File size: 4,448 Bytes
acc4ffe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "07c1e3b9",
   "metadata": {},
   "source": [
    "# Getting Started\n",
    "\n",
    "This example showcases question answering over a vector database.\n",
    "We have chosen this as the example for getting started because it nicely combines a lot of different elements (Text splitters, embeddings, vectorstores) and then also shows how to use them in a chain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "82525493",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.vectorstores import Chroma\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain import OpenAI, VectorDBQA"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b7adc54",
   "metadata": {},
   "source": [
    "Here we load in the documents we want to use to create our index."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "611e0c19",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import TextLoader\n",
    "loader = TextLoader('../state_of_the_union.txt')\n",
    "documents = loader.load()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fdc0fc2",
   "metadata": {},
   "source": [
    "Next, we will split the documents into chunks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "afecb8cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
    "texts = text_splitter.split_documents(documents)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bebc041",
   "metadata": {},
   "source": [
    "We will then select which embeddings we want to use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9eaaa735",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = OpenAIEmbeddings()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "24612905",
   "metadata": {},
   "source": [
    "We now create the vectorstore to use as the index."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5c7049db",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running Chroma using direct local API.\n",
      "Using DuckDB in-memory for database. Data will be transient.\n"
     ]
    }
   ],
   "source": [
    "db = Chroma.from_documents(texts, embeddings)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "30c4e5c6",
   "metadata": {},
   "source": [
    "Finally, we create a chain and use it to answer questions!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3018f865",
   "metadata": {},
   "outputs": [],
   "source": [
    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=db)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "032a47f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\" The President said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "qa.run(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8b403637",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.1"
  },
  "vscode": {
   "interpreter": {
    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}