputParser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.display import Markdown\n",
    "def to_Markdown(text):\n",
    "    return Markdown(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "def VectorStore(data,embedding):\n",
    "    splitter = RecursiveCharacterTextSplitter(chunk_size = 1000,chunk_overlap =500)\n",
    "    chunks = splitter.split_documents(data)\n",
    "    vector = FAISS.from_documents(chunks,embedding)\n",
    "    retriever = vector.as_retriever()\n",
    "    return retriever\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = ChatGoogleGenerativeAI(model='gemini-1.5-flash')\n",
    "from langchain_huggingface import HuggingFaceEmbeddings\n",
    "embedding = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Hi there! How can I help you today?'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.invoke(\"hi\").content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def data_ingestion(path):\n",
    "    loader = WebBaseLoader(path)  \n",
    "    data = loader.load()\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import ChatPromptTemplate\n",
    "def prompt_helper():\n",
    "    template = \"\"\" Answer Based on the following context:\n",
    "    {context}\n",
    "    Question: {question}\n",
    "    provide only helpful information.\n",
    "    \"\"\"\n",
    "    prompt = ChatPromptTemplate.from_template(template)\n",
    "    return prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def main():\n",
    "    path = input(\"Enter the website link: \")\n",
    "    data = data_ingestion(path)\n",
    "    retriever = VectorStore(data,embedding)\n",
    "    prompt = prompt_helper()\n",
    "    chain = (\n",
    "    {'context': retriever , 'question': RunnablePassthrough()}\n",
    "    | prompt\n",
    "    |llm\n",
    "    |StrOutputParser()\n",
    "    )\n",
    "    question = input(\"Enter the question from the link: \")\n",
    "    response = chain.invoke(question)\n",
    "    print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The provided text does not contain any information about the color blue.\n"
     ]
    }
   ],
   "source": [
    "main()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}