chore: fix no lock build warnings and CI timeouts (#2650)

Example CI failures:
- publish build timeout:
https://github.com/lancedb/lancedb/actions/runs/17626482881/job/50084552906
- doc test build timeout:
https://github.com/lancedb/lancedb/actions/runs/17627058590/job/50086456818

.github/workflows/docs_test.yml

@@ -24,7 +24,8 @@ env:
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: ubuntu-24.04
+    runs-on: warp-ubuntu-2204-x64-8x
+    timeout-minutes: 60
     steps:
     - name: Checkout
       uses: actions/checkout@v4
@@ -48,7 +49,6 @@ jobs:
       uses: swatinem/rust-cache@v2
     - name: Build Python
       working-directory: docs/test
-      timeout-minutes: 60
       run:
         python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -r requirements.txt
     - name: Create test files

Cargo.lock

@@ -713,9 +713,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-s3"
-version = "1.104.0"
+version = "1.105.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38c488cd6abb0ec9811c401894191932e941c5f91dc226043edacd0afa1634bc"
+checksum = "c99789e929b5e1d9a5aa3fa1d81317f3a789afc796141d11b0eaafd9d9f47e38"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -963,9 +963,9 @@ dependencies = [
 
 [[package]]
 name = "aws-smithy-runtime"
-version = "1.9.1"
+version = "1.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d3946acbe1ead1301ba6862e712c7903ca9bb230bdf1fbd1b5ac54158ef2ab1f"
+checksum = "4fa63ad37685ceb7762fa4d73d06f1d5493feb88e3f27259b9ed277f4c01b185"
 dependencies = [
  "aws-smithy-async",
  "aws-smithy-http",
@@ -1153,7 +1153,7 @@ dependencies = [
  "bitflags 2.9.4",
  "cexpr",
  "clang-sys",
- "itertools 0.12.1",
+ "itertools 0.11.0",
  "lazy_static",
  "lazycell",
  "log",

java/core/lancedb-jni/src/ffi.rs

@@ -16,6 +16,7 @@ pub trait JNIEnvExt {
     fn get_integers(&mut self, obj: &JObject) -> Result<Vec<i32>>;
 
     /// Get strings from Java List<String> object.
+    #[allow(dead_code)]
     fn get_strings(&mut self, obj: &JObject) -> Result<Vec<String>>;
 
     /// Get strings from Java String[] object.

java/core/lancedb-jni/src/traits.rs

@@ -6,6 +6,7 @@ use jni::JNIEnv;
 
 use crate::Result;
 
+#[allow(dead_code)]
 pub trait FromJObject<T> {
     fn extract(&self) -> Result<T>;
 }
@@ -39,6 +40,7 @@ impl FromJObject<f64> for JObject<'_> {
     }
 }
 
+#[allow(dead_code)]
 pub trait FromJString {
     fn extract(&self, env: &mut JNIEnv) -> Result<String>;
 }
@@ -66,6 +68,7 @@ pub trait JMapExt {
     fn get_f64(&self, env: &mut JNIEnv, key: &str) -> Result<Option<f64>>;
 }
 
+#[allow(dead_code)]
 fn get_map_value<T>(env: &mut JNIEnv, map: &JMap, key: &str) -> Result<Option<T>>
 where
     for<'a> JObject<'a>: FromJObject<T>,

python/src/connection.rs

@@ -255,7 +255,7 @@ impl Connection {
 #[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
-    py: Python,
+    py: Python<'_>,
     uri: String,
     api_key: Option<String>,
     region: Option<String>,

rust/lancedb/Cargo.toml

@@ -86,11 +86,11 @@ rand = { version = "0.9", features = ["small_rng"] }
 random_word = { version = "0.4.3", features = ["en"] }
 uuid = { version = "1.7.0", features = ["v4"] }
 walkdir = "2"
-aws-sdk-dynamodb = { version = "1.38.0" }
+aws-sdk-dynamodb = { version = "1.55.0" }
-aws-sdk-s3 = { version = "1.38.0" }
+aws-sdk-s3 = { version = "1.55.0" }
-aws-sdk-kms = { version = "1.37" }
+aws-sdk-kms = { version = "1.48.0" }
-aws-config = { version = "1.0" }
+aws-config = { version = "1.5.10" }
-aws-smithy-runtime = { version = "1.3" }
+aws-smithy-runtime = { version = "1.9.1" }
 datafusion.workspace = true
 http-body = "1"                                        # Matching reqwest
 rstest = "0.23.0"

rust/lancedb/src/embeddings.rs

@@ -45,10 +45,10 @@ use crate::{
 pub trait EmbeddingFunction: std::fmt::Debug + Send + Sync {
     fn name(&self) -> &str;
     /// The type of the input data
-    fn source_type(&self) -> Result<Cow<DataType>>;
+    fn source_type(&self) -> Result<Cow<'_, DataType>>;
     /// The type of the output data
     /// This should **always** match the output of the `embed` function
-    fn dest_type(&self) -> Result<Cow<DataType>>;
+    fn dest_type(&self) -> Result<Cow<'_, DataType>>;
     /// Compute the embeddings for the source column in the database
     fn compute_source_embeddings(&self, source: Arc<dyn Array>) -> Result<Arc<dyn Array>>;
     /// Compute the embeddings for a given user query

rust/lancedb/src/embeddings/bedrock.rs

@@ -75,11 +75,11 @@ impl EmbeddingFunction for BedrockEmbeddingFunction {
         "bedrock"
     }
 
-    fn source_type(&self) -> Result<Cow<DataType>> {
+    fn source_type(&self) -> Result<Cow<'_, DataType>> {
         Ok(Cow::Owned(DataType::Utf8))
     }
 
-    fn dest_type(&self) -> Result<Cow<DataType>> {
+    fn dest_type(&self) -> Result<Cow<'_, DataType>> {
         let n_dims = self.model.ndims();
         Ok(Cow::Owned(DataType::new_fixed_size_list(
             DataType::Float32,

rust/lancedb/src/embeddings/openai.rs

@@ -144,11 +144,11 @@ impl EmbeddingFunction for OpenAIEmbeddingFunction {
         "openai"
     }
 
-    fn source_type(&self) -> Result<Cow<DataType>> {
+    fn source_type(&self) -> Result<Cow<'_, DataType>> {
         Ok(Cow::Owned(DataType::Utf8))
     }
 
-    fn dest_type(&self) -> Result<Cow<DataType>> {
+    fn dest_type(&self) -> Result<Cow<'_, DataType>> {
         let n_dims = self.model.ndims();
         Ok(Cow::Owned(DataType::new_fixed_size_list(
             DataType::Float32,

rust/lancedb/src/embeddings/sentence_transformers.rs

@@ -407,11 +407,11 @@ impl EmbeddingFunction for SentenceTransformersEmbeddings {
         "sentence-transformers"
     }
 
-    fn source_type(&self) -> crate::Result<std::borrow::Cow<arrow_schema::DataType>> {
+    fn source_type(&self) -> crate::Result<std::borrow::Cow<'_, arrow_schema::DataType>> {
         Ok(Cow::Owned(DataType::Utf8))
     }
 
-    fn dest_type(&self) -> crate::Result<std::borrow::Cow<arrow_schema::DataType>> {
+    fn dest_type(&self) -> crate::Result<std::borrow::Cow<'_, arrow_schema::DataType>> {
         let (n_dims, dtype) = self.compute_ndims_and_dtype()?;
         Ok(Cow::Owned(DataType::new_fixed_size_list(
             dtype,

rust/lancedb/src/table.rs

@@ -242,17 +242,15 @@ pub struct OptimizeStats {
 /// Describes what happens when a vector either contains NaN or
 /// does not have enough values
 #[derive(Clone, Debug, Default)]
+#[allow(dead_code)] // https://github.com/lancedb/lancedb/issues/992
 enum BadVectorHandling {
     /// An error is returned
     #[default]
     Error,
-    #[allow(dead_code)] // https://github.com/lancedb/lancedb/issues/992
     /// The offending row is droppped
     Drop,
-    #[allow(dead_code)] // https://github.com/lancedb/lancedb/issues/992
     /// The invalid/missing items are replaced by fill_value
     Fill(f32),
-    #[allow(dead_code)] // https://github.com/lancedb/lancedb/issues/992
     /// The invalid items are replaced by NULL
     None,
 }

rust/lancedb/tests/embedding_registry_test.rs

@@ -341,10 +341,10 @@ impl EmbeddingFunction for MockEmbed {
     fn name(&self) -> &str {
         &self.name
     }
-    fn source_type(&self) -> Result<Cow<DataType>> {
+    fn source_type(&self) -> Result<Cow<'_, DataType>> {
         Ok(Cow::Borrowed(&self.source_type))
     }
-    fn dest_type(&self) -> Result<Cow<DataType>> {
+    fn dest_type(&self) -> Result<Cow<'_, DataType>> {
         Ok(Cow::Borrowed(&self.dest_type))
     }
     fn compute_source_embeddings(&self, source: Arc<dyn Array>) -> Result<Arc<dyn Array>> {