update

Author: mrbullwinkle

articles/ai-services/openai/includes/api-versions/latest-inference-preview.md

@@ -40,9 +40,9 @@ Creates a completion for the provided prompt, parameters and chosen model.
 | best_of | integer | Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results can't be streamed.<br><br>When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
 | echo | boolean | Echo back the prompt in addition to the completion<br> | No | False |
 | frequency_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.<br> | No | 0 |
-| logit_bias | object | Modify the likelihood of specified tokens appearing in the completion.<br><br>Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](https://platform.openai.com/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.<br><br>As an example, you can pass `{"50256": -100}` to prevent the <&#124;endoftext&#124;> token from being generated.<br> | No | None |
+| logit_bias | object | Modify the likelihood of specified tokens appearing in the completion.<br><br>Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.<br><br>As an example, you can pass `{"50256": -100}` to prevent the <&#124;endoftext&#124;> token from being generated.<br> | No | None |
 | logprobs | integer | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the five most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.<br><br>The maximum value for `logprobs` is 5.<br> | No | None |
-| max_tokens | integer | The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length.<br> | No | 16 |
+| max_tokens | integer | The maximum number of tokens that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length.<br> | No | 16 |
 | n | integer | How many completions to generate for each prompt.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | seed | integer | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.<br><br>Determinism isn't guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.<br> | No |  |
@@ -265,7 +265,7 @@ Creates a completion for the chat message
 | top_p | number | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.<br><br>We generally recommend altering this or `temperature` but not both.<br> | No | 1 |
 | stream | boolean | If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. | No | False |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens.<br> | No |  |
-| max_tokens | integer | The maximum number of [tokens](/tokenizer) that can be generated in the chat completion.<br><br>The total length of input tokens and generated tokens is limited by the model's context length. | No |  |
+| max_tokens | integer | The maximum number of tokens that can be generated in the chat completion.<br><br>The total length of input tokens and generated tokens is limited by the model's context length. | No |  |
 | max_completion_tokens | integer | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. | No |  |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | frequency_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.<br> | No | 0 |
@@ -4515,9 +4515,9 @@ Information about the content filtering category (hate, sexual, violence, self_h
 | best_of | integer | Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results can't be streamed.<br><br>When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
 | echo | boolean | Echo back the prompt in addition to the completion<br> | No | False |
 | frequency_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.<br> | No | 0 |
-| logit_bias | object | Modify the likelihood of specified tokens appearing in the completion.<br><br>Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](https://platform.openai.com/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.<br><br>As an example, you can pass `{"50256": -100}` to prevent the <&#124;endoftext&#124;> token from being generated.<br> | No | None |
+| logit_bias | object | Modify the likelihood of specified tokens appearing in the completion.<br><br>Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.<br><br>As an example, you can pass `{"50256": -100}` to prevent the <&#124;endoftext&#124;> token from being generated.<br> | No | None |
 | logprobs | integer | Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the five most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.<br><br>The maximum value for `logprobs` is 5.<br> | No | None |
-| max_tokens | integer | The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length. | No | 16 |
+| max_tokens | integer | The maximum number of tokens that can be generated in the completion.<br><br>The token count of your prompt plus `max_tokens` can't exceed the model's context length. | No | 16 |
 | n | integer | How many completions to generate for each prompt.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.<br> | No | 1 |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | seed | integer | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.<br><br>Determinism isn't guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.<br> | No |  |
@@ -4556,7 +4556,7 @@ Represents a completion response from the API. Note: both the streamed and nonst
 | top_p | number | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.<br><br>We generally recommend altering this or `temperature` but not both.<br> | No | 1 |
 | stream | boolean | If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. | No | False |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens.<br> | No |  |
-| max_tokens | integer | The maximum number of [tokens](/tokenizer) that can be generated in the chat completion.<br><br>The total length of input tokens and generated tokens is limited by the model's context length. | No |  |
+| max_tokens | integer | The maximum number of tokens that can be generated in the chat completion.<br><br>The total length of input tokens and generated tokens is limited by the model's context length. | No |  |
 | max_completion_tokens | integer | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. | No |  |
 | presence_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br> | No | 0 |
 | frequency_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.<br> | No | 0 |
@@ -5241,7 +5241,7 @@ on a public Azure OpenAI endpoint call for embeddings.
 | Name | Type | Description | Required | Default |
 |------|------|-------------|----------|---------|
 | type | [onYourDataVectorizationSourceType](#onyourdatavectorizationsourcetype) | Represents the available sources Azure OpenAI On Your Data can use to configure vectorization of data for use with<br>vector search. | Yes |  |
-| endpoint | string | Specifies the resource endpoint URL from which embeddings should be retrieved. It should be in the format of https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/embeddings. The api-version query parameter isn't allowed. | No |  |
+| endpoint | string | Specifies the resource endpoint URL from which embeddings should be retrieved. It should be in the format of `https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/embeddings`. The api-version query parameter isn't allowed. | No |  |
 | authentication | [onYourDataApiKeyAuthenticationOptions](#onyourdataapikeyauthenticationoptions) or [onYourDataAccessTokenAuthenticationOptions](#onyourdataaccesstokenauthenticationoptions) |  | No |  |
 | dimensions | integer | The number of dimensions the embeddings should have. Only supported in `text-embedding-3` and later models. | No |  |
 
@@ -6045,7 +6045,7 @@ Represents an `assistant` that can call the model and use tools.
 | created_at | integer | The Unix timestamp (in seconds) for when the assistant was created. | Yes |  |
 | name | string | The name of the assistant. The maximum length is 256 characters.<br> | Yes |  |
 | description | string | The description of the assistant. The maximum length is 512 characters.<br> | Yes |  |
-| model | string | Deployment ID of the model to use. You can use the [List models](/rest/api/azureopenai/models/list?view=rest-azureopenai-2024-06-01&tabs=HTTP) API to see all of your available models, or see our [Model overview](/azure/ai-services/openai/concepts/models) for descriptions of them.<br> | Yes |  |
+| model | string | Deployment ID of the model to use. You can use the [List models](/rest/api/azureopenai/models/list) API to see all of your available models, or see our [Model overview](/azure/ai-services/openai/concepts/models) for descriptions of them.<br> | Yes |  |
 | instructions | string | The system instructions that the assistant uses. The maximum length is 256,000 characters.<br> | Yes |  |
 | tools | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.<br> | Yes | [] |
 | tool_resources | object | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.<br> | No |  |
@@ -7961,9 +7961,7 @@ to create a message during a run, we emit a `thread.message.created event`, a
 `thread.message.in_progress` event, many `thread.message.delta` events, and finally a
 `thread.message.completed` event.
 
-We may add additional events over time, so we recommend handling unknown events gracefully
-in your code. See the [Assistants API quick start](/docs/assistants/overview) to learn how to
-integrate the Assistants API with streaming.
+We may add additional events over time, so we recommend handling unknown events gracefully in your code. 
 
 
 This component can be one of the following: