update

Author: mrbullwinkle

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

@@ -42,12 +42,12 @@ Creates a completion for the provided prompt, parameters and chosen model.
 | 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 |
 | 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. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.<br> | No | 16 |
+| 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 |
 | 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 |  |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens. The returned text won't contain the stop sequence.<br> | No |  |
-| stream | boolean | Whether to stream back partial progress. If set, 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).<br> | No | False |
+| stream | boolean | Whether to stream back partial progress. If set, 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.<br> | No | False |
 | suffix | string | The suffix that comes after a completion of inserted text.<br><br>This parameter is only supported for `gpt-3.5-turbo-instruct`.<br> | No | None |
 | temperature | number | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.<br><br>We generally recommend altering this or `top_p` but not both.<br> | No | 1 |
 | 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 |
@@ -263,15 +263,15 @@ Creates a completion for the chat message
 |------|------|-------------|----------|---------|
 | temperature | number | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.<br><br>We generally recommend altering this or `top_p` but not both.<br> | No | 1 |
 | 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).<br> | No | False |
+| 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. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting 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_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 |
 | 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 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> | No | None |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse.<br> | No |  |
-| messages | array | A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb). | Yes |  |
+| messages | array | A list of messages comprising the conversation so far. | Yes |  |
 | data_sources | array |   The configuration entries for Azure OpenAI chat extensions that use them.<br>  This additional specification is only compatible with Azure OpenAI. | No |  |
 | logprobs | boolean | Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. | No | False |
 | top_logprobs | integer | An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. | No |  |
@@ -4517,12 +4517,12 @@ Information about the content filtering category (hate, sexual, violence, self_h
 | 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 |
 | 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. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.<br> | No | 16 |
+| 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 |
 | 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 |  |
 | stop | string or array | Up to four sequences where the API will stop generating further tokens. The returned text won't contain the stop sequence.<br> | No |  |
-| stream | boolean | Whether to stream back partial progress. If set, 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).<br> | No | False |
+| stream | boolean | Whether to stream back partial progress. If set, 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 |
 | suffix | string | The suffix that comes after a completion of inserted text.<br><br>This parameter is only supported for `gpt-3.5-turbo-instruct`.<br> | No | None |
 | temperature | number | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.<br><br>We generally recommend altering this or `top_p` but not both.<br> | No | 1 |
 | 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 |
@@ -4554,15 +4554,15 @@ Represents a completion response from the API. Note: both the streamed and nonst
 |------|------|-------------|----------|---------|
 | temperature | number | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.<br><br>We generally recommend altering this or `top_p` but not both.<br> | No | 1 |
 | 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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).<br> | No | False |
+| 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. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting 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_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 |
 | 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 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> | No | None |
 | user | string | A unique identifier representing your end-user, which can help to monitor and detect abuse.<br> | No |  |
-| messages | array | A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb). | Yes |  |
+| messages | array | A list of messages comprising the conversation so far. | Yes |  |
 | data_sources | array |   The configuration entries for Azure OpenAI chat extensions that use them.<br>  This additional specification is only compatible with Azure OpenAI. | No |  |
 | logprobs | boolean | Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. | No | False |
 | top_logprobs | integer | An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. | No |  |