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
Copy file name to clipboardExpand all lines: docs/source/guide/ask_ai.md
+9-9Lines changed: 9 additions & 9 deletions
Original file line number
Diff line number
Diff line change
@@ -1,19 +1,19 @@
1
1
---
2
-
title: About Ask AI - Beta 🧪
3
-
short: Ask AI
2
+
title: About AI Features - Beta 🧪
3
+
short: AI features
4
4
tier: enterprise
5
5
type: guide
6
6
order: 0
7
7
order_enterprise: 356
8
-
meta_title: About Ask AI
9
-
meta_description: Information about using the Ask AI tool in Label Studio
8
+
meta_title: About AI features
9
+
meta_description: Information about using the AI features in Label Studio
10
10
section: "Manage Your Organization"
11
11
date: 2025-01-28 16:40:16
12
12
---
13
13
14
-
The Ask AI tool is an LLM that has been trained on our documentation, codebase, and several other Label Studio resources.
14
+
AI features in Label Studio use an LLM that has been trained on our documentation, codebase, and several other Label Studio resources.
15
15
16
-
You can use Ask AI to create or refine your labeling configuration. Instead of manually building labeling interfaces or project instructions from scratch, you can prompt the AI with a description of what your labeling project needs, and the AI generates a suggested configuration.
16
+
You can use AI to create or refine your labeling configuration. Instead of manually building labeling interfaces or project instructions from scratch, you can prompt the AI with a description of what your labeling project needs, and the AI generates a suggested configuration.
17
17
18
18
19
19
## What models do you use?
@@ -36,13 +36,13 @@ The model is trained on public resources like our documentation, codebase, blog,
36
36
37
37
We are on a Tier 5 OpenAI account, and opt out of all requests for training data.
38
38
39
-
We track requests to Ask AI to use as quality control, but they are only used to test the outputs of the model. For example: If Company X asks "Make a project to label opossums," we may notice that Ask AI did not provide a satisfactory answer and we may create configurations with opossums in them and train the model on them. The model would not be trained on any of Company X's questions or data.
39
+
We track requests to our AI to use as quality control, but they are only used to test the outputs of the model. For example: If Company X asks "Make a project to label opossums," we may notice that our AI did not provide a satisfactory answer and we may create configurations with opossums in them and train the model on them. The model would not be trained on any of Company X's questions or data.
40
40
41
41
All tracked data is covered by our industry-leading [security and privacy policies](https://humansignal.com/security/).
42
42
43
-
## Can I disable Ask AI?
43
+
## How do I enable or disable AI features?
44
44
45
-
Yes, contact us to disable this feature.
45
+
You can enable AI features from the **Organization > Billing & Usage** page. Only users in the Owners role have access to view and modify this page.
Copy file name to clipboardExpand all lines: docs/source/guide/prompts_keys.md
+9Lines changed: 9 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,7 @@ There are two approaches to adding a model provider API key.
18
18
* OpenAI
19
19
* Vertex AI
20
20
* Gemini
21
+
* Anthropic
21
22
22
23
* In the second scenario, you add a separate API key per model. Examples include:
23
24
@@ -58,6 +59,14 @@ The JSON credentials are required. You can also optionally provide the project I
58
59
59
60
Once added, all supported models will appear in the base model drop-down when you [draft your prompt](prompts_draft).
60
61
62
+
## Anthropic API key
63
+
64
+
You can only have one Anthropic key per organization. This grants you access to set of whitelisted models. For a list of these models, see [Supported base models](prompts_overview#Supported-base-models).
65
+
66
+
For information on getting an Anthropic API key, see [Anthropic - Accessing the API](https://docs.anthropic.com/en/api/getting-started#accessing-the-api).
67
+
68
+
Once added, all supported models will appear in the base model drop-down when you [draft your prompt](prompts_draft).
69
+
61
70
## Azure OpenAI key
62
71
63
72
Each Azure OpenAI key is tied to a specific deployment, and each deployment comprises a single OpenAI model. So if you want to use multiple models through Azure, you will need to create a deployment for each model and then add each key to Label Studio.
Copy file name to clipboardExpand all lines: docs/source/guide/prompts_overview.md
+2-1Lines changed: 2 additions & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -48,9 +48,10 @@ With Prompts, you can:
48
48
49
49
| Provider | Supported models |
50
50
| --- | --- |
51
-
|**OpenAI**| gpt-3.5-turbo-16k* <br>gpt-3.5-turbo* <br>gpt-4 <br>gpt-4-turbo <br>gpt-4o <br>gpt-4o-mini <br>o3-mini<br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data. |
51
+
|**OpenAI**| gpt-3.5-turbo-16k* <br>gpt-3.5-turbo* <br>gpt-4 <br>gpt-4-turbo <br>gpt-4o <br>gpt-4o-mini <br>o3-mini <br>o1<br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data. |
|**Azure OpenAI**|[Azure OpenAI chat-based models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) <br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data. |
0 commit comments