oci-generativeaiinference 2.98.0 → 2.98.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/index.d.ts +2 -2
- package/index.js +2 -2
- package/lib/client.d.ts +2 -2
- package/lib/client.js +2 -2
- package/lib/model/assistant-message.d.ts +2 -2
- package/lib/model/assistant-message.js +2 -2
- package/lib/model/base-chat-request.d.ts +2 -2
- package/lib/model/base-chat-request.js +2 -2
- package/lib/model/base-chat-response.d.ts +2 -2
- package/lib/model/base-chat-response.js +2 -2
- package/lib/model/chat-choice.d.ts +2 -2
- package/lib/model/chat-choice.js +2 -2
- package/lib/model/chat-content.d.ts +2 -2
- package/lib/model/chat-content.js +6 -2
- package/lib/model/chat-content.js.map +1 -1
- package/lib/model/chat-details.d.ts +2 -2
- package/lib/model/chat-details.js +2 -2
- package/lib/model/chat-result.d.ts +2 -2
- package/lib/model/chat-result.js +2 -2
- package/lib/model/choice.d.ts +2 -2
- package/lib/model/choice.js +2 -2
- package/lib/model/citation.d.ts +2 -2
- package/lib/model/citation.js +2 -2
- package/lib/model/cohere-chat-bot-message.d.ts +2 -2
- package/lib/model/cohere-chat-bot-message.js +2 -2
- package/lib/model/cohere-chat-request.d.ts +8 -3
- package/lib/model/cohere-chat-request.js +8 -2
- package/lib/model/cohere-chat-request.js.map +1 -1
- package/lib/model/cohere-chat-response.d.ts +2 -2
- package/lib/model/cohere-chat-response.js +2 -2
- package/lib/model/cohere-llm-inference-request.d.ts +2 -2
- package/lib/model/cohere-llm-inference-request.js +2 -2
- package/lib/model/cohere-llm-inference-response.d.ts +2 -2
- package/lib/model/cohere-llm-inference-response.js +2 -2
- package/lib/model/cohere-message.d.ts +2 -2
- package/lib/model/cohere-message.js +2 -2
- package/lib/model/cohere-parameter-definition.d.ts +2 -2
- package/lib/model/cohere-parameter-definition.js +2 -2
- package/lib/model/cohere-response-format.d.ts +29 -0
- package/lib/model/cohere-response-format.js +79 -0
- package/lib/model/cohere-response-format.js.map +1 -0
- package/lib/model/cohere-response-json-format.d.ts +35 -0
- package/lib/model/cohere-response-json-format.js +61 -0
- package/lib/model/cohere-response-json-format.js.map +1 -0
- package/lib/model/cohere-response-text-format.d.ts +31 -0
- package/lib/model/cohere-response-text-format.js +61 -0
- package/lib/model/cohere-response-text-format.js.map +1 -0
- package/lib/model/cohere-system-message.d.ts +2 -2
- package/lib/model/cohere-system-message.js +2 -2
- package/lib/model/cohere-tool-call.d.ts +2 -2
- package/lib/model/cohere-tool-call.js +2 -2
- package/lib/model/cohere-tool-message.d.ts +2 -2
- package/lib/model/cohere-tool-message.js +2 -2
- package/lib/model/cohere-tool-result.d.ts +2 -2
- package/lib/model/cohere-tool-result.js +2 -2
- package/lib/model/cohere-tool.d.ts +2 -2
- package/lib/model/cohere-tool.js +2 -2
- package/lib/model/cohere-user-message.d.ts +2 -2
- package/lib/model/cohere-user-message.js +2 -2
- package/lib/model/dedicated-serving-mode.d.ts +2 -2
- package/lib/model/dedicated-serving-mode.js +2 -2
- package/lib/model/embed-text-details.d.ts +2 -2
- package/lib/model/embed-text-details.js +2 -2
- package/lib/model/embed-text-result.d.ts +2 -2
- package/lib/model/embed-text-result.js +2 -2
- package/lib/model/generate-text-details.d.ts +2 -2
- package/lib/model/generate-text-details.js +2 -2
- package/lib/model/generate-text-result.d.ts +2 -2
- package/lib/model/generate-text-result.js +2 -2
- package/lib/model/generated-text.d.ts +2 -2
- package/lib/model/generated-text.js +2 -2
- package/lib/model/generic-chat-request.d.ts +2 -2
- package/lib/model/generic-chat-request.js +2 -2
- package/lib/model/generic-chat-response.d.ts +2 -2
- package/lib/model/generic-chat-response.js +2 -2
- package/lib/model/image-content.d.ts +32 -0
- package/lib/model/image-content.js +61 -0
- package/lib/model/image-content.js.map +1 -0
- package/lib/model/image-url.d.ts +46 -0
- package/lib/model/image-url.js +47 -0
- package/lib/model/image-url.js.map +1 -0
- package/lib/model/index.d.ts +12 -2
- package/lib/model/index.js +13 -3
- package/lib/model/index.js.map +1 -1
- package/lib/model/llama-llm-inference-request.d.ts +2 -2
- package/lib/model/llama-llm-inference-request.js +2 -2
- package/lib/model/llama-llm-inference-response.d.ts +2 -2
- package/lib/model/llama-llm-inference-response.js +2 -2
- package/lib/model/llm-inference-request.d.ts +2 -2
- package/lib/model/llm-inference-request.js +2 -2
- package/lib/model/llm-inference-response.d.ts +2 -2
- package/lib/model/llm-inference-response.js +2 -2
- package/lib/model/logprobs.d.ts +2 -2
- package/lib/model/logprobs.js +2 -2
- package/lib/model/message.d.ts +2 -2
- package/lib/model/message.js +2 -2
- package/lib/model/on-demand-serving-mode.d.ts +2 -2
- package/lib/model/on-demand-serving-mode.js +2 -2
- package/lib/model/search-query.d.ts +2 -2
- package/lib/model/search-query.js +2 -2
- package/lib/model/serving-mode.d.ts +2 -2
- package/lib/model/serving-mode.js +2 -2
- package/lib/model/summarize-text-details.d.ts +2 -2
- package/lib/model/summarize-text-details.js +2 -2
- package/lib/model/summarize-text-result.d.ts +2 -2
- package/lib/model/summarize-text-result.js +2 -2
- package/lib/model/system-message.d.ts +2 -2
- package/lib/model/system-message.js +2 -2
- package/lib/model/text-content.d.ts +2 -2
- package/lib/model/text-content.js +2 -2
- package/lib/model/token-likelihood.d.ts +2 -2
- package/lib/model/token-likelihood.js +2 -2
- package/lib/model/user-message.d.ts +2 -2
- package/lib/model/user-message.js +2 -2
- package/lib/request/index.d.ts +2 -2
- package/lib/request/index.js +2 -2
- package/lib/response/index.d.ts +2 -2
- package/lib/response/index.js +2 -2
- package/package.json +3 -3
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
package/lib/request/index.d.ts
CHANGED
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
package/lib/request/index.js
CHANGED
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
package/lib/response/index.d.ts
CHANGED
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
* Generative AI Service Inference API
|
|
3
3
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
4
4
|
|
|
5
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
5
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
6
6
|
|
|
7
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
7
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
8
8
|
|
|
9
9
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
10
10
|
|
package/lib/response/index.js
CHANGED
|
@@ -3,9 +3,9 @@
|
|
|
3
3
|
* Generative AI Service Inference API
|
|
4
4
|
* OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
|
|
5
5
|
|
|
6
|
-
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/
|
|
6
|
+
Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to [chat](#/EN/generative-ai-inference/latest/ChatResult/Chat), [generate text](#/EN/generative-ai-inference/latest/GenerateTextResult/GenerateText), [summarize](#/EN/generative-ai-inference/latest/SummarizeTextResult/SummarizeText), and [create text embeddings](#/EN/generative-ai-inference/latest/EmbedTextResult/EmbedText).
|
|
7
7
|
|
|
8
|
-
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](
|
|
8
|
+
To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the [Generative AI service management API](#/EN/generative-ai/latest/) to [create a custom model](#/EN/generative-ai/latest/Model/) by fine-tuning an out-of-the-box model, or a previous version of a custom model, using your own data. Fine-tune the custom model on a [fine-tuning dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/). Then, create a [hosting dedicated AI cluster](#/EN/generative-ai/latest/DedicatedAiCluster/) with an [endpoint](#/en/generative-ai/latest/Endpoint/) to host your custom model. For resource management in the Generative AI service, use the [Generative AI service management API](#/EN/generative-ai/latest/).
|
|
9
9
|
|
|
10
10
|
To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
|
|
11
11
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "oci-generativeaiinference",
|
|
3
|
-
"version": "2.98.
|
|
3
|
+
"version": "2.98.1",
|
|
4
4
|
"description": "OCI NodeJS client for Generative Ai Inference Service",
|
|
5
5
|
"repository": {
|
|
6
6
|
"type": "git",
|
|
@@ -15,8 +15,8 @@
|
|
|
15
15
|
},
|
|
16
16
|
"license": "(UPL-1.0 OR Apache-2.0)",
|
|
17
17
|
"dependencies": {
|
|
18
|
-
"oci-common": "2.98.
|
|
19
|
-
"oci-workrequests": "2.98.
|
|
18
|
+
"oci-common": "2.98.1",
|
|
19
|
+
"oci-workrequests": "2.98.1"
|
|
20
20
|
},
|
|
21
21
|
"publishConfig": {
|
|
22
22
|
"registry": "https://registry.npmjs.org"
|