You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Run this Quickstart in Colab: [](https://colab.research.google.com/drive/1qMLzS4pAQfFBQ1wvCePbkSB6lOlrAcof?usp=sharing)
16
+
17
+
### 1. Set up Relevance AI
18
+
[block:code]
19
+
{
20
+
"codes": [
21
+
{
22
+
"code": "pip install -U RelevanceAI",
23
+
"language": "shell",
24
+
"name": "shell"
25
+
}
26
+
]
27
+
}
28
+
[/block]
29
+
### 2. Create a dataset and insert data
30
+
[block:code]
31
+
{
32
+
"codes": [
33
+
{
34
+
"code": "from relevanceai import Client \n\n#\"You can sign up/login and find your credentials here: https://development.qualitative-cloud.pages.dev/login\"\n#\"Once you have signed up, click on the value under `Authorization token` and paste it here\"\nclient = Client()\n\ndocs = [\n\t{\"_id\": \"1\", \"example_vector_\": [0.1, 0.1, 0.1], \"data\": \"Documentation\"},\n\t{\"_id\": \"2\", \"example_vector_\": [0.2, 0.2, 0.2], \"data\": \"Best document!\"},\n\t{\"_id\": \"3\", \"example_vector_\": [0.3, 0.3, 0.3], \"data\": \"document example\"},\n\t{\"_id\": \"4\", \"example_vector_\": [0.4, 0.4, 0.4], \"data\": \"this is another doc\"},\n\t{\"_id\": \"5\", \"example_vector_\": [0.5, 0.5, 0.5], \"data\": \"this is a doc\"},\n]\n\nclient.insert_documents(dataset_id=\"quickstart\", docs=docs)",
35
+
"language": "python",
36
+
"name": "Python"
37
+
}
38
+
]
39
+
}
40
+
[/block]
41
+
### 3. Vector search
42
+
[block:code]
43
+
{
44
+
"codes": [
45
+
{
46
+
"code": "client.services.search.vector(\n dataset_id=\"quickstart\", \n multivector_query=[\n {\"vector\": [0.2, 0.2, 0.2], \"fields\": [\"example_vector_\"]},\n ],\n page_size=3,\n query=\"sample search\" # Stored on the dashboard but not required\n)",
47
+
"language": "python"
48
+
}
49
+
]
50
+
}
51
+
[/block]
52
+
This is just the start. Relevance AI comes out of the box with support for features such as multi-vector search, filters, facets and traditional keyword matching to combine with your vector search. You can read more about how to construct a multi-vector query with those features [here](doc:vector-search-prerequisites).
53
+
54
+
Get started with some example applications you can build with Relevance AI. Check out some other guides below!
55
+
-[Text-to-image search with OpenAI's CLIP](doc:quickstart-text-to-image-search)
56
+
-[Multi-vector search with your own vectors](doc:search-with-your-own-vectors)
57
+
-[Hybrid Text search with Universal Sentence Encoder using Vectorhub](doc:quickstart-text-search)
58
+
-[Text search with Universal Sentence Encoder Question Answer from Google](doc:quickstart-question-answering)
0 commit comments