embedchain

1
{
2
  "cells": [
3
    {
4
      "cell_type": "markdown",
5
      "metadata": {
6
        "id": "b02n_zJ_hl3d"
7
      },
8
      "source": [
9
        "## Cookbook for using Cohere with Embedchain"
10
      ]
11
    },
12
    {
13
      "cell_type": "markdown",
14
      "metadata": {
15
        "id": "gyJ6ui2vhtMY"
16
      },
17
      "source": [
18
        "### Step-1: Install embedchain package"
19
      ]
20
    },
21
    {
22
      "cell_type": "code",
23
      "execution_count": null,
24
      "metadata": {
25
        "colab": {
26
          "base_uri": "https://localhost:8080/"
27
        },
28
        "id": "-NbXjAdlh0vJ",
29
        "outputId": "fae77912-4e6a-4c78-fcb7-fbbe46f7a9c7"
30
      },
31
      "outputs": [],
32
      "source": [
33
        "!pip install embedchain[cohere]"
34
      ]
35
    },
36
    {
37
      "cell_type": "markdown",
38
      "metadata": {
39
        "id": "nGnpSYAAh2bQ"
40
      },
41
      "source": [
42
        "### Step-2: Set Cohere related environment variables\n",
43
        "\n",
44
        "You can find `OPENAI_API_KEY` on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and `COHERE_API_KEY` key on your [Cohere dashboard](https://dashboard.cohere.com/api-keys)."
45
      ]
46
    },
47
    {
48
      "cell_type": "code",
49
      "execution_count": null,
50
      "metadata": {
51
        "id": "0fBdQ9GAiRvK"
52
      },
53
      "outputs": [],
54
      "source": [
55
        "import os\n",
56
        "from embedchain import App\n",
57
        "\n",
58
        "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
59
        "os.environ[\"COHERE_API_KEY\"] = \"xxx\""
60
      ]
61
    },
62
    {
63
      "cell_type": "markdown",
64
      "metadata": {
65
        "id": "PGt6uPLIi1CS"
66
      },
67
      "source": [
68
        "### Step-3 Create embedchain app and define your config"
69
      ]
70
    },
71
    {
72
      "cell_type": "code",
73
      "execution_count": null,
74
      "metadata": {
75
        "colab": {
76
          "base_uri": "https://localhost:8080/",
77
          "height": 321
78
        },
79
        "id": "Amzxk3m-i3tD",
80
        "outputId": "afe8afde-5cb8-46bc-c541-3ad26cc3fa6e"
81
      },
82
      "outputs": [],
83
      "source": [
84
        "app = App.from_config(config={\n",
85
        "    \"provider\": \"cohere\",\n",
86
        "    \"config\": {\n",
87
        "        \"model\": \"gptd-instruct-tft\",\n",
88
        "        \"temperature\": 0.5,\n",
89
        "        \"max_tokens\": 1000,\n",
90
        "        \"top_p\": 1,\n",
91
        "        \"stream\": False\n",
92
        "    }\n",
93
        "})"
94
      ]
95
    },
96
    {
97
      "cell_type": "markdown",
98
      "metadata": {
99
        "id": "XNXv4yZwi7ef"
100
      },
101
      "source": [
102
        "### Step-4: Add data sources to your app"
103
      ]
104
    },
105
    {
106
      "cell_type": "code",
107
      "execution_count": null,
108
      "metadata": {
109
        "colab": {
110
          "base_uri": "https://localhost:8080/",
111
          "height": 176
112
        },
113
        "id": "Sn_0rx9QjIY9",
114
        "outputId": "2f2718a4-3b7e-4844-fd46-3e0857653ca0"
115
      },
116
      "outputs": [],
117
      "source": [
118
        "app.add(\"https://www.forbes.com/profile/elon-musk\")"
119
      ]
120
    },
121
    {
122
      "cell_type": "markdown",
123
      "metadata": {
124
        "id": "_7W6fDeAjMAP"
125
      },
126
      "source": [
127
        "### Step-5: All set. Now start asking questions related to your data"
128
      ]
129
    },
130
    {
131
      "cell_type": "code",
132
      "execution_count": null,
133
      "metadata": {
134
        "colab": {
135
          "base_uri": "https://localhost:8080/"
136
        },
137
        "id": "cvIK7dWRjN_f",
138
        "outputId": "79e873c8-9594-45da-f5a3-0a893511267f"
139
      },
140
      "outputs": [],
141
      "source": [
142
        "while(True):\n",
143
        "    question = input(\"Enter question: \")\n",
144
        "    if question in ['q', 'exit', 'quit']:\n",
145
        "        break\n",
146
        "    answer = app.query(question)\n",
147
        "    print(answer)"
148
      ]
149
    }
150
  ],
151
  "metadata": {
152
    "colab": {
153
      "provenance": []
154
    },
155
    "kernelspec": {
156
      "display_name": "Python 3",
157
      "name": "python3"
158
    },
159
    "language_info": {
160
      "name": "python"
161
    }
162
  },
163
  "nbformat": 4,
164
  "nbformat_minor": 0
165
}
166