embedchain
121 строка · 3.3 Кб
1{
2"cells": [
3{
4"cell_type": "code",
5"execution_count": 1,
6"id": "e9a9dc6a",
7"metadata": {},
8"outputs": [],
9"source": [
10"from embedchain import App\n",
11"\n",
12"embedchain_docs_bot = App()"
13]
14},
15{
16"cell_type": "code",
17"execution_count": 2,
18"id": "c1c24d68",
19"metadata": {},
20"outputs": [
21{
22"name": "stdout",
23"output_type": "stream",
24"text": [
25"All data from https://docs.embedchain.ai/ already exists in the database.\n"
26]
27}
28],
29"source": [
30"embedchain_docs_bot.add(\"docs_site\", \"https://docs.embedchain.ai/\")"
31]
32},
33{
34"cell_type": "code",
35"execution_count": 3,
36"id": "48cdaecf",
37"metadata": {},
38"outputs": [],
39"source": [
40"answer = embedchain_docs_bot.query(\"Write a flask API for embedchain bot\")"
41]
42},
43{
44"cell_type": "code",
45"execution_count": 4,
46"id": "0fe18085",
47"metadata": {},
48"outputs": [
49{
50"data": {
51"text/markdown": [
52"To write a Flask API for the embedchain bot, you can use the following code snippet:\n",
53"\n",
54"```python\n",
55"from flask import Flask, request, jsonify\n",
56"from embedchain import App\n",
57"\n",
58"app = Flask(__name__)\n",
59"bot = App()\n",
60"\n",
61"# Add datasets to the bot\n",
62"bot.add(\"youtube_video\", \"https://www.youtube.com/watch?v=3qHkcs3kG44\")\n",
63"bot.add(\"pdf_file\", \"https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf\")\n",
64"\n",
65"@app.route('/query', methods=['POST'])\n",
66"def query():\n",
67" data = request.get_json()\n",
68" question = data['question']\n",
69" response = bot.query(question)\n",
70" return jsonify({'response': response})\n",
71"\n",
72"if __name__ == '__main__':\n",
73" app.run()\n",
74"```\n",
75"\n",
76"In this code, we create a Flask app and initialize an instance of the embedchain bot. We then add the desired datasets to the bot using the `add()` function.\n",
77"\n",
78"Next, we define a route `/query` that accepts POST requests. The request body should contain a JSON object with a `question` field. The bot's `query()` function is called with the provided question, and the response is returned as a JSON object.\n",
79"\n",
80"Finally, we run the Flask app using `app.run()`.\n",
81"\n",
82"Note: Make sure to install Flask and embedchain packages before running this code."
83],
84"text/plain": [
85"<IPython.core.display.Markdown object>"
86]
87},
88"metadata": {},
89"output_type": "display_data"
90}
91],
92"source": [
93"from IPython.display import Markdown\n",
94"# Create a Markdown object and display it\n",
95"markdown_answer = Markdown(answer)\n",
96"display(markdown_answer)"
97]
98}
99],
100"metadata": {
101"kernelspec": {
102"display_name": "Python 3 (ipykernel)",
103"language": "python",
104"name": "python3"
105},
106"language_info": {
107"codemirror_mode": {
108"name": "ipython",
109"version": 3
110},
111"file_extension": ".py",
112"mimetype": "text/x-python",
113"name": "python",
114"nbconvert_exporter": "python",
115"pygments_lexer": "ipython3",
116"version": "3.11.4"
117}
118},
119"nbformat": 4,
120"nbformat_minor": 5
121}
122