More doctests (#47)

* Update docs

* add -> add_single

* add_many -> add

* More doctests

* fix wasm

Cargo.toml

@@ -56,8 +56,9 @@ fastembed = "4.3.0"
 
 [dev-dependencies]
 wasm-bindgen-test = "0.3"
-tokio = { version = "1", features = ["rt", "macros"] }
 rand = "0.8"
+tokio-test = "0.4"
+
 
 [profile.release]
 # Tell `rustc` to optimize for small code size.

README.md

@@ -67,13 +67,15 @@ let mut victor = Db::new(PathBuf::from("./victor_test_data"));
 victor.clear_db().await.unwrap();
 
 victor
-    .add_many(
+    .add(
         vec!["Pineapple", "Rocks"], // documents
         vec!["Pizza Toppings"],     // tags (only used for filtering)
     )
     .await;
 
-victor.add("Cheese pizza", vec!["Pizza Flavors"]).await; // Add another entry with no tags
+victor
+    .add_single("Cheese pizza", vec!["Pizza Flavors"])
+    .await; // Add another entry with no tags
 
 // read the 10 closest results from victor that are tagged with "Pizza Toppings"
 // (only 2 will be returned because we only inserted two embeddings)

examples/in_memory.rs

@@ -7,13 +7,15 @@ async fn main() {
     victor.clear_db().await.unwrap();
 
     victor
-        .add_many(
+        .add(
             vec!["Pineapple", "Rocks"], // documents
             vec!["Pizza Toppings"],     // tags (only used for filtering)
         )
         .await;
 
-    victor.add("Cheese pizza", vec!["Pizza Flavors"]).await; // Add another entry with no tags
+    victor
+        .add_single("Cheese pizza", vec!["Pizza Flavors"])
+        .await; // Add another entry with no tags
 
     // read the 10 closest results from victor that are tagged with "Pizza Toppings"
     // (only 2 will be returned because we only inserted two embeddings)

examples/native_filesystem.rs

@@ -10,13 +10,15 @@ async fn main() {
     victor.clear_db().await.unwrap();
 
     victor
-        .add_many(
+        .add(
             vec!["Pineapple", "Rocks"], // documents
             vec!["Pizza Toppings"],     // tags (only used for filtering)
         )
         .await;
 
-    victor.add("Cheese pizza", vec!["Pizza Flavors"]).await; // Add another entry with no tags
+    victor
+        .add_single("Cheese pizza", vec!["Pizza Flavors"])
+        .await; // Add another entry with no tags
 
     // read the 10 closest results from victor that are tagged with "Pizza Toppings"
     // (only 2 will be returned because we only inserted two embeddings)

src/db.rs

@@ -19,6 +19,8 @@ use crate::{
     similarity,
 };
 
+/// The main database struct.
+/// Through this you can [`Victor::add`] and [`Victor::search`] for embeddings.
 pub struct Victor<D> {
     root: D,
 }
@@ -72,19 +74,32 @@ extern "C" {
 }
 
 impl<D: DirectoryHandle> Victor<D> {
+    /// Create a new Victor database given a directory handle.
+    ///
+    /// For example, you can use [`std::path::PathBuf`] to use the native filesystem.
+    /// Or you can use [`crate::memory::DirectoryHandle`] to use an in-memory database.
     pub fn new(root: impl Into<D>) -> Self {
         let root = root.into();
         Self { root }
     }
 
     /// Add many documents to the database.
     /// Embeddings will be generated for each document.
+    ///
+    /// ```rust
+    /// # tokio_test::block_on(async {
+    /// # use victor_db::memory::{Db, DirectoryHandle};
+    /// # let mut victor = Db::new(DirectoryHandle::default());
+    /// victor
+    ///     .add(
+    ///         vec!["Pineapple", "Rocks"], // documents
+    ///         vec!["Pizza Toppings"],     // tags (only used for filtering)
+    ///     )
+    ///     .await;
+    /// # })
+    /// ```
     #[cfg(not(target_arch = "wasm32"))]
-    pub async fn add_many(
-        &mut self,
-        content: Vec<impl Into<String>>,
-        tags: Vec<impl Into<String>>,
-    ) {
+    pub async fn add(&mut self, content: Vec<impl Into<String>>, tags: Vec<impl Into<String>>) {
         let tags = tags.into_iter().map(|t| t.into()).collect::<Vec<String>>();
         let model = fastembed::TextEmbedding::try_new(Default::default()).unwrap();
         let content = content
@@ -95,20 +110,36 @@ impl<D: DirectoryHandle> Victor<D> {
         let vectors = model.embed(content.clone(), None).unwrap();
 
         let to_add = content.into_iter().zip(vectors.into_iter()).collect();
-        self.add_embedding_many(to_add, tags).await;
+        self.add_embeddings(to_add, tags).await;
     }
 
     /// Add a single document to the database.
     /// Embedding will be generated for the document.
-    /// When adding many documents, it is more efficient to use `add_many`.
+    /// When adding many documents, it is more efficient to use `add`.
+    ///
+    /// ```rust
+    /// # tokio_test::block_on(async {
+    /// # use victor_db::memory::{Db, DirectoryHandle};
+    /// # let mut victor = Db::new(DirectoryHandle::default());
+    /// victor.add_single("Pepperoni pizza", vec!["Pizza Flavors"]).await;
+    /// # })
+    /// ```
     #[cfg(not(target_arch = "wasm32"))]
-    pub async fn add(&mut self, content: impl Into<String>, tags: Vec<impl Into<String>>) {
-        self.add_many(vec![content], tags).await;
+    pub async fn add_single(&mut self, content: impl Into<String>, tags: Vec<impl Into<String>>) {
+        self.add(vec![content], tags).await;
     }
 
-    /// Add many documen/embedding pairs to the database.
+    /// Add many document/embedding pairs to the database.
     /// This is useful for adding embeddings that have already been generated.
-    pub async fn add_embedding_many(
+    ///
+    /// ```rust
+    /// # tokio_test::block_on(async {
+    /// # use victor_db::memory::{Db, DirectoryHandle};
+    /// # let mut victor = Db::new(DirectoryHandle::default());
+    /// victor.add_embeddings(vec![("Pepperoni pizza", vec![0.1, 0.2, 0.3])], vec!["Pizza Flavors"]).await;
+    /// # })
+    /// ```
+    pub async fn add_embeddings(
         &mut self,
         to_add: Vec<(impl Into<String>, Vec<f32>)>,
         tags: Vec<impl Into<String>>,
@@ -134,19 +165,35 @@ impl<D: DirectoryHandle> Victor<D> {
 
     /// Add a single document/embedding pair to the database.
     /// This is useful for adding embeddings that have already been generated.
-    /// When adding many documents, it is more efficient to use `add_embedding_many`.
-    pub async fn add_embedding(
+    /// When adding many documents, it is more efficient to use `add_embeddings`.
+    ///
+    /// ```rust
+    /// # tokio_test::block_on(async {
+    /// # use victor_db::memory::{Db, DirectoryHandle};
+    /// # let mut victor = Db::new(DirectoryHandle::default());
+    /// victor.add_single_embedding("Pepperoni pizza", vec![0.1, 0.2, 0.3], vec!["Pizza Flavors"]).await;
+    /// # })
+    /// ```
+    pub async fn add_single_embedding(
         &mut self,
         content: impl Into<String>,
         vector: Vec<f32>,
         tags: Vec<impl Into<String>>,
     ) {
-        self.add_embedding_many(vec![(content, vector)], tags).await;
+        self.add_embeddings(vec![(content, vector)], tags).await;
     }
 
     /// Search the database for the nearest neighbors to a given document.
     /// An embedding will be generated for the document being searched for.
     /// This will return the top `top_n` nearest neighbors.
+    ///
+    /// ```rust
+    /// # tokio_test::block_on(async {
+    /// # use victor_db::memory::{Db, DirectoryHandle};
+    /// # let mut victor = Db::new(DirectoryHandle::default());
+    /// victor.search("Pepperoni pizza", vec!["Pizza Flavors"], 10).await;
+    /// # })
+    /// ```
     #[cfg(not(target_arch = "wasm32"))]
     pub async fn search(
         &self,
@@ -557,6 +604,7 @@ impl<D: DirectoryHandle> Victor<D> {
         content.to_string()
     }
 
+    /// Clear the database, deleting all data.
     pub async fn clear_db(&mut self) -> Result<(), D::Error> {
         // clear db files
         let files = Index::get_all_db_filenames(&mut self.root).await?;

src/lib.rs

@@ -1,4 +1,91 @@
-//! A browser-optimized vector database. Backed by the private virtual filesystem API on web. On native, supports running with the native filesystem or in memory.
+//! A browser-optimized vector database. Backed by the private virtual filesystem API on web.
+//!
+//! You're viewing this on crates.io, so you're probably interested in the native version. The native version supports running with the native filesystem or in memory.
+//!
+//! If you want to use it on the web, [check out victor-db on npm](https://www.npmjs.com/package/victor-db).
+//!
+//! ## In-memory database
+//!
+//! Use this if you want to run victor in-memory (all data is lost when the program exits).
+//!
+//! The in-memory version is useful for testing and applications where you don't need to persist data:
+//! ```rust
+//! # tokio_test::block_on(async {
+//! // use victor_db::memory for the in-memory implementation
+//! use victor_db::memory::{Db, DirectoryHandle};
+//!
+//! // create a new in-memory database
+//! let mut victor = Db::new(DirectoryHandle::default());
+//!
+//! // add some embeddings to the database
+//! victor
+//!     .add(
+//!         vec!["Pineapple", "Rocks"], // documents
+//!         vec!["Pizza Toppings"],     // tags (only used for filtering)
+//!     )
+//!     .await;
+//!
+//! // add another embedding to the database, this time with no tags
+//! victor.add_single("Cheese pizza", vec!["Pizza Flavors"]).await;
+//!
+//! // read the 10 closest results from victor that are tagged with "Pizza Toppings"
+//! // (only 2 will be returned because we only inserted two embeddings)
+//! let nearest = victor
+//!     .search("Hawaiian pizza", vec!["Pizza Toppings"], 10)
+//!     .await
+//!     .first()
+//!     .unwrap()
+//!     .content
+//!     .clone();
+//! assert_eq!(nearest, "Pineapple".to_string());
+//!
+//! // Clear the database
+//! victor.clear_db().await.unwrap();
+//! # })
+//! ```
+//!
+//! ## Native database
+//!
+//! Use this if you want to persist your database to disk.
+//!
+//! ```rust
+//! # tokio_test::block_on(async {
+//! // use victor_db::native for the native filesystem implementation
+//! use victor_db::native::Db;
+//! use std::path::PathBuf;
+//!
+//! // create a new native database under "./victor_test_data"
+//! let _ = std::fs::create_dir("./victor_test_data");
+//! let mut victor = Db::new(PathBuf::from("./victor_test_data"));
+//!
+//! // add some embeddings to the database
+//! victor
+//!     .add(
+//!         vec!["Pineapple", "Rocks"], // documents
+//!         vec!["Pizza Toppings"],     // tags (only used for filtering)
+//!     )
+//!     .await;
+//!
+//! // add another embedding to the database, this time with no tags
+//! victor.add_single("Cheese pizza", vec!["Pizza Flavors"]).await;
+//!
+//! // read the 10 closest results from victor that are tagged with "Pizza Toppings"
+//! // (only 2 will be returned because we only inserted two embeddings)
+//! let nearest = victor
+//!     .search("Hawaiian pizza", vec!["Pizza Toppings"], 10)
+//!     .await
+//!     .first()
+//!     .unwrap()
+//!     .content
+//!     .clone();
+//! assert_eq!(nearest, "Pineapple".to_string());
+//!
+//! // Clear the database
+//! victor.clear_db().await.unwrap();
+//! # })
+//! ```
+//!
+//! See the docs for [`Victor`] for more information.
 
 #![deny(missing_docs)]
 
@@ -9,6 +96,9 @@ mod packed_vector;
 mod similarity;
 mod utils;
 
+#[cfg(not(target_arch = "wasm32"))]
+pub use db::Victor;
+
 #[cfg(test)]
 mod tests;
 
@@ -22,7 +112,9 @@ type Victor = crate::db::Victor<filesystem::web::DirectoryHandle>;
 
 // Native
 
-/// Used to tell victor to use the native filesystem.
+/// Victor's native filesystem implementation.
+///
+/// Use this if you want to persist your database to disk.
 #[cfg(not(target_arch = "wasm32"))]
 pub mod native {
     use crate::db::Victor;
@@ -31,7 +123,9 @@ pub mod native {
     pub type Db = Victor<crate::filesystem::native::DirectoryHandle>;
 }
 
-/// Used to tell victor to use an in-memory filesystem.
+/// Victor's in-memory implementation.
+///
+/// Use this if you want to run victor in-memory (all data is lost when the program exits).
 #[cfg(not(target_arch = "wasm32"))]
 pub mod memory {
     use crate::db::Victor;
@@ -105,7 +199,9 @@ impl Db {
             })
             .unwrap_or(vec![]);
 
-        self.victor.add_embedding(content, embedding, tags).await;
+        self.victor
+            .add_single_embedding(content, embedding, tags)
+            .await;
     }
 
     /// Search the database for the nearest neighbors to a given embedding.

src/tests.rs

@@ -7,7 +7,7 @@ async fn store_and_retrieve() {
     let mut victor = Db::new(DirectoryHandle::default());
 
     victor
-        .add_embedding("hello", embedding.clone(), Vec::<String>::new())
+        .add_single_embedding("hello", embedding.clone(), Vec::<String>::new())
         .await;
 
     let result = victor
@@ -29,10 +29,10 @@ async fn store_two_and_retrieve() {
     let mut victor = Db::new(DirectoryHandle::default());
 
     victor
-        .add_embedding("hello", embedding_1.clone(), Vec::<String>::new())
+        .add_single_embedding("hello", embedding_1.clone(), Vec::<String>::new())
         .await;
     victor
-        .add_embedding("goodbye", embedding_2.clone(), Vec::<String>::new())
+        .add_single_embedding("goodbye", embedding_2.clone(), Vec::<String>::new())
         .await;
 
     {
@@ -67,10 +67,10 @@ async fn store_two_and_retrieve_with_tags() {
     let mut victor = Db::new(DirectoryHandle::default());
 
     victor
-        .add_embedding("hello", embedding_1.clone(), vec!["greetings".to_string()])
+        .add_single_embedding("hello", embedding_1.clone(), vec!["greetings".to_string()])
         .await;
     victor
-        .add_embedding("goodbye", embedding_2.clone(), vec!["goodbyes".to_string()])
+        .add_single_embedding("goodbye", embedding_2.clone(), vec!["goodbyes".to_string()])
         .await;
 
     {
@@ -135,19 +135,19 @@ async fn incompatible_size_panic() {
     let mut victor = Db::new(DirectoryHandle::default());
 
     victor
-        .add_embedding("hello", embedding_1, Vec::<String>::new())
+        .add_single_embedding("hello", embedding_1, Vec::<String>::new())
         .await;
     victor
-        .add_embedding("hello", embedding_2, Vec::<String>::new())
+        .add_single_embedding("hello", embedding_2, Vec::<String>::new())
         .await;
 }
 
 #[tokio::test]
-async fn add_many() {
+async fn add() {
     let mut victor = Db::new(DirectoryHandle::default());
 
     victor
-        .add_many(vec!["pineapple", "rocks"], Vec::<String>::new())
+        .add(vec!["pineapple", "rocks"], Vec::<String>::new())
         .await;
 
     let result = victor