style: fmt code

rig-core/src/agent.rs

@@ -33,19 +33,19 @@
 //! let chat_response = agent.chat("Prompt", chat_history)
 //!     .await
 //!     .expect("Failed to chat with Agent");
-//! 
+//!
 //! // Generate a prompt completion response from a simple prompt
 //! let chat_response = agent.prompt("Prompt")
 //!     .await
 //!     .expect("Failed to prompt the Agent");
-//! 
+//!
 //! // Generate a completion request builder from a prompt and chat history. The builder
-//! // will contain the agent's configuration (i.e.: preamble, context documents, tools, 
+//! // will contain the agent's configuration (i.e.: preamble, context documents, tools,
 //! // model parameters, etc.), but these can be overwritten.
 //! let completion_req_builder = agent.completion("Prompt", chat_history)
 //!     .await
 //!     .expect("Failed to create completion request builder");
-//! 
+//!
 //! let response = completion_req_builder
 //!     .temperature(0.9) // Overwrite the agent's temperature
 //!     .send()

rig-core/src/cli_chatbot.rs

@@ -2,7 +2,7 @@ use std::io::{self, Write};
 
 use crate::completion::{Chat, Message, PromptError};
 
-/// Utility function to create a simple REPL CLI chatbot from a type that implements the 
+/// Utility function to create a simple REPL CLI chatbot from a type that implements the
 /// `Chat` trait.
 pub async fn cli_chatbot(chatbot: impl Chat) -> Result<(), PromptError> {
     let stdin = io::stdin();

rig-core/src/completion.rs

@@ -133,12 +133,12 @@ pub struct ToolDefinition {
 /// Trait defining a high-level LLM simple prompt interface (i.e.: prompt in, response out).
 pub trait Prompt: Send + Sync {
     /// Send a simple prompt to the underlying completion model.
-    /// 
-    /// If the completion model's response is a message, then it is returned as a string. 
-    /// 
-    /// If the completion model's response is a tool call, then the tool is called and 
+    ///
+    /// If the completion model's response is a message, then it is returned as a string.
+    ///
+    /// If the completion model's response is a tool call, then the tool is called and
     /// the result is returned as a string.
-    /// 
+    ///
     /// If the tool does not exist, or the tool call fails, then an error is returned.
     fn prompt(
         &self,
@@ -149,12 +149,12 @@ pub trait Prompt: Send + Sync {
 /// Trait defining a high-level LLM chat interface (i.e.: prompt and chat history in, response out).
 pub trait Chat: Send + Sync {
     /// Send a prompt with optional chat history to the underlying completion model.
-    /// 
-    /// If the completion model's response is a message, then it is returned as a string. 
-    /// 
-    /// If the completion model's response is a tool call, then the tool is called and the result 
+    ///
+    /// If the completion model's response is a message, then it is returned as a string.
+    ///
+    /// If the completion model's response is a tool call, then the tool is called and the result
     /// is returned as a string.
-    /// 
+    ///
     /// If the tool does not exist, or the tool call fails, then an error is returned.
     fn chat(
         &self,
@@ -242,38 +242,38 @@ pub struct CompletionRequest {
 }
 
 /// Builder struct for constructing a completion request.
-/// 
+///
 /// Example usage:
 /// ```rust
 /// use rig::{
 ///     providers::openai::{Client, self},
 ///     completion::CompletionRequestBuilder,
 /// };
-/// 
+///
 /// let openai = Client::new("your-openai-api-key");
 /// let model = openai.completion_model(openai::GPT_4O).build();
-/// 
+///
 /// // Create the completion request and execute it separately
 /// let request = CompletionRequestBuilder::new(model, "Who are you?".to_string())
 ///     .preamble("You are Marvin from the Hitchhiker's Guide to the Galaxy.".to_string())
 ///     .temperature(0.5)
 ///     .build();
-/// 
+///
 /// let response = model.completion(request)
 ///     .await
 ///     .expect("Failed to get completion response");
 /// ```
-/// 
+///
 /// Alternatively, you can execute the completion request directly from the builder:
 /// ```rust
 /// use rig::{
 ///     providers::openai::{Client, self},
 ///     completion::CompletionRequestBuilder,
 /// };
-/// 
+///
 /// let openai = Client::new("your-openai-api-key");
 /// let model = openai.completion_model(openai::GPT_4O).build();
-/// 
+///
 /// // Create the completion request and execute it directly
 /// let response = CompletionRequestBuilder::new(model, "Who are you?".to_string())
 ///     .preamble("You are Marvin from the Hitchhiker's Guide to the Galaxy.".to_string())
@@ -282,7 +282,7 @@ pub struct CompletionRequest {
 ///     .await
 ///     .expect("Failed to get completion response");
 /// ```
-/// 
+///
 /// Note: It is usually unnecessary to create a completion request builder directly.
 /// Instead, use the [CompletionModel::completion_request] method.
 pub struct CompletionRequestBuilder<M: CompletionModel> {

rig-core/src/embeddings.rs

@@ -134,10 +134,10 @@ impl Embedding {
 ///
 /// The struct is designed to model any kind of documents that can be serialized to JSON
 /// (including a simple string).
-/// 
-/// Moreover, it can hold multiple embeddings for the same document, thus allowing a 
-/// large document to be retrieved from a query that matches multiple smaller and 
-/// distinct text documents. For example, if the document is a textbook, a summary of 
+///
+/// Moreover, it can hold multiple embeddings for the same document, thus allowing a
+/// large document to be retrieved from a query that matches multiple smaller and
+/// distinct text documents. For example, if the document is a textbook, a summary of
 /// each chapter could serve as the book's embeddings.
 #[derive(Clone, Eq, PartialEq, Serialize, Deserialize)]
 pub struct DocumentEmbeddings {

rig-core/src/extractor.rs

@@ -1,6 +1,6 @@
 //! This module provides high-level abstractions for extracting structured data from text using LLMs.
-//! 
-//! Note: The target structure must implement the `serde::Deserialize`, `serde::Serialize`, 
+//!
+//! Note: The target structure must implement the `serde::Deserialize`, `serde::Serialize`,
 //! and `schemars::JsonSchema` traits. Those can be easily derived using the `derive` macro.
 //!
 //! # Example

rig-core/src/model.rs

@@ -1,12 +1,12 @@
 //! This module contains the implementation of the [Model] struct and its builder.
 //!
 //! The [Model] type is the simplest building block for creating an LLM powered application
-//! and can be used to prompt completions from a completion model. This struct acts as a 
-//! thin wrapper around a completion model (i.e.: a struct implementing the 
+//! and can be used to prompt completions from a completion model. This struct acts as a
+//! thin wrapper around a completion model (i.e.: a struct implementing the
 //! [CompletionModel](crate::completion::CompletionModel) trait).
 //!  
 //! The [ModelBuilder] struct provides a builder interface for creating [Model] instances
-//! and allows the user to set the underlying model and other common parameters such as 
+//! and allows the user to set the underlying model and other common parameters such as
 //! the temperature of the model.
 //!
 //! # Example
@@ -28,19 +28,19 @@
 //! let chat_response = agent.chat("Prompt", chat_history)
 //!     .await
 //!     .expect("Failed to chat with model");
-//! 
+//!
 //! // Generate a prompt completion response from a simple prompt
 //! let chat_response = agent.prompt("Prompt")
 //!     .await
 //!     .expect("Failed to prompt the model");
-//! 
+//!
 //! // Generate a completion request builder from a prompt and chat history. The builder
-//! // will contain the model's configuration (i.e.: model parameters, etc.), but these 
+//! // will contain the model's configuration (i.e.: model parameters, etc.), but these
 //! // can be overwritten.
 //! let completion_req_builder = agent.completion("Prompt", chat_history)
 //!     .await
 //!     .expect("Failed to create completion request builder");
-//! 
+//!
 //! let response = completion_req_builder
 //!     .temperature(0.9) // Overwrite the model's temperature
 //!     .send()

rig-mongodb/src/lib.rs

@@ -83,11 +83,11 @@ impl MongoDbVectorStore {
     }
 
     /// Create a new `MongoDbVectorIndex` from an existing `MongoDbVectorStore`.
-    /// 
+    ///
     /// The index (of type "vector") must already exist for the MongoDB collection.
     /// See the MongoDB [documentation](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-type/) for more information on creating indexes.
-    /// 
-    /// An additional filter can be provided to further restrict the documents that are 
+    ///
+    /// An additional filter can be provided to further restrict the documents that are
     /// considered in the search.
     pub fn index<M: EmbeddingModel>(
         &self,