davanstrien HF staff commited on
Commit
b558f4f
1 Parent(s): 19c43aa

function calling example

Browse files
Files changed (1) hide show
  1. function_calling_search.ipynb +230 -0
function_calling_search.ipynb ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ }
15
+ },
16
+ "cells": [
17
+ {
18
+ "cell_type": "code",
19
+ "execution_count": 1,
20
+ "metadata": {
21
+ "id": "-DBXBd1Q6SFF"
22
+ },
23
+ "outputs": [],
24
+ "source": [
25
+ "import requests\n",
26
+ "from typing import List, Dict, Any, Iterator\n",
27
+ "\n",
28
+ "class DatasetSearchClient:\n",
29
+ " def __init__(self, base_url: str = \"https://librarian-bots-dataset-column-search-api.hf.space\"):\n",
30
+ " self.base_url = base_url\n",
31
+ "\n",
32
+ " def search(self,\n",
33
+ " columns: List[str],\n",
34
+ " match_all: bool = False,\n",
35
+ " page_size: int = 100) -> Iterator[Dict[str, Any]]:\n",
36
+ " \"\"\"\n",
37
+ " Search datasets using the provided API, automatically handling pagination.\n",
38
+ "\n",
39
+ " Args:\n",
40
+ " columns (List[str]): List of column names to search for.\n",
41
+ " match_all (bool, optional): If True, match all columns. If False, match any column. Defaults to False.\n",
42
+ " page_size (int, optional): Number of results per page. Defaults to 100.\n",
43
+ "\n",
44
+ " Yields:\n",
45
+ " Dict[str, Any]: Each dataset result from all pages.\n",
46
+ "\n",
47
+ " Raises:\n",
48
+ " requests.RequestException: If there's an error with the HTTP request.\n",
49
+ " ValueError: If the API returns an unexpected response format.\n",
50
+ " \"\"\"\n",
51
+ " page = 1\n",
52
+ " total_results = None\n",
53
+ "\n",
54
+ " while total_results is None or (page - 1) * page_size < total_results:\n",
55
+ " params = {\n",
56
+ " \"columns\": columns,\n",
57
+ " \"match_all\": str(match_all).lower(),\n",
58
+ " \"page\": page,\n",
59
+ " \"page_size\": page_size\n",
60
+ " }\n",
61
+ "\n",
62
+ " try:\n",
63
+ " response = requests.get(f\"{self.base_url}/search\", params=params)\n",
64
+ " response.raise_for_status()\n",
65
+ " data = response.json()\n",
66
+ "\n",
67
+ " if not {\"total\", \"page\", \"page_size\", \"results\"}.issubset(data.keys()):\n",
68
+ " raise ValueError(\"Unexpected response format from the API\")\n",
69
+ "\n",
70
+ " if total_results is None:\n",
71
+ " total_results = data['total']\n",
72
+ "\n",
73
+ " for dataset in data['results']:\n",
74
+ " yield dataset\n",
75
+ "\n",
76
+ " page += 1\n",
77
+ "\n",
78
+ " except requests.RequestException as e:\n",
79
+ " raise requests.RequestException(f\"Error connecting to the API: {str(e)}\")\n",
80
+ " except ValueError as e:\n",
81
+ " raise ValueError(f\"Error processing API response: {str(e)}\")\n",
82
+ "\n",
83
+ "# Create an instance of the client\n",
84
+ "client = DatasetSearchClient()"
85
+ ]
86
+ },
87
+ {
88
+ "cell_type": "code",
89
+ "source": [
90
+ "results = list(client.search(['tools'],match_all=True))\n",
91
+ "len(results)"
92
+ ],
93
+ "metadata": {
94
+ "colab": {
95
+ "base_uri": "https://localhost:8080/"
96
+ },
97
+ "id": "9yupgFYx6Sqx",
98
+ "outputId": "ac6d7c15-2267-4bbd-ceaa-1d98faee188b"
99
+ },
100
+ "execution_count": 5,
101
+ "outputs": [
102
+ {
103
+ "output_type": "execute_result",
104
+ "data": {
105
+ "text/plain": [
106
+ "38"
107
+ ]
108
+ },
109
+ "metadata": {},
110
+ "execution_count": 5
111
+ }
112
+ ]
113
+ },
114
+ {
115
+ "cell_type": "code",
116
+ "source": [
117
+ "results[0]"
118
+ ],
119
+ "metadata": {
120
+ "colab": {
121
+ "base_uri": "https://localhost:8080/"
122
+ },
123
+ "id": "atL-PQq76VrV",
124
+ "outputId": "f357fe16-a1f9-4bb2-ca3d-767f3ac6508d"
125
+ },
126
+ "execution_count": 6,
127
+ "outputs": [
128
+ {
129
+ "output_type": "execute_result",
130
+ "data": {
131
+ "text/plain": [
132
+ "{'hub_id': 'llamafactory/glaive_toolcall_en',\n",
133
+ " 'likes': 1,\n",
134
+ " 'downloads': 1151,\n",
135
+ " 'tags': ['task_categories:text-generation',\n",
136
+ " 'task_categories:question-answering',\n",
137
+ " 'language:en',\n",
138
+ " 'license:apache-2.0',\n",
139
+ " 'size_categories:1K<n<10K',\n",
140
+ " 'json',\n",
141
+ " 'text',\n",
142
+ " 'datasets',\n",
143
+ " 'mlcroissant',\n",
144
+ " 'region:us',\n",
145
+ " 'llama-factory',\n",
146
+ " 'croissant'],\n",
147
+ " 'created_at': 1715955540,\n",
148
+ " 'last_modified': 1717785919,\n",
149
+ " 'license': ['apache-2.0'],\n",
150
+ " 'language': ['en'],\n",
151
+ " 'config_name': 'default',\n",
152
+ " 'column_names': ['conversations', 'tools'],\n",
153
+ " 'features': [{'name': 'conversations',\n",
154
+ " 'list': [{'name': 'from', 'dtype': 'string'},\n",
155
+ " {'name': 'value', 'dtype': 'string'}]},\n",
156
+ " {'name': 'tools', 'dtype': 'string'}],\n",
157
+ " 'match_count': 1}"
158
+ ]
159
+ },
160
+ "metadata": {},
161
+ "execution_count": 6
162
+ }
163
+ ]
164
+ },
165
+ {
166
+ "cell_type": "code",
167
+ "source": [
168
+ "from huggingface_hub import create_collection, add_collection_item"
169
+ ],
170
+ "metadata": {
171
+ "id": "pXKtgF3r7GSK"
172
+ },
173
+ "execution_count": 9,
174
+ "outputs": []
175
+ },
176
+ {
177
+ "cell_type": "code",
178
+ "source": [
179
+ "collection = create_collection(\"Probably function calling datasets\", namespace=\"librarian-bots\",)"
180
+ ],
181
+ "metadata": {
182
+ "id": "MzkGofqF7M0i"
183
+ },
184
+ "execution_count": 11,
185
+ "outputs": []
186
+ },
187
+ {
188
+ "cell_type": "code",
189
+ "source": [
190
+ "collection.slug"
191
+ ],
192
+ "metadata": {
193
+ "colab": {
194
+ "base_uri": "https://localhost:8080/",
195
+ "height": 36
196
+ },
197
+ "id": "rAGoahvb7Ucp",
198
+ "outputId": "c5f7b158-85cb-49be-903f-7caaa98f7b74"
199
+ },
200
+ "execution_count": 12,
201
+ "outputs": [
202
+ {
203
+ "output_type": "execute_result",
204
+ "data": {
205
+ "text/plain": [
206
+ "'librarian-bots/probably-function-calling-datasets-6683d24da13a7bb7efee7464'"
207
+ ],
208
+ "application/vnd.google.colaboratory.intrinsic+json": {
209
+ "type": "string"
210
+ }
211
+ },
212
+ "metadata": {},
213
+ "execution_count": 12
214
+ }
215
+ ]
216
+ },
217
+ {
218
+ "cell_type": "code",
219
+ "source": [
220
+ "for item in results:\n",
221
+ " add_collection_item(collection.slug, item['hub_id'], item_type=\"dataset\")"
222
+ ],
223
+ "metadata": {
224
+ "id": "LR6nJyCL7ZZK"
225
+ },
226
+ "execution_count": 13,
227
+ "outputs": []
228
+ }
229
+ ]
230
+ }