Change max_tokens type to Option<u32> (#233)

Author: MakotoE

async-openai/src/lib.rs

@@ -58,7 +58,7 @@
 //! let request = CreateCompletionRequestArgs::default()
 //!     .model("gpt-3.5-turbo-instruct")
 //!     .prompt("Tell me the recipe of alfredo pasta")
-//!     .max_tokens(40_u16)
+//!     .max_tokens(40_u32)
 //!     .build()
 //!     .unwrap();
 //!

async-openai/src/types/chat.rs

@@ -420,7 +420,7 @@ pub struct CreateChatCompletionRequest {
     ///
     /// 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.
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub max_tokens: Option<u16>,
+    pub max_tokens: Option<u32>,
 
     /// How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
     #[serde(skip_serializing_if = "Option::is_none")]

async-openai/src/types/completion.rs

@@ -33,7 +33,7 @@ pub struct CreateCompletionRequest {
     ///
     /// The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub max_tokens: Option<u16>,
+    pub max_tokens: Option<u32>,
 
     /// 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.
     ///

async-openai/tests/boxed_future.rs

@@ -32,7 +32,7 @@ async fn boxed_future_test() {
         .prompt("does 2 and 2 add to four? (yes/no):\n")
         .stream(true)
         .logprobs(3)
-        .max_tokens(64_u16)
+        .max_tokens(64_u32)
         .build()
         .unwrap();
 

examples/azure-openai-service/src/main.rs

@@ -11,7 +11,7 @@ use async_openai::{
 
 async fn chat_completion_example(client: &Client<AzureConfig>) -> Result<(), Box<dyn Error>> {
     let request = CreateChatCompletionRequestArgs::default()
-        .max_tokens(512u16)
+        .max_tokens(512u32)
         .model("gpt-3.5-turbo")
         .messages([
             ChatCompletionRequestSystemMessageArgs::default()
@@ -44,7 +44,7 @@ async fn chat_completion_example(client: &Client<AzureConfig>) -> Result<(), Box
 //         .n(1)
 //         .prompt("Tell me a short bedtime story about Optimus Prime and Bumblebee in Sir David Attenborough voice")
 //         .stream(true)
-//         .max_tokens(512_u16)
+//         .max_tokens(512_u32)
 //         .build()?;
 
 //     let mut stream = client.completions().create_stream(request).await?;

examples/chat-stream/src/main.rs

@@ -11,7 +11,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
 
     let request = CreateChatCompletionRequestArgs::default()
         .model("gpt-3.5-turbo")
-        .max_tokens(512u16)
+        .max_tokens(512u32)
         .messages([ChatCompletionRequestUserMessageArgs::default()
             .content("Write a marketing blog praising and introducing Rust library async-openai")
             .build()?

examples/chat/src/main.rs

@@ -13,7 +13,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
     let client = Client::new();
 
     let request = CreateChatCompletionRequestArgs::default()
-        .max_tokens(512u16)
+        .max_tokens(512u32)
         .model("gpt-3.5-turbo")
         .messages([
             ChatCompletionRequestSystemMessageArgs::default()

examples/completions-stream/src/main.rs

@@ -10,7 +10,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
         .n(1)
         .prompt("Tell me a bedtime story about Optimus Prime and Bumblebee")
         .stream(true)
-        .max_tokens(1024_u16)
+        .max_tokens(1024_u32)
         .build()?;
 
     let mut stream = client.completions().create_stream(request).await?;

examples/completions/src/main.rs

@@ -10,7 +10,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
     let request = CreateCompletionRequestArgs::default()
         .model("gpt-3.5-turbo-instruct")
         .prompt("Tell me a joke about the universe")
-        .max_tokens(40_u16)
+        .max_tokens(40_u32)
         .build()?;
 
     let response = client.completions().create(request).await?;
@@ -27,7 +27,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
             "How old is the human civilization?",
             "How old is the Earth?",
         ])
-        .max_tokens(40_u16)
+        .max_tokens(40_u32)
         .build()?;
 
     let response = client.completions().create(request).await?;

examples/function-call-stream/src/main.rs

@@ -19,7 +19,7 @@ async fn main() -> Result<(), Box<dyn Error>> {
     let client = Client::new();
 
     let request = CreateChatCompletionRequestArgs::default()
-        .max_tokens(512u16)
+        .max_tokens(512u32)
         .model("gpt-3.5-turbo-0613")
         .messages([ChatCompletionRequestUserMessageArgs::default()
             .content("What's the weather like in Boston?")
@@ -110,7 +110,7 @@ async fn call_fn(
     ];
 
     let request = CreateChatCompletionRequestArgs::default()
-        .max_tokens(512u16)
+        .max_tokens(512u32)
         .model("gpt-3.5-turbo-0613")
         .messages(message)
         .build()?;