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
When you only specify `model_configs`, the default model providers (NVIDIAand OpenAI) are still available. You only need to create custom providers if you want to connect to different endpoints or modify provider settings.
99
+
When you only specify `model_configs`, the default model providers (NVIDIA, OpenAI, and OpenRouter) are still available. You only need to create custom providers if you want to connect to different endpoints or modify provider settings.
100
100
101
101
!!! tip "Mixing Custom and Default Models"
102
102
When you provide custom `model_configs` to `DataDesignerConfigBuilder`, they **replace** the defaults entirely. To use custom model configs in addition to the default configs, use the add_model_config method:
Copy file name to clipboardExpand all lines: docs/concepts/models/default-model-settings.md
+35-12Lines changed: 35 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ Data Designer ships with pre-configured model providers and model configurations
4
4
5
5
## Model Providers
6
6
7
-
Data Designer includes two default model providers that are configured automatically:
7
+
Data Designer includes a few default model providers that are configured automatically:
8
8
9
9
### NVIDIA Provider (`nvidia`)
10
10
@@ -24,6 +24,15 @@ The NVIDIA provider gives you access to state-of-the-art models including Nemotr
24
24
25
25
The OpenAI provider gives you access to GPT models and other OpenAI offerings.
26
26
27
+
### OpenRouter Provider (`openrouter`)
28
+
29
+
-**Endpoint**: `https://openrouter.ai/api/v1`
30
+
-**API Key**: Set via `OPENROUTER_API_KEY` environment variable
31
+
-**Models**: Access to a wide variety of models through OpenRouter's unified API
32
+
-**Getting Started**: Get your API key from [openrouter.ai](https://openrouter.ai)
33
+
34
+
The OpenRouter provider gives you access to a unified interface for many different language models from various providers.
35
+
27
36
## Model Configurations
28
37
29
38
Data Designer provides pre-configured model aliases for common use cases. When you create a `DataDesignerConfigBuilder` without specifying `model_configs`, these default configurations are automatically available.
@@ -32,22 +41,35 @@ Data Designer provides pre-configured model aliases for common use cases. When y
32
41
33
42
The following model configurations are automatically available when `NVIDIA_API_KEY` is set:
34
43
35
-
| Alias | Model | Use Case | Temperature | Top P |
|`openrouter-text`|`nvidia/nemotron-3-nano-30b-a3b`| General text generation |`temperature=1.0, top_p=1.0`|
70
+
|`openrouter-reasoning`|`openai/gpt-oss-20b`| Reasoning and analysis tasks |`temperature=0.35, top_p=0.95`|
71
+
|`openrouter-vision`|`nvidia/nemotron-nano-12b-v2-vl`| Vision and image understanding |`temperature=0.85, top_p=0.95`|
72
+
|`openrouter-embedding`|`openai/text-embedding-3-large`| Text embeddings |`encoding_format="float"`|
51
73
52
74
53
75
## Using Default Settings
@@ -83,7 +105,7 @@ Both methods operate on the same files, ensuring consistency across your entire
83
105
## Important Notes
84
106
85
107
!!! warning "API Key Requirements"
86
-
While default model configurations are always available, you need to set the appropriate API key environment variable (`NVIDIA_API_KEY`or `OPENAI_API_KEY`) to actually use the corresponding models for data generation. Without a valid API key, any attempt to generate data using that provider's models will fail.
108
+
While default model configurations are always available, you need to set the appropriate API key environment variable (`NVIDIA_API_KEY`, `OPENAI_API_KEY`, or `OPENROUTER_API_KEY`) to actually use the corresponding models for data generation. Without a valid API key, any attempt to generate data using that provider's models will fail.
87
109
88
110
!!! tip "Environment Variables"
89
111
Store your API keys in environment variables rather than hardcoding them in your scripts:
@@ -92,6 +114,7 @@ Both methods operate on the same files, ensuring consistency across your entire
Copy file name to clipboardExpand all lines: docs/concepts/models/model-configs.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,7 +15,7 @@ The `ModelConfig` class has the following fields:
15
15
|`alias`|`str`| Yes | Unique identifier for this model configuration (e.g., `"my-text-model"`, `"reasoning-model"`) |
16
16
|`model`|`str`| Yes | Model identifier as recognized by the provider (e.g., `"nvidia/nemotron-3-nano-30b-a3b"`, `"gpt-4"`) |
17
17
|`inference_parameters`|`InferenceParamsT`| No | Controls model behavior during generation. Use `ChatCompletionInferenceParams` for text/code/structured generation or `EmbeddingInferenceParams` for embeddings. Defaults to `ChatCompletionInferenceParams()` if not provided. The generation type is automatically determined by the inference parameters type. See [Inference Parameters](inference_parameters.md) for details. |
18
-
|`provider`|`str`| No | Reference to the name of the Provider to use (e.g., `"nvidia"`, `"openai"`). If not specified, one set as the default provider, which may resolve to the first provider if there are more than one |
18
+
|`provider`|`str`| No | Reference to the name of the Provider to use (e.g., `"nvidia"`, `"openai"`, `"openrouter"`). If not specified, one set as the default provider, which may resolve to the first provider if there are more than one |
For more information, check the [Quick Start](../quick-start.md), [Default Model Settings](../concepts/models/default-model-settings.md) and how to [Configure Model Settings Using The CLI](../concepts/models/configure-model-settings-with-the-cli.md).
0 commit comments