oci-generativeaiinference 2.102.1 → 2.103.0

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.
Files changed (144) hide show
  1. package/index.d.ts +3 -3
  2. package/index.js +3 -3
  3. package/lib/client.d.ts +8 -8
  4. package/lib/client.js +8 -8
  5. package/lib/model/assistant-message.d.ts +3 -3
  6. package/lib/model/assistant-message.js +3 -3
  7. package/lib/model/base-chat-request.d.ts +3 -3
  8. package/lib/model/base-chat-request.js +3 -3
  9. package/lib/model/base-chat-response.d.ts +3 -3
  10. package/lib/model/base-chat-response.js +3 -3
  11. package/lib/model/chat-choice.d.ts +3 -3
  12. package/lib/model/chat-choice.js +3 -3
  13. package/lib/model/chat-content.d.ts +3 -3
  14. package/lib/model/chat-content.js +3 -3
  15. package/lib/model/chat-details.d.ts +3 -3
  16. package/lib/model/chat-details.js +3 -3
  17. package/lib/model/chat-result.d.ts +3 -3
  18. package/lib/model/chat-result.js +3 -3
  19. package/lib/model/choice.d.ts +3 -3
  20. package/lib/model/choice.js +3 -3
  21. package/lib/model/citation.d.ts +3 -3
  22. package/lib/model/citation.js +3 -3
  23. package/lib/model/cohere-chat-bot-message.d.ts +3 -3
  24. package/lib/model/cohere-chat-bot-message.js +3 -3
  25. package/lib/model/cohere-chat-request.d.ts +3 -3
  26. package/lib/model/cohere-chat-request.js +3 -3
  27. package/lib/model/cohere-chat-response.d.ts +3 -3
  28. package/lib/model/cohere-chat-response.js +3 -3
  29. package/lib/model/cohere-llm-inference-request.d.ts +3 -3
  30. package/lib/model/cohere-llm-inference-request.js +3 -3
  31. package/lib/model/cohere-llm-inference-response.d.ts +3 -3
  32. package/lib/model/cohere-llm-inference-response.js +3 -3
  33. package/lib/model/cohere-message.d.ts +3 -3
  34. package/lib/model/cohere-message.js +3 -3
  35. package/lib/model/cohere-parameter-definition.d.ts +3 -3
  36. package/lib/model/cohere-parameter-definition.js +3 -3
  37. package/lib/model/cohere-response-format.d.ts +3 -3
  38. package/lib/model/cohere-response-format.js +3 -3
  39. package/lib/model/cohere-response-json-format.d.ts +3 -3
  40. package/lib/model/cohere-response-json-format.js +3 -3
  41. package/lib/model/cohere-response-text-format.d.ts +3 -3
  42. package/lib/model/cohere-response-text-format.js +3 -3
  43. package/lib/model/cohere-system-message.d.ts +3 -3
  44. package/lib/model/cohere-system-message.js +3 -3
  45. package/lib/model/cohere-tool-call.d.ts +3 -3
  46. package/lib/model/cohere-tool-call.js +3 -3
  47. package/lib/model/cohere-tool-message.d.ts +3 -3
  48. package/lib/model/cohere-tool-message.js +3 -3
  49. package/lib/model/cohere-tool-result.d.ts +3 -3
  50. package/lib/model/cohere-tool-result.js +3 -3
  51. package/lib/model/cohere-tool.d.ts +3 -3
  52. package/lib/model/cohere-tool.js +3 -3
  53. package/lib/model/cohere-user-message.d.ts +3 -3
  54. package/lib/model/cohere-user-message.js +3 -3
  55. package/lib/model/dedicated-serving-mode.d.ts +3 -3
  56. package/lib/model/dedicated-serving-mode.js +3 -3
  57. package/lib/model/document-rank.d.ts +3 -3
  58. package/lib/model/document-rank.js +3 -3
  59. package/lib/model/document.d.ts +3 -3
  60. package/lib/model/document.js +3 -3
  61. package/lib/model/embed-text-details.d.ts +3 -3
  62. package/lib/model/embed-text-details.js +3 -3
  63. package/lib/model/embed-text-result.d.ts +3 -3
  64. package/lib/model/embed-text-result.js +3 -3
  65. package/lib/model/function-call.d.ts +3 -3
  66. package/lib/model/function-call.js +3 -3
  67. package/lib/model/function-definition.d.ts +3 -3
  68. package/lib/model/function-definition.js +3 -3
  69. package/lib/model/generate-text-details.d.ts +3 -3
  70. package/lib/model/generate-text-details.js +3 -3
  71. package/lib/model/generate-text-result.d.ts +3 -3
  72. package/lib/model/generate-text-result.js +3 -3
  73. package/lib/model/generated-text.d.ts +3 -3
  74. package/lib/model/generated-text.js +3 -3
  75. package/lib/model/generic-chat-request.d.ts +3 -3
  76. package/lib/model/generic-chat-request.js +3 -3
  77. package/lib/model/generic-chat-response.d.ts +3 -3
  78. package/lib/model/generic-chat-response.js +3 -3
  79. package/lib/model/image-content.d.ts +3 -3
  80. package/lib/model/image-content.js +3 -3
  81. package/lib/model/image-url.d.ts +3 -3
  82. package/lib/model/image-url.js +3 -3
  83. package/lib/model/index.d.ts +3 -3
  84. package/lib/model/index.js +3 -3
  85. package/lib/model/llama-llm-inference-request.d.ts +3 -3
  86. package/lib/model/llama-llm-inference-request.js +3 -3
  87. package/lib/model/llama-llm-inference-response.d.ts +3 -3
  88. package/lib/model/llama-llm-inference-response.js +3 -3
  89. package/lib/model/llm-inference-request.d.ts +3 -3
  90. package/lib/model/llm-inference-request.js +3 -3
  91. package/lib/model/llm-inference-response.d.ts +3 -3
  92. package/lib/model/llm-inference-response.js +3 -3
  93. package/lib/model/logprobs.d.ts +3 -3
  94. package/lib/model/logprobs.js +3 -3
  95. package/lib/model/message.d.ts +3 -3
  96. package/lib/model/message.js +3 -3
  97. package/lib/model/on-demand-serving-mode.d.ts +3 -3
  98. package/lib/model/on-demand-serving-mode.js +3 -3
  99. package/lib/model/rerank-text-details.d.ts +3 -3
  100. package/lib/model/rerank-text-details.js +3 -3
  101. package/lib/model/rerank-text-result.d.ts +3 -3
  102. package/lib/model/rerank-text-result.js +3 -3
  103. package/lib/model/search-query.d.ts +3 -3
  104. package/lib/model/search-query.js +3 -3
  105. package/lib/model/serving-mode.d.ts +3 -3
  106. package/lib/model/serving-mode.js +3 -3
  107. package/lib/model/summarize-text-details.d.ts +3 -3
  108. package/lib/model/summarize-text-details.js +3 -3
  109. package/lib/model/summarize-text-result.d.ts +3 -3
  110. package/lib/model/summarize-text-result.js +3 -3
  111. package/lib/model/system-message.d.ts +3 -3
  112. package/lib/model/system-message.js +3 -3
  113. package/lib/model/text-content.d.ts +3 -3
  114. package/lib/model/text-content.js +3 -3
  115. package/lib/model/token-likelihood.d.ts +3 -3
  116. package/lib/model/token-likelihood.js +3 -3
  117. package/lib/model/tool-call.d.ts +3 -3
  118. package/lib/model/tool-call.js +3 -3
  119. package/lib/model/tool-choice-auto.d.ts +3 -3
  120. package/lib/model/tool-choice-auto.js +3 -3
  121. package/lib/model/tool-choice-function.d.ts +3 -3
  122. package/lib/model/tool-choice-function.js +3 -3
  123. package/lib/model/tool-choice-none.d.ts +3 -3
  124. package/lib/model/tool-choice-none.js +3 -3
  125. package/lib/model/tool-choice-required.d.ts +3 -3
  126. package/lib/model/tool-choice-required.js +3 -3
  127. package/lib/model/tool-choice.d.ts +3 -3
  128. package/lib/model/tool-choice.js +3 -3
  129. package/lib/model/tool-definition.d.ts +3 -3
  130. package/lib/model/tool-definition.js +3 -3
  131. package/lib/model/tool-message.d.ts +3 -3
  132. package/lib/model/tool-message.js +3 -3
  133. package/lib/model/user-message.d.ts +3 -3
  134. package/lib/model/user-message.js +3 -3
  135. package/lib/request/chat-request.d.ts +1 -1
  136. package/lib/request/embed-text-request.d.ts +1 -1
  137. package/lib/request/generate-text-request.d.ts +1 -1
  138. package/lib/request/index.d.ts +3 -3
  139. package/lib/request/index.js +3 -3
  140. package/lib/request/rerank-text-request.d.ts +1 -1
  141. package/lib/request/summarize-text-request.d.ts +1 -1
  142. package/lib/response/index.d.ts +3 -3
  143. package/lib/response/index.js +3 -3
  144. package/package.json +3 -3
package/index.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/index.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/client.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
@@ -93,7 +93,7 @@ export declare class GenerativeAiInferenceClient {
93
93
  * @param ChatRequest
94
94
  * @return ChatResponse
95
95
  * @throws OciError when an error occurs
96
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/Chat.ts.html |here} to see how to use Chat API.
96
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/Chat.ts.html |here} to see how to use Chat API.
97
97
  */
98
98
  chat(chatRequest: requests.ChatRequest): Promise<responses.ChatResponse | ReadableStream<Uint8Array> | null>;
99
99
  /**
@@ -105,7 +105,7 @@ export declare class GenerativeAiInferenceClient {
105
105
  * @param EmbedTextRequest
106
106
  * @return EmbedTextResponse
107
107
  * @throws OciError when an error occurs
108
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/EmbedText.ts.html |here} to see how to use EmbedText API.
108
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/EmbedText.ts.html |here} to see how to use EmbedText API.
109
109
  */
110
110
  embedText(embedTextRequest: requests.EmbedTextRequest): Promise<responses.EmbedTextResponse>;
111
111
  /**
@@ -115,7 +115,7 @@ export declare class GenerativeAiInferenceClient {
115
115
  * @param GenerateTextRequest
116
116
  * @return GenerateTextResponse
117
117
  * @throws OciError when an error occurs
118
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/GenerateText.ts.html |here} to see how to use GenerateText API.
118
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/GenerateText.ts.html |here} to see how to use GenerateText API.
119
119
  */
120
120
  generateText(generateTextRequest: requests.GenerateTextRequest): Promise<responses.GenerateTextResponse | ReadableStream<Uint8Array> | null>;
121
121
  /**
@@ -127,7 +127,7 @@ export declare class GenerativeAiInferenceClient {
127
127
  * @param RerankTextRequest
128
128
  * @return RerankTextResponse
129
129
  * @throws OciError when an error occurs
130
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/RerankText.ts.html |here} to see how to use RerankText API.
130
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/RerankText.ts.html |here} to see how to use RerankText API.
131
131
  */
132
132
  rerankText(rerankTextRequest: requests.RerankTextRequest): Promise<responses.RerankTextResponse>;
133
133
  /**
@@ -137,7 +137,7 @@ export declare class GenerativeAiInferenceClient {
137
137
  * @param SummarizeTextRequest
138
138
  * @return SummarizeTextResponse
139
139
  * @throws OciError when an error occurs
140
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/SummarizeText.ts.html |here} to see how to use SummarizeText API.
140
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/SummarizeText.ts.html |here} to see how to use SummarizeText API.
141
141
  */
142
142
  summarizeText(summarizeTextRequest: requests.SummarizeTextRequest): Promise<responses.SummarizeTextResponse>;
143
143
  }
package/lib/client.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
@@ -199,7 +199,7 @@ class GenerativeAiInferenceClient {
199
199
  * @param ChatRequest
200
200
  * @return ChatResponse
201
201
  * @throws OciError when an error occurs
202
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/Chat.ts.html |here} to see how to use Chat API.
202
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/Chat.ts.html |here} to see how to use Chat API.
203
203
  */
204
204
  chat(chatRequest) {
205
205
  return __awaiter(this, void 0, void 0, function* () {
@@ -270,7 +270,7 @@ class GenerativeAiInferenceClient {
270
270
  * @param EmbedTextRequest
271
271
  * @return EmbedTextResponse
272
272
  * @throws OciError when an error occurs
273
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/EmbedText.ts.html |here} to see how to use EmbedText API.
273
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/EmbedText.ts.html |here} to see how to use EmbedText API.
274
274
  */
275
275
  embedText(embedTextRequest) {
276
276
  return __awaiter(this, void 0, void 0, function* () {
@@ -334,7 +334,7 @@ class GenerativeAiInferenceClient {
334
334
  * @param GenerateTextRequest
335
335
  * @return GenerateTextResponse
336
336
  * @throws OciError when an error occurs
337
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/GenerateText.ts.html |here} to see how to use GenerateText API.
337
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/GenerateText.ts.html |here} to see how to use GenerateText API.
338
338
  */
339
339
  generateText(generateTextRequest) {
340
340
  return __awaiter(this, void 0, void 0, function* () {
@@ -405,7 +405,7 @@ class GenerativeAiInferenceClient {
405
405
  * @param RerankTextRequest
406
406
  * @return RerankTextResponse
407
407
  * @throws OciError when an error occurs
408
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/RerankText.ts.html |here} to see how to use RerankText API.
408
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/RerankText.ts.html |here} to see how to use RerankText API.
409
409
  */
410
410
  rerankText(rerankTextRequest) {
411
411
  return __awaiter(this, void 0, void 0, function* () {
@@ -469,7 +469,7 @@ class GenerativeAiInferenceClient {
469
469
  * @param SummarizeTextRequest
470
470
  * @return SummarizeTextResponse
471
471
  * @throws OciError when an error occurs
472
- * @example Click {@link https://docs.cloud.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/SummarizeText.ts.html |here} to see how to use SummarizeText API.
472
+ * @example Click {@link https://docs.oracle.com/en-us/iaas/tools/typescript-sdk-examples/latest/generativeaiinference/SummarizeText.ts.html |here} to see how to use SummarizeText API.
473
473
  */
474
474
  summarizeText(summarizeTextRequest) {
475
475
  return __awaiter(this, void 0, void 0, function* () {
package/lib/model/assistant-message.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/assistant-message.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/base-chat-request.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/base-chat-request.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/base-chat-response.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/base-chat-response.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/chat-choice.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/chat-choice.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/chat-content.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/chat-content.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/chat-details.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/chat-details.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/chat-result.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/chat-result.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/choice.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *
package/lib/model/choice.js CHANGED
@@ -3,11 +3,11 @@
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](#/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
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
9
9
 
10
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
10
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
11
11
 
12
12
  * OpenAPI spec version: 20231130
13
13
  *
package/lib/model/citation.d.ts CHANGED
@@ -2,11 +2,11 @@
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](#/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).
5
+ Use the Generative AI service inference API to access your custom model endpoints, or to try the out-of-the-box models to {@link #eNGenerative-ai-inferenceLatestChatResultChat(ENGenerative-ai-inferenceLatestChatResultChatRequest) eNGenerative-ai-inferenceLatestChatResultChat}, {@link #eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText(ENGenerative-ai-inferenceLatestGenerateTextResultGenerateTextRequest) eNGenerative-ai-inferenceLatestGenerateTextResultGenerateText}, {@link #eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText(ENGenerative-ai-inferenceLatestSummarizeTextResultSummarizeTextRequest) eNGenerative-ai-inferenceLatestSummarizeTextResultSummarizeText}, and {@link #eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText(ENGenerative-ai-inferenceLatestEmbedTextResultEmbedTextRequest) eNGenerative-ai-inferenceLatestEmbedTextResultEmbedText}.
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](#/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/).
7
+ To use a Generative AI custom model for inference, you must first create an endpoint for that model. Use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest} to {@link #eNGenerative-aiLatestModel(ENGenerative-aiLatestModelRequest) eNGenerative-aiLatestModel} 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 {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster}. Then, create a {@link #eNGenerative-aiLatestDedicatedAiCluster(ENGenerative-aiLatestDedicatedAiClusterRequest) eNGenerative-aiLatestDedicatedAiCluster} with an {@link Endpoint} to host your custom model. For resource management in the Generative AI service, use the {@link #eNGenerative-aiLatest(ENGenerative-aiLatestRequest) eNGenerative-aiLatest}.
8
8
 
9
- To learn more about the service, see the [Generative AI documentation](/iaas/Content/generative-ai/home.htm).
9
+ To learn more about the service, see the [Generative AI documentation](https://docs.oracle.com/iaas/Content/generative-ai/home.htm).
10
10
 
11
11
  * OpenAPI spec version: 20231130
12
12
  *