Bump version: 0.22.0-beta.5 → 0.22.0-beta.6

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **Chores**
- Updated internal library dependencies to the latest beta version for
improved system stability.
- **Tests**
- Added automated tests to validate full-text search functionality on
list-based text fields.
- **Refactor**
- Enhanced the search processing logic to provide robust support for
list-type text data, ensuring more reliable results.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: BubbleCal <bubble-cal@outlook.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.18.3-beta.0"
+current_version = "0.19.0-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/npm-publish.yml

@@ -18,6 +18,7 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/npm-publish.yml
+      - Cargo.toml # Change in dependency frequently breaks builds
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -130,29 +131,24 @@ jobs:
               set -e &&
               apt-get update &&
               apt-get install -y protobuf-compiler pkg-config
-
+          - target: x86_64-unknown-linux-musl
-          # TODO: re-enable x64 musl builds. I could not figure out why, but it
+            # This one seems to need some extra memory
-          # consistently made GHA runners non-responsive at the end of build. Example:
+            host: ubuntu-2404-8x-x64
-          # https://github.com/lancedb/lancedb/actions/runs/13980431071/job/39144319470?pr=2250
+            # https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
-
+            docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
-          # - target: x86_64-unknown-linux-musl
+            features: fp16kernels
-          #   # This one seems to need some extra memory
+            pre_build: |-
-          #   host: ubuntu-2404-8x-x64
+              set -e &&
-          #   # https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
+              apk add protobuf-dev curl &&
-          #   docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
+              ln -s /usr/lib/gcc/x86_64-alpine-linux-musl/14.2.0/crtbeginS.o /usr/lib/crtbeginS.o &&
-          #   features: ","
+              ln -s /usr/lib/libgcc_s.so /usr/lib/libgcc.so &&
-          #   pre_build: |-
+              CC=gcc &&
-          #     set -e &&
+              CXX=g++
-          #     apk add protobuf-dev curl &&
-          #     ln -s /usr/lib/gcc/x86_64-alpine-linux-musl/14.2.0/crtbeginS.o /usr/lib/crtbeginS.o &&
-          #     ln -s /usr/lib/libgcc_s.so /usr/lib/libgcc.so
-
           - target: aarch64-unknown-linux-gnu
             host: ubuntu-2404-8x-x64
             # https://github.com/napi-rs/napi-rs/blob/main/debian-aarch64.Dockerfile
             docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian-aarch64
-            # TODO: enable fp16kernels after https://github.com/lancedb/lance/pull/3559
+            features: "fp16kernels"
-            features: ","
             pre_build: |-
               set -e &&
               apt-get update &&
@@ -170,8 +166,8 @@ jobs:
               set -e &&
               apk add protobuf-dev &&
               rustup target add aarch64-unknown-linux-musl &&
-              export CC="/aarch64-linux-musl-cross/bin/aarch64-linux-musl-gcc" &&
+              export CC_aarch64_unknown_linux_musl=aarch64-linux-musl-gcc &&
-              export CXX="/aarch64-linux-musl-cross/bin/aarch64-linux-musl-g++"
+              export CXX_aarch64_unknown_linux_musl=aarch64-linux-musl-g++
     name: build - ${{ matrix.settings.target }}
     runs-on: ${{ matrix.settings.host }}
     defaults:
@@ -535,6 +531,12 @@ jobs:
           for filename in *.tgz; do
             npm publish $PUBLISH_ARGS $filename
           done
+      - name: Deprecate
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
+        # We need to deprecate the old package to avoid confusion.
+        # Each time we publish a new version, it gets undeprecated.
+        run: npm deprecate vectordb "Use @lancedb/lancedb instead."
       - name: Notify Slack Action
         uses: ravsamhq/notify-slack-action@2.3.0
         if: ${{ always() }}

.github/workflows/pypi-publish.yml

@@ -8,6 +8,7 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/pypi-publish.yml
+      - Cargo.toml # Change in dependency frequently breaks builds
 
 jobs:
   linux:

Cargo.lock

@@ -1816,27 +1816,30 @@ dependencies = [
 
 [[package]]
 name = "datafusion"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eae420e7a5b0b7f1c39364cc76cbcd0f5fdc416b2514ae3847c2676bbd60702a"
+checksum = "914e6f9525599579abbd90b0f7a55afcaaaa40350b9e9ed52563f126dfe45fd3"
 dependencies = [
  "arrow",
- "arrow-array",
  "arrow-ipc",
  "arrow-schema",
  "async-trait",
  "bytes",
  "chrono",
  "datafusion-catalog",
+ "datafusion-catalog-listing",
  "datafusion-common",
  "datafusion-common-runtime",
+ "datafusion-datasource",
  "datafusion-execution",
  "datafusion-expr",
+ "datafusion-expr-common",
  "datafusion-functions",
  "datafusion-functions-aggregate",
  "datafusion-functions-nested",
  "datafusion-functions-table",
  "datafusion-functions-window",
+ "datafusion-macros",
  "datafusion-optimizer",
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
@@ -1844,14 +1847,13 @@ dependencies = [
  "datafusion-physical-plan",
  "datafusion-sql",
  "futures",
- "glob",
  "itertools 0.14.0",
  "log",
  "object_store",
  "parking_lot",
  "rand 0.8.5",
  "regex",
- "sqlparser 0.53.0",
+ "sqlparser 0.54.0",
  "tempfile",
  "tokio",
  "url",
@@ -1860,9 +1862,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-catalog"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f27987bc22b810939e8dfecc55571e9d50355d6ea8ec1c47af8383a76a6d0e1"
+checksum = "998a6549e6ee4ee3980e05590b2960446a56b343ea30199ef38acd0e0b9036e2"
 dependencies = [
  "arrow",
  "async-trait",
@@ -1876,21 +1878,39 @@ dependencies = [
  "itertools 0.14.0",
  "log",
  "parking_lot",
- "sqlparser 0.53.0",
+]
+
+[[package]]
+name = "datafusion-catalog-listing"
+version = "46.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a5ac10096a5b3c0d8a227176c0e543606860842e943594ccddb45cf42a526e43"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-datasource",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "futures",
+ "log",
+ "object_store",
+ "tokio",
 ]
 
 [[package]]
 name = "datafusion-common"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3f6d5b8c9408cc692f7c194b8aa0c0f9b253e065a8d960ad9cdc2a13e697602"
+checksum = "1f53d7ec508e1b3f68bd301cee3f649834fad51eff9240d898a4b2614cfd0a7a"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ipc",
- "arrow-schema",
  "base64 0.22.1",
  "half",
  "hashbrown 0.14.5",
@@ -1899,32 +1919,60 @@ dependencies = [
  "log",
  "object_store",
  "paste",
- "sqlparser 0.53.0",
+ "sqlparser 0.54.0",
  "tokio",
  "web-time",
 ]
 
 [[package]]
 name = "datafusion-common-runtime"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d4603c8e8a4baf77660ab7074cc66fc15cc8a18f2ce9dfadb755fc6ee294e48"
+checksum = "e0fcf41523b22e14cc349b01526e8b9f59206653037f2949a4adbfde5f8cb668"
 dependencies = [
  "log",
  "tokio",
 ]
 
 [[package]]
-name = "datafusion-doc"
+name = "datafusion-datasource"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5bf4bc68623a5cf231eed601ed6eb41f46a37c4d15d11a0bff24cbc8396cd66"
+checksum = "cf7f37ad8b6e88b46c7eeab3236147d32ea64b823544f498455a8d9042839c92"
+dependencies = [
+ "arrow",
+ "async-trait",
+ "bytes",
+ "chrono",
+ "datafusion-catalog",
+ "datafusion-common",
+ "datafusion-common-runtime",
+ "datafusion-execution",
+ "datafusion-expr",
+ "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
+ "datafusion-physical-plan",
+ "futures",
+ "glob",
+ "itertools 0.14.0",
+ "log",
+ "object_store",
+ "rand 0.8.5",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "datafusion-doc"
+version = "46.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7db7a0239fd060f359dc56c6e7db726abaa92babaed2fb2e91c3a8b2fff8b256"
 
 [[package]]
 name = "datafusion-execution"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88b491c012cdf8e051053426013429a76f74ee3c2db68496c79c323ca1084d27"
+checksum = "0938f9e5b6bc5782be4111cdfb70c02b7b5451bf34fd57e4de062a7f7c4e31f1"
 dependencies = [
  "arrow",
  "dashmap",
@@ -1941,9 +1989,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5a181408d4fc5dc22f9252781a8f39f2d0e5d1b33ec9bde242844980a2689c1"
+checksum = "b36c28b00b00019a8695ad7f1a53ee1673487b90322ecbd604e2cf32894eb14f"
 dependencies = [
  "arrow",
  "chrono",
@@ -1956,26 +2004,27 @@ dependencies = [
  "indexmap 2.8.0",
  "paste",
  "serde_json",
- "sqlparser 0.53.0",
+ "sqlparser 0.54.0",
 ]
 
 [[package]]
 name = "datafusion-expr-common"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d1129b48e8534d8c03c6543bcdccef0b55c8ac0c1272a15a56c67068b6eb1885"
+checksum = "18f0a851a436c5a2139189eb4617a54e6a9ccb9edc96c4b3c83b3bb7c58b950e"
 dependencies = [
  "arrow",
  "datafusion-common",
+ "indexmap 2.8.0",
  "itertools 0.14.0",
  "paste",
 ]
 
 [[package]]
 name = "datafusion-functions"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6125874e4856dfb09b59886784fcb74cde5cfc5930b3a80a1a728ef7a010df6b"
+checksum = "e3196e37d7b65469fb79fee4f05e5bb58a456831035f9a38aa5919aeb3298d40"
 dependencies = [
  "arrow",
  "arrow-buffer",
@@ -1989,7 +2038,6 @@ dependencies = [
  "datafusion-expr",
  "datafusion-expr-common",
  "datafusion-macros",
- "hashbrown 0.14.5",
  "hex",
  "itertools 0.14.0",
  "log",
@@ -2003,14 +2051,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f3add7b1d3888e05e7c95f2b281af900ca69ebdcb21069ba679b33bde8b3b9d6"
+checksum = "adfc2d074d5ee4d9354fdcc9283d5b2b9037849237ddecb8942a29144b77ca05"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -2026,9 +2072,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate-common"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e18baa4cfc3d2f144f74148ed68a1f92337f5072b6dde204a0dbbdf3324989c"
+checksum = "1cbceba0f98d921309a9121b702bcd49289d383684cccabf9a92cda1602f3bbb"
 dependencies = [
  "ahash",
  "arrow",
@@ -2039,15 +2085,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-nested"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3ec5ee8cecb0dc370291279673097ddabec03a011f73f30d7f1096457127e03e"
+checksum = "170e27ce4baa27113ddf5f77f1a7ec484b0dbeda0c7abbd4bad3fc609c8ab71a"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
- "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
  "datafusion-execution",
@@ -2063,9 +2106,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-table"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c403ddd473bbb0952ba880008428b3c7febf0ed3ce1eec35a205db20efb2a36"
+checksum = "7d3a06a7f0817ded87b026a437e7e51de7f59d48173b0a4e803aa896a7bd6bb5"
 dependencies = [
  "arrow",
  "async-trait",
@@ -2079,9 +2122,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ab18c2fb835614d06a75f24a9e09136d3a8c12a92d97c95a6af316a1787a9c5"
+checksum = "d6c608b66496a1e05e3d196131eb9bebea579eed1f59e88d962baf3dda853bc6"
 dependencies = [
  "datafusion-common",
  "datafusion-doc",
@@ -2096,9 +2139,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window-common"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a77b73bc15e7d1967121fdc7a55d819bfb9d6c03766a6c322247dce9094a53a4"
+checksum = "da2f9d83348957b4ad0cd87b5cb9445f2651863a36592fe5484d43b49a5f8d82"
 dependencies = [
  "datafusion-common",
  "datafusion-physical-expr-common",
@@ -2106,9 +2149,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-macros"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09369b8d962291e808977cf94d495fd8b5b38647232d7ef562c27ac0f495b0af"
+checksum = "4800e1ff7ecf8f310887e9b54c9c444b8e215ccbc7b21c2f244cfae373b1ece7"
 dependencies = [
  "datafusion-expr",
  "quote",
@@ -2117,9 +2160,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-optimizer"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2403a7e4a84637f3de7d8d4d7a9ccc0cc4be92d89b0161ba3ee5be82f0531c54"
+checksum = "971c51c54cd309001376fae752fb15a6b41750b6d1552345c46afbfb6458801b"
 dependencies = [
  "arrow",
  "chrono",
@@ -2135,15 +2178,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86ff72ac702b62dbf2650c4e1d715ebd3e4aab14e3885e72e8549e250307347c"
+checksum = "e1447c2c6bc8674a16be4786b4abf528c302803fafa186aa6275692570e64d85"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
- "arrow-schema",
  "datafusion-common",
  "datafusion-expr",
  "datafusion-expr-common",
@@ -2160,13 +2200,12 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr-common"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60982b7d684e25579ee29754b4333057ed62e2cc925383c5f0bd8cab7962f435"
+checksum = "69f8c25dcd069073a75b3d2840a79d0f81e64bdd2c05f2d3d18939afb36a7dcb"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-buffer",
  "datafusion-common",
  "datafusion-expr-common",
  "hashbrown 0.14.5",
@@ -2175,12 +2214,11 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-optimizer"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac5e85c189d5238a5cf181a624e450c4cd4c66ac77ca551d6f3ff9080bac90bb"
+checksum = "68da5266b5b9847c11d1b3404ee96b1d423814e1973e1ad3789131e5ec912763"
 dependencies = [
  "arrow",
- "arrow-schema",
  "datafusion-common",
  "datafusion-execution",
  "datafusion-expr",
@@ -2188,22 +2226,18 @@ dependencies = [
  "datafusion-physical-expr",
  "datafusion-physical-expr-common",
  "datafusion-physical-plan",
- "futures",
  "itertools 0.14.0",
  "log",
- "url",
 ]
 
 [[package]]
 name = "datafusion-physical-plan"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c36bf163956d7e2542657c78b3383fdc78f791317ef358a359feffcdb968106f"
+checksum = "88cc160df00e413e370b3b259c8ea7bfbebc134d32de16325950e9e923846b7f"
 dependencies = [
  "ahash",
  "arrow",
- "arrow-array",
- "arrow-buffer",
  "arrow-ord",
  "arrow-schema",
  "async-trait",
@@ -2228,20 +2262,18 @@ dependencies = [
 
 [[package]]
 name = "datafusion-sql"
-version = "45.0.0"
+version = "46.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13caa4daede211ecec53c78b13c503b592794d125f9a3cc3afe992edf9e7f43"
+checksum = "325a212b67b677c0eb91447bf9a11b630f9fc4f62d8e5d145bf859f5a6b29e64"
 dependencies = [
  "arrow",
- "arrow-array",
- "arrow-schema",
  "bigdecimal",
  "datafusion-common",
  "datafusion-expr",
  "indexmap 2.8.0",
  "log",
  "regex",
- "sqlparser 0.53.0",
+ "sqlparser 0.54.0",
 ]
 
 [[package]]
@@ -2687,12 +2719,21 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "rand 0.8.5",
 ]
 
+[[package]]
+name = "fst"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7ab85b9b05e3978cc9a9cf8fea7f01b494e1a09ed3037e16ba39edc7a29eb61a"
+dependencies = [
+ "utf8-ranges",
+]
+
 [[package]]
 name = "funty"
 version = "2.0.0"
@@ -3666,8 +3707,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3726,8 +3767,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3744,8 +3785,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3781,8 +3822,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3798,6 +3839,7 @@ dependencies = [
  "futures",
  "lance-arrow",
  "lance-core",
+ "lance-datagen",
  "lazy_static",
  "log",
  "prost",
@@ -3806,10 +3848,26 @@ dependencies = [
  "tracing",
 ]
 
+[[package]]
+name = "lance-datagen"
+version = "0.25.3"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+dependencies = [
+ "arrow",
+ "arrow-array",
+ "arrow-cast",
+ "arrow-schema",
+ "chrono",
+ "futures",
+ "hex",
+ "rand 0.8.5",
+ "rand_xoshiro",
+]
+
 [[package]]
 name = "lance-encoding"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrayref",
  "arrow",
@@ -3832,6 +3890,7 @@ dependencies = [
  "lance-core",
  "lazy_static",
  "log",
+ "lz4",
  "num-traits",
  "paste",
  "prost",
@@ -3847,8 +3906,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -3882,8 +3941,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3902,6 +3961,7 @@ dependencies = [
  "datafusion-sql",
  "deepsize",
  "dirs",
+ "fst",
  "futures",
  "half",
  "itertools 0.13.0",
@@ -3935,8 +3995,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3974,8 +4034,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow-array",
  "arrow-ord",
@@ -3998,8 +4058,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4038,8 +4098,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "0.25.1"
+version = "0.25.3"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.25.1-beta.3#33634d3b2e8f6a54e63a97721c7fcd31206e999a"
+source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4050,7 +4110,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4137,7 +4197,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-node"
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4162,7 +4222,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4180,7 +4240,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.21.3-beta.0"
+version = "0.22.0-beta.5"
 dependencies = [
  "arrow",
  "env_logger",
@@ -5895,6 +5955,15 @@ dependencies = [
  "rand 0.8.5",
 ]
 
+[[package]]
+name = "rand_xoshiro"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f97cdb2a36ed4183de61b2f824cc45c9f1037f28afe0a322e9fff4c108b5aaa"
+dependencies = [
+ "rand_core 0.6.4",
+]
+
 [[package]]
 name = "random_word"
 version = "0.4.3"
@@ -6781,11 +6850,12 @@ dependencies = [
 
 [[package]]
 name = "sqlparser"
-version = "0.53.0"
+version = "0.54.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05a528114c392209b3264855ad491fcce534b94a38771b0a0b97a79379275ce8"
+checksum = "c66e3b7374ad4a6af849b08b3e7a6eda0edbd82f0fd59b57e22671bf16979899"
 dependencies = [
  "log",
+ "recursive",
  "sqlparser_derive",
 ]
 
@@ -7636,7 +7706,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "458f7a779bf54acc9f347480ac654f68407d3aab21269a6e3c9f922acd9e2da9"
 dependencies = [
  "getrandom 0.3.2",
+ "js-sys",
  "serde",
+ "wasm-bindgen",
 ]
 
 [[package]]

Cargo.toml

@@ -21,16 +21,16 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.25.1", "features" = [
+lance = { "version" = "=0.25.3", "features" = [
     "dynamodb",
-], tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+], tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-io = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-io = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-index = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-index = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-linalg = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-linalg = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-table = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-table = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-testing = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-testing = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-datafusion = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-datafusion = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
-lance-encoding = { version = "=0.25.1", tag = "v0.25.1-beta.3", git = "https://github.com/lancedb/lance.git" }
+lance-encoding = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
 # Note that this one does not include pyarrow
 arrow = { version = "54.1", optional = false }
 arrow-array = "54.1"
@@ -41,12 +41,12 @@ arrow-schema = "54.1"
 arrow-arith = "54.1"
 arrow-cast = "54.1"
 async-trait = "0"
-datafusion = { version = "45.0", default-features = false }
+datafusion = { version = "46.0", default-features = false }
-datafusion-catalog = "45.0"
+datafusion-catalog = "46.0"
-datafusion-common = { version = "45.0", default-features = false }
+datafusion-common = { version = "46.0", default-features = false }
-datafusion-execution = "45.0"
+datafusion-execution = "46.0"
-datafusion-expr = "45.0"
+datafusion-expr = "46.0"
-datafusion-physical-plan = "45.0"
+datafusion-physical-plan = "46.0"
 env_logger = "0.11"
 half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",

docs/src/js/classes/BoostQuery.md

@@ -0,0 +1,75 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / BoostQuery
+
+# Class: BoostQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new BoostQuery()
+
+```ts
+new BoostQuery(
+   positive,
+   negative,
+   negativeBoost): BoostQuery
+```
+
+Creates an instance of BoostQuery.
+
+#### Parameters
+
+* **positive**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
+    The positive query that boosts the relevance score.
+
+* **negative**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
+    The negative query that reduces the relevance score.
+
+* **negativeBoost**: `number`
+    The factor by which the negative query reduces the score.
+
+#### Returns
+
+[`BoostQuery`](BoostQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)
+
+***
+
+### toDict()
+
+```ts
+toDict(): Record<string, unknown>
+```
+
+#### Returns
+
+`Record`&lt;`string`, `unknown`&gt;
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`toDict`](../interfaces/FullTextQuery.md#todict)

docs/src/js/classes/MatchQuery.md

@@ -0,0 +1,83 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MatchQuery
+
+# Class: MatchQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new MatchQuery()
+
+```ts
+new MatchQuery(
+   query,
+   column,
+   boost,
+   fuzziness,
+   maxExpansions): MatchQuery
+```
+
+Creates an instance of MatchQuery.
+
+#### Parameters
+
+* **query**: `string`
+    The text query to search for.
+
+* **column**: `string`
+    The name of the column to search within.
+
+* **boost**: `number` = `1.0`
+    (Optional) The boost factor to influence the relevance score of this query. Default is `1.0`.
+
+* **fuzziness**: `number` = `0`
+    (Optional) The allowed edit distance for fuzzy matching. Default is `0`.
+
+* **maxExpansions**: `number` = `50`
+    (Optional) The maximum number of terms to consider for fuzzy matching. Default is `50`.
+
+#### Returns
+
+[`MatchQuery`](MatchQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)
+
+***
+
+### toDict()
+
+```ts
+toDict(): Record<string, unknown>
+```
+
+#### Returns
+
+`Record`&lt;`string`, `unknown`&gt;
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`toDict`](../interfaces/FullTextQuery.md#todict)

docs/src/js/classes/MultiMatchQuery.md

@@ -0,0 +1,77 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / MultiMatchQuery
+
+# Class: MultiMatchQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new MultiMatchQuery()
+
+```ts
+new MultiMatchQuery(
+   query,
+   columns,
+   boosts): MultiMatchQuery
+```
+
+Creates an instance of MultiMatchQuery.
+
+#### Parameters
+
+* **query**: `string`
+    The text query to search for across multiple columns.
+
+* **columns**: `string`[]
+    An array of column names to search within.
+
+* **boosts**: `number`[] = `...`
+    (Optional) An array of boost factors corresponding to each column. Default is an array of 1.0 for each column.
+    The `boosts` array should have the same length as `columns`. If not provided, all columns will have a default boost of 1.0.
+    If the length of `boosts` is less than `columns`, it will be padded with 1.0s.
+
+#### Returns
+
+[`MultiMatchQuery`](MultiMatchQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)
+
+***
+
+### toDict()
+
+```ts
+toDict(): Record<string, unknown>
+```
+
+#### Returns
+
+`Record`&lt;`string`, `unknown`&gt;
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`toDict`](../interfaces/FullTextQuery.md#todict)

docs/src/js/classes/PhraseQuery.md

@@ -0,0 +1,69 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / PhraseQuery
+
+# Class: PhraseQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Implements
+
+- [`FullTextQuery`](../interfaces/FullTextQuery.md)
+
+## Constructors
+
+### new PhraseQuery()
+
+```ts
+new PhraseQuery(query, column): PhraseQuery
+```
+
+Creates an instance of `PhraseQuery`.
+
+#### Parameters
+
+* **query**: `string`
+    The phrase to search for in the specified column.
+
+* **column**: `string`
+    The name of the column to search within.
+
+#### Returns
+
+[`PhraseQuery`](PhraseQuery.md)
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)
+
+***
+
+### toDict()
+
+```ts
+toDict(): Record<string, unknown>
+```
+
+#### Returns
+
+`Record`&lt;`string`, `unknown`&gt;
+
+#### Implementation of
+
+[`FullTextQuery`](../interfaces/FullTextQuery.md).[`toDict`](../interfaces/FullTextQuery.md#todict)

docs/src/js/classes/Query.md

@@ -206,7 +206,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
 * **options?**: `Partial`<[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)>
 
@@ -309,7 +309,7 @@ nearestToText(query, columns?): Query
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
 * **columns?**: `string`[]
 

docs/src/js/classes/QueryBase.md

@@ -192,7 +192,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
 * **options?**: `Partial`<[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)>
 

docs/src/js/classes/VectorQuery.md

@@ -347,7 +347,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string`
+* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
 
 * **options?**: `Partial`<[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)>
 

docs/src/js/enumerations/FullTextQueryType.md

@@ -0,0 +1,46 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FullTextQueryType
+
+# Enumeration: FullTextQueryType
+
+Enum representing the types of full-text queries supported.
+
+- `Match`: Performs a full-text search for terms in the query string.
+- `MatchPhrase`: Searches for an exact phrase match in the text.
+- `Boost`: Boosts the relevance score of specific terms in the query.
+- `MultiMatch`: Searches across multiple fields for the query terms.
+
+## Enumeration Members
+
+### Boost
+
+```ts
+Boost: "boost";
+```
+
+***
+
+### Match
+
+```ts
+Match: "match";
+```
+
+***
+
+### MatchPhrase
+
+```ts
+MatchPhrase: "match_phrase";
+```
+
+***
+
+### MultiMatch
+
+```ts
+MultiMatch: "multi_match";
+```

docs/src/js/globals.md

@@ -9,12 +9,20 @@
 - [embedding](namespaces/embedding/README.md)
 - [rerankers](namespaces/rerankers/README.md)
 
+## Enumerations
+
+- [FullTextQueryType](enumerations/FullTextQueryType.md)
+
 ## Classes
 
+- [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
+- [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
+- [MultiMatchQuery](classes/MultiMatchQuery.md)
+- [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
 - [RecordBatchIterator](classes/RecordBatchIterator.md)
@@ -33,6 +41,7 @@
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
 - [FtsOptions](interfaces/FtsOptions.md)
+- [FullTextQuery](interfaces/FullTextQuery.md)
 - [FullTextSearchOptions](interfaces/FullTextSearchOptions.md)
 - [HnswPqOptions](interfaces/HnswPqOptions.md)
 - [HnswSqOptions](interfaces/HnswSqOptions.md)

docs/src/js/interfaces/FullTextQuery.md

@@ -0,0 +1,35 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / FullTextQuery
+
+# Interface: FullTextQuery
+
+Represents a full-text query interface.
+This interface defines the structure and behavior for full-text queries,
+including methods to retrieve the query type and convert the query to a dictionary format.
+
+## Methods
+
+### queryType()
+
+```ts
+queryType(): FullTextQueryType
+```
+
+#### Returns
+
+[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
+
+***
+
+### toDict()
+
+```ts
+toDict(): Record<string, unknown>
+```
+
+#### Returns
+
+`Record`&lt;`string`, `unknown`&gt;

docs/src/js/interfaces/QueryExecutionOptions.md

@@ -20,3 +20,13 @@ The maximum number of rows to return in a single batch
 
 Batches may have fewer rows if the underlying data is stored
 in smaller chunks.
+
+***
+
+### timeoutMs?
+
+```ts
+optional timeoutMs: number;
+```
+
+Timeout for query execution in milliseconds

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.18.3-beta.0</version>
+        <version>0.19.0-beta.5</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.18.3-beta.0</version>
+    <version>0.19.0-beta.5</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.18.3-beta.0",
+  "version": "0.19.0-beta.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.18.3-beta.0",
+        "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.5",
-        "@lancedb/vectordb-darwin-x64": "0.18.3-beta.0",
+        "@lancedb/vectordb-darwin-x64": "0.19.0-beta.5",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.18.3-beta.0",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.5",
-        "@lancedb/vectordb-linux-x64-gnu": "0.18.3-beta.0",
+        "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.5",
-        "@lancedb/vectordb-win32-x64-msvc": "0.18.3-beta.0"
+        "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.5"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.18.3-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.0-beta.5.tgz",
-      "integrity": "sha512-dhJ5VlXV2N/L67mIpTSePhb8krX0FyQgpuz3I+4T4vYuU5JEF3cmedQ5TF5+3cGJhZim4PHRYLkfgCyTlxcqUg==",
+      "integrity": "sha512-NuJVGaV4b6XgH3dlkCEquvtGM1cY5sIJE5M/LgJ3HYYvAbco/seBQM5AHTV/7CULoPEY9eQeJZOj9fWP5oQLYQ==",
       "cpu": [
         "arm64"
       ],
@@ -340,9 +340,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.18.3-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.0-beta.5.tgz",
-      "integrity": "sha512-SHqPkuyfe87d5skf9GERzdeu6AKvVIbXMUwl5N+dVrE7HH6qiuP2HvOmiyHS2lJFgo0Ph8jSBVzPDxxtjF36Dg==",
+      "integrity": "sha512-hbadwvQcUgKJfluUHhN+mx+XeFRwTuh9mD0L3Tf3t3BkDTxyHpEG5WNgOpWrh6e1RU6zW54CoCyQuSEaVqGgGw==",
       "cpu": [
         "x64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.18.3-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.0-beta.5.tgz",
-      "integrity": "sha512-ohnWsV1n9cxL5ik/GGL4FdQ04Ff9REELcNb1zgmJYyEfwyc6TH9m5HdySO/1ACPZJiLbML4gSvZ10J0Zyb+2SA==",
+      "integrity": "sha512-fu/EOYLr3mx76/SP4dEgbq0vSYHfuTf68lVl5/tL6eIb1Purz42l22+jNKLJ/S3Plase2SkXdxyY90K2Y/CvSg==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.18.3-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.0-beta.5.tgz",
-      "integrity": "sha512-nhbW2CKaBSUesiYCPBd9fAsDYIJLadlGsrb2gfjODlFy+2Lpnbz6T9SuV7dNqj6KBw+KHhaRhLqta7tyMZm/EA==",
+      "integrity": "sha512-pzb8fl5M8155sc/mEFnKmuh9rCfQohHBlb+j+5qNMe84AyygQ8Me1H3b1h9fOkUPu2Y168zYfuGkjNv4Bjm9eA==",
       "cpu": [
         "x64"
       ],
@@ -379,9 +379,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.18.3-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.0-beta.5.tgz",
-      "integrity": "sha512-VE4TvMdZ7DIrTC8VYylGxEcH4h2UEejSwGX4PxRzrN9QsCQ4m4pOh3L/UguSO3g+Y1QEaGE20iWQoX6wgSEUhA==",
+      "integrity": "sha512-5z6BSfTuZYJdDL2wwRrEQlnfluahzaUH2U7vj3i4ik4zaAwvaYcrjmdYCTLRYhFscUqzxd2pVFHbfRYe+maYzA==",
       "cpu": [
         "x64"
       ],
@@ -1184,9 +1184,10 @@
       }
     },
     "node_modules/axios": {
-      "version": "1.7.7",
+      "version": "1.8.4",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.7.7.tgz",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.8.4.tgz",
-      "integrity": "sha512-S4kL7XrjgBmvdGut0sN3yJxqYzrDOnivkBiN0OFs6hLiUam3UPvswUo0kqGyhqUZGEOytHyumEdXsAkgCOUf3Q==",
+      "integrity": "sha512-eBSYY4Y68NNlHbHBMdeDmKNtDgXWhQsJcGqzO3iLUM0GraQFSS9cVgPX5I9b3lbdFKyYoAEGAZF1DwhTaljNAw==",
+      "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
         "form-data": "^4.0.0",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.18.3-beta.0",
+  "version": "0.19.0-beta.5",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.18.3-beta.0",
+    "@lancedb/vectordb-darwin-x64": "0.19.0-beta.5",
-    "@lancedb/vectordb-darwin-arm64": "0.18.3-beta.0",
+    "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.5",
-    "@lancedb/vectordb-linux-x64-gnu": "0.18.3-beta.0",
+    "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.5",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.18.3-beta.0",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.5",
-    "@lancedb/vectordb-win32-x64-msvc": "0.18.3-beta.0"
+    "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.5"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/table.test.ts

@@ -867,6 +867,44 @@ describe("When creating an index", () => {
   });
 });
 
+describe("When querying a table", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("should throw an error when timeout is reached", async () => {
+    const db = await connect(tmpDir.name);
+    const data = makeArrowTable([
+      { text: "a", vector: [0.1, 0.2] },
+      { text: "b", vector: [0.3, 0.4] },
+    ]);
+    const table = await db.createTable("test", data);
+    await table.createIndex("text", { config: Index.fts() });
+
+    await expect(
+      table.query().where("text != 'a'").toArray({ timeoutMs: 0 }),
+    ).rejects.toThrow("Query timeout");
+
+    await expect(
+      table.query().nearestTo([0.0, 0.0]).toArrow({ timeoutMs: 0 }),
+    ).rejects.toThrow("Query timeout");
+
+    await expect(
+      table.search("a", "fts").toArray({ timeoutMs: 0 }),
+    ).rejects.toThrow("Query timeout");
+
+    await expect(
+      table
+        .query()
+        .nearestToText("a")
+        .nearestTo([0.0, 0.0])
+        .toArrow({ timeoutMs: 0 }),
+    ).rejects.toThrow("Query timeout");
+  });
+});
+
 describe("Read consistency interval", () => {
   let tmpDir: tmp.DirResult;
   beforeEach(() => {
@@ -1266,6 +1304,27 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results[0].text).toBe(data[0].text);
     });
 
+    test("full text index on list", async () => {
+      const db = await connect(tmpDir.name);
+      const data = [
+        { text: ["lance database", "the", "search"], vector: [0.1, 0.2, 0.3] },
+        { text: ["lance database"], vector: [0.4, 0.5, 0.6] },
+        { text: ["lance", "search"], vector: [0.7, 0.8, 0.9] },
+        { text: ["database", "search"], vector: [1.0, 1.1, 1.2] },
+        { text: ["unrelated", "doc"], vector: [1.3, 1.4, 1.5] },
+      ];
+      const table = await db.createTable("test", data);
+      await table.createIndex("text", {
+        config: Index.fts(),
+      });
+
+      const results = await table.search("lance").toArray();
+      expect(results.length).toBe(3);
+
+      const results2 = await table.search('"lance database"').toArray();
+      expect(results2.length).toBe(2);
+    });
+
     test("full text search without positions", async () => {
       const db = await connect(tmpDir.name);
       const data = [

nodejs/lancedb/index.ts

@@ -47,6 +47,12 @@ export {
   QueryExecutionOptions,
   FullTextSearchOptions,
   RecordBatchIterator,
+  FullTextQuery,
+  MatchQuery,
+  PhraseQuery,
+  BoostQuery,
+  MultiMatchQuery,
+  FullTextQueryType,
 } from "./query";
 
 export {

nodejs/lancedb/query.ts

@@ -17,6 +17,7 @@ import {
   VectorQuery as NativeVectorQuery,
 } from "./native";
 import { Reranker } from "./rerankers";
+
 export class RecordBatchIterator implements AsyncIterator<RecordBatch> {
   private promisedInner?: Promise<NativeBatchIterator>;
   private inner?: NativeBatchIterator;
@@ -62,7 +63,7 @@ class RecordBatchIterable<
   // biome-ignore lint/suspicious/noExplicitAny: skip
   [Symbol.asyncIterator](): AsyncIterator<RecordBatch<any>, any, undefined> {
     return new RecordBatchIterator(
-      this.inner.execute(this.options?.maxBatchLength),
+      this.inner.execute(this.options?.maxBatchLength, this.options?.timeoutMs),
     );
   }
 }
@@ -78,6 +79,11 @@ export interface QueryExecutionOptions {
    * in smaller chunks.
    */
   maxBatchLength?: number;
+
+  /**
+   * Timeout for query execution in milliseconds
+   */
+  timeoutMs?: number;
 }
 
 /**
@@ -152,7 +158,7 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
   }
 
   fullTextSearch(
-    query: string,
+    query: string | FullTextQuery,
     options?: Partial<FullTextSearchOptions>,
   ): this {
     let columns: string[] | null = null;
@@ -164,9 +170,18 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
       }
     }
 
-    this.doCall((inner: NativeQueryType) =>
+    this.doCall((inner: NativeQueryType) => {
-      inner.fullTextSearch(query, columns),
+      if (typeof query === "string") {
-    );
+        inner.fullTextSearch({
+          query: query,
+          columns: columns,
+        });
+      } else {
+        // If query is a FullTextQuery object, convert it to a dict
+        const queryObj = query.toDict();
+        inner.fullTextSearch(queryObj);
+      }
+    });
     return this;
   }
 
@@ -273,9 +288,11 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
     options?: Partial<QueryExecutionOptions>,
   ): Promise<NativeBatchIterator> {
     if (this.inner instanceof Promise) {
-      return this.inner.then((inner) => inner.execute(options?.maxBatchLength));
+      return this.inner.then((inner) =>
+        inner.execute(options?.maxBatchLength, options?.timeoutMs),
+      );
     } else {
-      return this.inner.execute(options?.maxBatchLength);
+      return this.inner.execute(options?.maxBatchLength, options?.timeoutMs);
     }
   }
 
@@ -718,8 +735,167 @@ export class Query extends QueryBase<NativeQuery> {
     }
   }
 
-  nearestToText(query: string, columns?: string[]): Query {
+  nearestToText(query: string | FullTextQuery, columns?: string[]): Query {
-    this.doCall((inner) => inner.fullTextSearch(query, columns));
+    this.doCall((inner) => {
+      if (typeof query === "string") {
+        inner.fullTextSearch({
+          query: query,
+          columns: columns,
+        });
+      } else {
+        const queryObj = query.toDict();
+        inner.fullTextSearch(queryObj);
+      }
+    });
     return this;
   }
 }
+
+/**
+ * Enum representing the types of full-text queries supported.
+ *
+ * - `Match`: Performs a full-text search for terms in the query string.
+ * - `MatchPhrase`: Searches for an exact phrase match in the text.
+ * - `Boost`: Boosts the relevance score of specific terms in the query.
+ * - `MultiMatch`: Searches across multiple fields for the query terms.
+ */
+export enum FullTextQueryType {
+  Match = "match",
+  MatchPhrase = "match_phrase",
+  Boost = "boost",
+  MultiMatch = "multi_match",
+}
+
+/**
+ * Represents a full-text query interface.
+ * This interface defines the structure and behavior for full-text queries,
+ * including methods to retrieve the query type and convert the query to a dictionary format.
+ */
+export interface FullTextQuery {
+  queryType(): FullTextQueryType;
+  toDict(): Record<string, unknown>;
+}
+
+export class MatchQuery implements FullTextQuery {
+  /**
+   * Creates an instance of MatchQuery.
+   *
+   * @param query - The text query to search for.
+   * @param column - The name of the column to search within.
+   * @param boost - (Optional) The boost factor to influence the relevance score of this query. Default is `1.0`.
+   * @param fuzziness - (Optional) The allowed edit distance for fuzzy matching. Default is `0`.
+   * @param maxExpansions - (Optional) The maximum number of terms to consider for fuzzy matching. Default is `50`.
+   */
+  constructor(
+    private query: string,
+    private column: string,
+    private boost: number = 1.0,
+    private fuzziness: number = 0,
+    private maxExpansions: number = 50,
+  ) {}
+
+  queryType(): FullTextQueryType {
+    return FullTextQueryType.Match;
+  }
+
+  toDict(): Record<string, unknown> {
+    return {
+      [this.queryType()]: {
+        [this.column]: {
+          query: this.query,
+          boost: this.boost,
+          fuzziness: this.fuzziness,
+          // biome-ignore lint/style/useNamingConvention: use underscore for consistency with the other APIs
+          max_expansions: this.maxExpansions,
+        },
+      },
+    };
+  }
+}
+
+export class PhraseQuery implements FullTextQuery {
+  /**
+   * Creates an instance of `PhraseQuery`.
+   *
+   * @param query - The phrase to search for in the specified column.
+   * @param column - The name of the column to search within.
+   */
+  constructor(
+    private query: string,
+    private column: string,
+  ) {}
+
+  queryType(): FullTextQueryType {
+    return FullTextQueryType.MatchPhrase;
+  }
+
+  toDict(): Record<string, unknown> {
+    return {
+      [this.queryType()]: {
+        [this.column]: this.query,
+      },
+    };
+  }
+}
+
+export class BoostQuery implements FullTextQuery {
+  /**
+   * Creates an instance of BoostQuery.
+   *
+   * @param positive - The positive query that boosts the relevance score.
+   * @param negative - The negative query that reduces the relevance score.
+   * @param negativeBoost - The factor by which the negative query reduces the score.
+   */
+  constructor(
+    private positive: FullTextQuery,
+    private negative: FullTextQuery,
+    private negativeBoost: number,
+  ) {}
+
+  queryType(): FullTextQueryType {
+    return FullTextQueryType.Boost;
+  }
+
+  toDict(): Record<string, unknown> {
+    return {
+      [this.queryType()]: {
+        positive: this.positive.toDict(),
+        negative: this.negative.toDict(),
+        // biome-ignore lint/style/useNamingConvention: use underscore for consistency with the other APIs
+        negative_boost: this.negativeBoost,
+      },
+    };
+  }
+}
+
+export class MultiMatchQuery implements FullTextQuery {
+  /**
+   * Creates an instance of MultiMatchQuery.
+   *
+   * @param query - The text query to search for across multiple columns.
+   * @param columns - An array of column names to search within.
+   * @param boosts - (Optional) An array of boost factors corresponding to each column. Default is an array of 1.0 for each column.
+   *
+   * The `boosts` array should have the same length as `columns`. If not provided, all columns will have a default boost of 1.0.
+   * If the length of `boosts` is less than `columns`, it will be padded with 1.0s.
+   */
+  constructor(
+    private query: string,
+    private columns: string[],
+    private boosts: number[] = columns.map(() => 1.0),
+  ) {}
+
+  queryType(): FullTextQueryType {
+    return FullTextQueryType.MultiMatch;
+  }
+
+  toDict(): Record<string, unknown> {
+    return {
+      [this.queryType()]: {
+        query: this.query,
+        columns: this.columns,
+        boost: this.boosts,
+      },
+    };
+  }
+}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.18.3-beta.0",
+  "version": "0.19.0-beta.5",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.18.3-beta.0",
+	"version": "0.19.0-beta.5",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.18.3-beta.0",
+  "version": "0.19.0-beta.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.18.3-beta.0",
+      "version": "0.19.0-beta.5",
       "cpu": [
         "x64",
         "arm64"
@@ -2304,89 +2304,20 @@
       }
     },
     "node_modules/@babel/code-frame": {
-      "version": "7.23.5",
+      "version": "7.26.2",
-      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.23.5.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
-      "integrity": "sha512-CgH3s1a96LipHCmSUmYFPwY7MNx8C3avkq7i4Wl3cfa662ldtUe4VM1TPXX70pfmrlWTb6jLqTYrZyT2ZTJBgA==",
+      "integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/highlight": "^7.23.4",
+        "@babel/helper-validator-identifier": "^7.25.9",
-        "chalk": "^2.4.2"
+        "js-tokens": "^4.0.0",
+        "picocolors": "^1.0.0"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
-    "node_modules/@babel/code-frame/node_modules/ansi-styles": {
-      "version": "3.2.1",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
-      "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
-      "dev": true,
-      "dependencies": {
-        "color-convert": "^1.9.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/code-frame/node_modules/chalk": {
-      "version": "2.4.2",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
-      "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
-      "dev": true,
-      "dependencies": {
-        "ansi-styles": "^3.2.1",
-        "escape-string-regexp": "^1.0.5",
-        "supports-color": "^5.3.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/code-frame/node_modules/color-convert": {
-      "version": "1.9.3",
-      "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
-      "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
-      "dev": true,
-      "dependencies": {
-        "color-name": "1.1.3"
-      }
-    },
-    "node_modules/@babel/code-frame/node_modules/color-name": {
-      "version": "1.1.3",
-      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
-      "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==",
-      "dev": true
-    },
-    "node_modules/@babel/code-frame/node_modules/escape-string-regexp": {
-      "version": "1.0.5",
-      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
-      "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==",
-      "dev": true,
-      "engines": {
-        "node": ">=0.8.0"
-      }
-    },
-    "node_modules/@babel/code-frame/node_modules/has-flag": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
-      "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==",
-      "dev": true,
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/code-frame/node_modules/supports-color": {
-      "version": "5.5.0",
-      "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
-      "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
-      "dev": true,
-      "dependencies": {
-        "has-flag": "^3.0.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
     "node_modules/@babel/compat-data": {
       "version": "7.23.5",
       "resolved": "https://registry.npmjs.org/@babel/compat-data/-/compat-data-7.23.5.tgz",
@@ -2589,19 +2520,21 @@
       }
     },
     "node_modules/@babel/helper-string-parser": {
-      "version": "7.23.4",
+      "version": "7.25.9",
-      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.23.4.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz",
-      "integrity": "sha512-803gmbQdqwdf4olxrX4AJyFBV/RTr3rSmOj0rKwesmzlfhYNDEs+/iOcznzpNWlJlIlTJC2QfPFcHB6DlzdVLQ==",
+      "integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==",
       "dev": true,
+      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
     },
     "node_modules/@babel/helper-validator-identifier": {
-      "version": "7.22.20",
+      "version": "7.25.9",
-      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.22.20.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz",
-      "integrity": "sha512-Y4OZ+ytlatR8AI+8KZfKuL5urKp7qey08ha31L8b3BwewJAoJamTzyvxPR/5D+KkdJCGPq/+8TukHBlY10FX9A==",
+      "integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==",
       "dev": true,
+      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
@@ -2616,109 +2549,28 @@
       }
     },
     "node_modules/@babel/helpers": {
-      "version": "7.23.8",
+      "version": "7.27.0",
-      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.23.8.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.27.0.tgz",
-      "integrity": "sha512-KDqYz4PiOWvDFrdHLPhKtCThtIcKVy6avWD2oG4GEvyQ+XDZwHD4YQd+H2vNMnq2rkdxsDkU82T+Vk8U/WXHRQ==",
+      "integrity": "sha512-U5eyP/CTFPuNE3qk+WZMxFkp/4zUzdceQlfzf7DdGdhp+Fezd7HD+i8Y24ZuTMKX3wQBld449jijbGq6OdGNQg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/template": "^7.22.15",
+        "@babel/template": "^7.27.0",
-        "@babel/traverse": "^7.23.7",
+        "@babel/types": "^7.27.0"
-        "@babel/types": "^7.23.6"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
-    "node_modules/@babel/highlight": {
-      "version": "7.23.4",
-      "resolved": "https://registry.npmjs.org/@babel/highlight/-/highlight-7.23.4.tgz",
-      "integrity": "sha512-acGdbYSfp2WheJoJm/EBBBLh/ID8KDc64ISZ9DYtBmC8/Q204PZJLHyzeB5qMzJ5trcOkybd78M4x2KWsUq++A==",
-      "dev": true,
-      "dependencies": {
-        "@babel/helper-validator-identifier": "^7.22.20",
-        "chalk": "^2.4.2",
-        "js-tokens": "^4.0.0"
-      },
-      "engines": {
-        "node": ">=6.9.0"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/ansi-styles": {
-      "version": "3.2.1",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
-      "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
-      "dev": true,
-      "dependencies": {
-        "color-convert": "^1.9.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/chalk": {
-      "version": "2.4.2",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
-      "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
-      "dev": true,
-      "dependencies": {
-        "ansi-styles": "^3.2.1",
-        "escape-string-regexp": "^1.0.5",
-        "supports-color": "^5.3.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/color-convert": {
-      "version": "1.9.3",
-      "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
-      "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
-      "dev": true,
-      "dependencies": {
-        "color-name": "1.1.3"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/color-name": {
-      "version": "1.1.3",
-      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
-      "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==",
-      "dev": true
-    },
-    "node_modules/@babel/highlight/node_modules/escape-string-regexp": {
-      "version": "1.0.5",
-      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
-      "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==",
-      "dev": true,
-      "engines": {
-        "node": ">=0.8.0"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/has-flag": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
-      "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==",
-      "dev": true,
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/@babel/highlight/node_modules/supports-color": {
-      "version": "5.5.0",
-      "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
-      "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
-      "dev": true,
-      "dependencies": {
-        "has-flag": "^3.0.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
     "node_modules/@babel/parser": {
-      "version": "7.23.6",
+      "version": "7.27.0",
-      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.23.6.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.27.0.tgz",
-      "integrity": "sha512-Z2uID7YJ7oNvAI20O9X0bblw7Qqs8Q2hFy0R9tAfnfLkp5MW0UH9eUvnDSnFwKZ0AvgS1ucqR4KzvVHgnke1VQ==",
+      "integrity": "sha512-iaepho73/2Pz7w2eMS0Q5f83+0RKI7i4xmiYeBmDzfRVbQtTOG7Ts0S4HzJVsTMGI9keU8rNfuZr8DKfSt7Yyg==",
       "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@babel/types": "^7.27.0"
+      },
       "bin": {
         "parser": "bin/babel-parser.js"
       },
@@ -2904,14 +2756,15 @@
       }
     },
     "node_modules/@babel/template": {
-      "version": "7.22.15",
+      "version": "7.27.0",
-      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.22.15.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.27.0.tgz",
-      "integrity": "sha512-QPErUVm4uyJa60rkI73qneDacvdvzxshT3kksGqlGWYdOTIUOwJ7RDUL8sGqslY1uXWSL6xMFKEXDS3ox2uF0w==",
+      "integrity": "sha512-2ncevenBqXI6qRMukPlXwHKHchC7RyMuu4xv5JBXRfOGVcTy1mXCD12qrp7Jsoxll1EV3+9sE4GugBVRjT2jFA==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/code-frame": "^7.22.13",
+        "@babel/code-frame": "^7.26.2",
-        "@babel/parser": "^7.22.15",
+        "@babel/parser": "^7.27.0",
-        "@babel/types": "^7.22.15"
+        "@babel/types": "^7.27.0"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -2948,14 +2801,14 @@
       }
     },
     "node_modules/@babel/types": {
-      "version": "7.23.6",
+      "version": "7.27.0",
-      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.23.6.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.27.0.tgz",
-      "integrity": "sha512-+uarb83brBzPKN38NX1MkB6vb6+mwvR6amUulqAE7ccQw1pEl+bCia9TbdG1lsnFP7lZySvUn37CHyXQdfTwzg==",
+      "integrity": "sha512-H45s8fVLYjbhFH62dIJ3WtmJ6RSPt/3DRO0ZcT2SUiYiQyz3BLVb9ADEnLl91m74aQPS3AzzeajZHYOalWe3bg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/helper-string-parser": "^7.23.4",
+        "@babel/helper-string-parser": "^7.25.9",
-        "@babel/helper-validator-identifier": "^7.22.20",
+        "@babel/helper-validator-identifier": "^7.25.9"
-        "to-fast-properties": "^2.0.0"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -5550,10 +5403,11 @@
       "devOptional": true
     },
     "node_modules/axios": {
-      "version": "1.7.7",
+      "version": "1.8.4",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.7.7.tgz",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.8.4.tgz",
-      "integrity": "sha512-S4kL7XrjgBmvdGut0sN3yJxqYzrDOnivkBiN0OFs6hLiUam3UPvswUo0kqGyhqUZGEOytHyumEdXsAkgCOUf3Q==",
+      "integrity": "sha512-eBSYY4Y68NNlHbHBMdeDmKNtDgXWhQsJcGqzO3iLUM0GraQFSS9cVgPX5I9b3lbdFKyYoAEGAZF1DwhTaljNAw==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
         "form-data": "^4.0.0",
@@ -7869,7 +7723,8 @@
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz",
       "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==",
-      "dev": true
+      "dev": true,
+      "license": "MIT"
     },
     "node_modules/js-yaml": {
       "version": "3.14.1",
@@ -9360,15 +9215,6 @@
       "integrity": "sha512-3f0uOEAQwIqGuWW2MVzYg8fV/QNnc/IpuJNG837rLuczAaLVHslWHZQj4IGiEl5Hs3kkbhwL9Ab7Hrsmuj+Smw==",
       "dev": true
     },
-    "node_modules/to-fast-properties": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/to-fast-properties/-/to-fast-properties-2.0.0.tgz",
-      "integrity": "sha512-/OaKK0xYrs3DmxRYqL/yDc+FxFUVYhDlXMhRmv3z915w2HF1tnN1omB354j8VUGO/hbRzyD6Y3sA7v7GS/ceog==",
-      "dev": true,
-      "engines": {
-        "node": ">=4"
-      }
-    },
     "node_modules/to-regex-range": {
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.18.3-beta.0",
+  "version": "0.19.0-beta.5",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -29,6 +29,7 @@
         "aarch64-apple-darwin",
         "x86_64-unknown-linux-gnu",
         "aarch64-unknown-linux-gnu",
+        "x86_64-unknown-linux-musl",
         "aarch64-unknown-linux-musl",
         "x86_64-pc-windows-msvc",
         "aarch64-pc-windows-msvc"

nodejs/src/query.rs

@@ -3,7 +3,7 @@
 
 use std::sync::Arc;
 
-use lancedb::index::scalar::FullTextSearchQuery;
+use lancedb::index::scalar::{FtsQuery, FullTextSearchQuery, MatchQuery, PhraseQuery};
 use lancedb::query::ExecutableQuery;
 use lancedb::query::Query as LanceDbQuery;
 use lancedb::query::QueryBase;
@@ -18,7 +18,7 @@ use crate::error::NapiErrorExt;
 use crate::iterator::RecordBatchIterator;
 use crate::rerankers::Reranker;
 use crate::rerankers::RerankerCallbacks;
-use crate::util::parse_distance_type;
+use crate::util::{parse_distance_type, parse_fts_query};
 
 #[napi]
 pub struct Query {
@@ -38,9 +38,53 @@ impl Query {
     }
 
     #[napi]
-    pub fn full_text_search(&mut self, query: String, columns: Option<Vec<String>>) {
+    pub fn full_text_search(&mut self, query: napi::JsUnknown) -> napi::Result<()> {
-        let query = FullTextSearchQuery::new(query).columns(columns);
+        let query = unsafe { query.cast::<napi::JsObject>() };
+        let query = if let Some(query_text) = query.get::<_, String>("query").transpose() {
+            let mut query_text = query_text?;
+            let columns = query.get::<_, Option<Vec<String>>>("columns")?.flatten();
+
+            let is_phrase =
+                query_text.len() >= 2 && query_text.starts_with('"') && query_text.ends_with('"');
+            let is_multi_match = columns.as_ref().map(|cols| cols.len() > 1).unwrap_or(false);
+
+            if is_phrase {
+                // Remove the surrounding quotes for phrase queries
+                query_text = query_text[1..query_text.len() - 1].to_string();
+            }
+
+            let query: FtsQuery = match (is_phrase, is_multi_match) {
+                (false, _) => MatchQuery::new(query_text).into(),
+                (true, false) => PhraseQuery::new(query_text).into(),
+                (true, true) => {
+                    return Err(napi::Error::from_reason(
+                        "Phrase queries cannot be used with multiple columns.",
+                    ));
+                }
+            };
+            let mut query = FullTextSearchQuery::new_query(query);
+            if let Some(cols) = columns {
+                if !cols.is_empty() {
+                    query = query.with_columns(&cols).map_err(|e| {
+                        napi::Error::from_reason(format!(
+                            "Failed to set full text search columns: {}",
+                            e
+                        ))
+                    })?;
+                }
+            }
+            query
+        } else if let Some(query) = query.get::<_, napi::JsObject>("query")? {
+            let query = parse_fts_query(&query)?;
+            FullTextSearchQuery::new_query(query)
+        } else {
+            return Err(napi::Error::from_reason(
+                "Invalid full text search query object".to_string(),
+            ));
+        };
+
         self.inner = self.inner.clone().full_text_search(query);
+        Ok(())
     }
 
     #[napi]
@@ -87,11 +131,15 @@ impl Query {
     pub async fn execute(
         &self,
         max_batch_length: Option<u32>,
+        timeout_ms: Option<u32>,
     ) -> napi::Result<RecordBatchIterator> {
         let mut execution_opts = QueryExecutionOptions::default();
         if let Some(max_batch_length) = max_batch_length {
             execution_opts.max_batch_length = max_batch_length;
         }
+        if let Some(timeout_ms) = timeout_ms {
+            execution_opts.timeout = Some(std::time::Duration::from_millis(timeout_ms as u64))
+        }
         let inner_stream = self
             .inner
             .execute_with_options(execution_opts)
@@ -195,9 +243,53 @@ impl VectorQuery {
     }
 
     #[napi]
-    pub fn full_text_search(&mut self, query: String, columns: Option<Vec<String>>) {
+    pub fn full_text_search(&mut self, query: napi::JsUnknown) -> napi::Result<()> {
-        let query = FullTextSearchQuery::new(query).columns(columns);
+        let query = unsafe { query.cast::<napi::JsObject>() };
+        let query = if let Some(query_text) = query.get::<_, String>("query").transpose() {
+            let mut query_text = query_text?;
+            let columns = query.get::<_, Option<Vec<String>>>("columns")?.flatten();
+
+            let is_phrase =
+                query_text.len() >= 2 && query_text.starts_with('"') && query_text.ends_with('"');
+            let is_multi_match = columns.as_ref().map(|cols| cols.len() > 1).unwrap_or(false);
+
+            if is_phrase {
+                // Remove the surrounding quotes for phrase queries
+                query_text = query_text[1..query_text.len() - 1].to_string();
+            }
+
+            let query: FtsQuery = match (is_phrase, is_multi_match) {
+                (false, _) => MatchQuery::new(query_text).into(),
+                (true, false) => PhraseQuery::new(query_text).into(),
+                (true, true) => {
+                    return Err(napi::Error::from_reason(
+                        "Phrase queries cannot be used with multiple columns.",
+                    ));
+                }
+            };
+            let mut query = FullTextSearchQuery::new_query(query);
+            if let Some(cols) = columns {
+                if !cols.is_empty() {
+                    query = query.with_columns(&cols).map_err(|e| {
+                        napi::Error::from_reason(format!(
+                            "Failed to set full text search columns: {}",
+                            e
+                        ))
+                    })?;
+                }
+            }
+            query
+        } else if let Some(query) = query.get::<_, napi::JsObject>("query")? {
+            let query = parse_fts_query(&query)?;
+            FullTextSearchQuery::new_query(query)
+        } else {
+            return Err(napi::Error::from_reason(
+                "Invalid full text search query object".to_string(),
+            ));
+        };
+
         self.inner = self.inner.clone().full_text_search(query);
+        Ok(())
     }
 
     #[napi]
@@ -242,11 +334,15 @@ impl VectorQuery {
     pub async fn execute(
         &self,
         max_batch_length: Option<u32>,
+        timeout_ms: Option<u32>,
     ) -> napi::Result<RecordBatchIterator> {
         let mut execution_opts = QueryExecutionOptions::default();
         if let Some(max_batch_length) = max_batch_length {
             execution_opts.max_batch_length = max_batch_length;
         }
+        if let Some(timeout_ms) = timeout_ms {
+            execution_opts.timeout = Some(std::time::Duration::from_millis(timeout_ms as u64))
+        }
         let inner_stream = self
             .inner
             .execute_with_options(execution_opts)

nodejs/src/util.rs

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+use lancedb::index::scalar::{BoostQuery, FtsQuery, MatchQuery, MultiMatchQuery, PhraseQuery};
 use lancedb::DistanceType;
 
 pub fn parse_distance_type(distance_type: impl AsRef<str>) -> napi::Result<DistanceType> {
@@ -15,3 +16,144 @@ pub fn parse_distance_type(distance_type: impl AsRef<str>) -> napi::Result<Dista
         ))),
     }
 }
+
+pub fn parse_fts_query(query: &napi::JsObject) -> napi::Result<FtsQuery> {
+    let query_type = query
+        .get_property_names()?
+        .get_element::<napi::JsString>(0)?;
+    let query_type = query_type.into_utf8()?.into_owned()?;
+    let query_value =
+        query
+            .get::<_, napi::JsObject>(&query_type)?
+            .ok_or(napi::Error::from_reason(format!(
+                "query value {} not found",
+                query_type
+            )))?;
+
+    match query_type.as_str() {
+        "match" => {
+            let column = query_value
+                .get_property_names()?
+                .get_element::<napi::JsString>(0)?
+                .into_utf8()?
+                .into_owned()?;
+            let params =
+                query_value
+                    .get::<_, napi::JsObject>(&column)?
+                    .ok_or(napi::Error::from_reason(format!(
+                        "column {} not found",
+                        column
+                    )))?;
+
+            let query = params
+                .get::<_, napi::JsString>("query")?
+                .ok_or(napi::Error::from_reason("query not found"))?
+                .into_utf8()?
+                .into_owned()?;
+            let boost = params
+                .get::<_, napi::JsNumber>("boost")?
+                .ok_or(napi::Error::from_reason("boost not found"))?
+                .get_double()? as f32;
+            let fuzziness = params
+                .get::<_, napi::JsNumber>("fuzziness")?
+                .map(|f| f.get_uint32())
+                .transpose()?;
+            let max_expansions = params
+                .get::<_, napi::JsNumber>("max_expansions")?
+                .ok_or(napi::Error::from_reason("max_expansions not found"))?
+                .get_uint32()? as usize;
+
+            let query = MatchQuery::new(query)
+                .with_column(Some(column))
+                .with_boost(boost)
+                .with_fuzziness(fuzziness)
+                .with_max_expansions(max_expansions);
+            Ok(query.into())
+        }
+
+        "match_phrase" => {
+            let column = query_value
+                .get_property_names()?
+                .get_element::<napi::JsString>(0)?
+                .into_utf8()?
+                .into_owned()?;
+            let query = query_value
+                .get::<_, napi::JsString>(&column)?
+                .ok_or(napi::Error::from_reason(format!(
+                    "column {} not found",
+                    column
+                )))?
+                .into_utf8()?
+                .into_owned()?;
+
+            let query = PhraseQuery::new(query).with_column(Some(column));
+            Ok(query.into())
+        }
+
+        "boost" => {
+            let positive = query_value
+                .get::<_, napi::JsObject>("positive")?
+                .ok_or(napi::Error::from_reason("positive not found"))?;
+
+            let negative = query_value
+                .get::<_, napi::JsObject>("negative")?
+                .ok_or(napi::Error::from_reason("negative not found"))?;
+            let negative_boost = query_value
+                .get::<_, napi::JsNumber>("negative_boost")?
+                .ok_or(napi::Error::from_reason("negative_boost not found"))?
+                .get_double()? as f32;
+
+            let positive = parse_fts_query(&positive)?;
+            let negative = parse_fts_query(&negative)?;
+            let query = BoostQuery::new(positive, negative, Some(negative_boost));
+            Ok(query.into())
+        }
+
+        "multi_match" => {
+            let query = query_value
+                .get::<_, napi::JsString>("query")?
+                .ok_or(napi::Error::from_reason("query not found"))?
+                .into_utf8()?
+                .into_owned()?;
+            let columns_array = query_value
+                .get::<_, napi::JsTypedArray>("columns")?
+                .ok_or(napi::Error::from_reason("columns not found"))?;
+            let columns_num = columns_array.get_array_length()?;
+            let mut columns = Vec::with_capacity(columns_num as usize);
+            for i in 0..columns_num {
+                let column = columns_array
+                    .get_element::<napi::JsString>(i)?
+                    .into_utf8()?
+                    .into_owned()?;
+                columns.push(column);
+            }
+            let boost_array = query_value
+                .get::<_, napi::JsTypedArray>("boost")?
+                .ok_or(napi::Error::from_reason("boost not found"))?;
+            if boost_array.get_array_length()? != columns_num {
+                return Err(napi::Error::from_reason(format!(
+                    "boost array length ({}) does not match columns length ({})",
+                    boost_array.get_array_length()?,
+                    columns_num
+                )));
+            }
+            let mut boost = Vec::with_capacity(columns_num as usize);
+            for i in 0..columns_num {
+                let b = boost_array.get_element::<napi::JsNumber>(i)?.get_double()? as f32;
+                boost.push(b);
+            }
+
+            let query =
+                MultiMatchQuery::try_new_with_boosts(query, columns, boost).map_err(|e| {
+                    napi::Error::from_reason(format!("Error creating MultiMatchQuery: {}", e))
+                })?;
+
+            Ok(query.into())
+        }
+
+        _ => Err(napi::Error::from_reason(format!(
+            "Unsupported query type: {}",
+            query_type
+        ))),
+    }
+}

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.0-beta.0"
+current_version = "0.22.0-beta.6"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.22.0-beta.0"
+version = "0.22.0-beta.6"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -4,11 +4,12 @@ name = "lancedb"
 dynamic = ["version"]
 dependencies = [
     "deprecation",
-    "tqdm>=4.27.0",
+    "numpy",
+    "overrides>=0.7",
+    "packaging",
     "pyarrow>=14",
     "pydantic>=1.10",
-    "packaging",
+    "tqdm>=4.27.0",
-    "overrides>=0.7",
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
@@ -55,6 +56,7 @@ tests = [
     "tantivy",
     "pyarrow-stubs",
     "pylance>=0.23.2",
+    "requests",
 ]
 dev = [
     "ruff",

python/python/lancedb/_lancedb.pyi

@@ -1,3 +1,4 @@
+from datetime import timedelta
 from typing import Dict, List, Optional, Tuple, Any, Union, Literal
 
 import pyarrow as pa
@@ -94,7 +95,9 @@ class Query:
     def postfilter(self): ...
     def nearest_to(self, query_vec: pa.Array) -> VectorQuery: ...
     def nearest_to_text(self, query: dict) -> FTSQuery: ...
-    async def execute(self, max_batch_length: Optional[int]) -> RecordBatchStream: ...
+    async def execute(
+        self, max_batch_length: Optional[int], timeout: Optional[timedelta]
+    ) -> RecordBatchStream: ...
     async def explain_plan(self, verbose: Optional[bool]) -> str: ...
     async def analyze_plan(self) -> str: ...
     def to_query_request(self) -> PyQueryRequest: ...
@@ -110,7 +113,9 @@ class FTSQuery:
     def get_query(self) -> str: ...
     def add_query_vector(self, query_vec: pa.Array) -> None: ...
     def nearest_to(self, query_vec: pa.Array) -> HybridQuery: ...
-    async def execute(self, max_batch_length: Optional[int]) -> RecordBatchStream: ...
+    async def execute(
+        self, max_batch_length: Optional[int], timeout: Optional[timedelta]
+    ) -> RecordBatchStream: ...
     def to_query_request(self) -> PyQueryRequest: ...
 
 class VectorQuery:

python/python/lancedb/embeddings/voyageai.py

@@ -1,9 +1,12 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
+import base64
-
 import os
-from typing import ClassVar, TYPE_CHECKING, List, Union
+from typing import ClassVar, TYPE_CHECKING, List, Union, Any
+
+from pathlib import Path
+from urllib.parse import urlparse
+from io import BytesIO
 
 import numpy as np
 import pyarrow as pa
@@ -11,12 +14,100 @@ import pyarrow as pa
 from ..util import attempt_import_or_raise
 from .base import EmbeddingFunction
 from .registry import register
-from .utils import api_key_not_found_help, IMAGES
+from .utils import api_key_not_found_help, IMAGES, TEXT
 
 if TYPE_CHECKING:
     import PIL
 
 
+def is_valid_url(text):
+    try:
+        parsed = urlparse(text)
+        return bool(parsed.scheme) and bool(parsed.netloc)
+    except Exception:
+        return False
+
+
+def transform_input(input_data: Union[str, bytes, Path]):
+    PIL = attempt_import_or_raise("PIL", "pillow")
+    if isinstance(input_data, str):
+        if is_valid_url(input_data):
+            content = {"type": "image_url", "image_url": input_data}
+        else:
+            content = {"type": "text", "text": input_data}
+    elif isinstance(input_data, PIL.Image.Image):
+        buffered = BytesIO()
+        input_data.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        content = {
+            "type": "image_base64",
+            "image_base64": "data:image/jpeg;base64," + img_str,
+        }
+    elif isinstance(input_data, bytes):
+        img = PIL.Image.open(BytesIO(input_data))
+        buffered = BytesIO()
+        img.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        content = {
+            "type": "image_base64",
+            "image_base64": "data:image/jpeg;base64," + img_str,
+        }
+    elif isinstance(input_data, Path):
+        img = PIL.Image.open(input_data)
+        buffered = BytesIO()
+        img.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        content = {
+            "type": "image_base64",
+            "image_base64": "data:image/jpeg;base64," + img_str,
+        }
+    else:
+        raise ValueError("Each input should be either str, bytes, Path or Image.")
+
+    return {"content": [content]}
+
+
+def sanitize_multimodal_input(inputs: Union[TEXT, IMAGES]) -> List[Any]:
+    """
+    Sanitize the input to the embedding function.
+    """
+    PIL = attempt_import_or_raise("PIL", "pillow")
+    if isinstance(inputs, (str, bytes, Path, PIL.Image.Image)):
+        inputs = [inputs]
+    elif isinstance(inputs, pa.Array):
+        inputs = inputs.to_pylist()
+    elif isinstance(inputs, pa.ChunkedArray):
+        inputs = inputs.combine_chunks().to_pylist()
+    else:
+        raise ValueError(
+            f"Input type {type(inputs)} not allowed with multimodal model."
+        )
+
+    if not all(isinstance(x, (str, bytes, Path, PIL.Image.Image)) for x in inputs):
+        raise ValueError("Each input should be either str, bytes, Path or Image.")
+
+    return [transform_input(i) for i in inputs]
+
+
+def sanitize_text_input(inputs: TEXT) -> List[str]:
+    """
+    Sanitize the input to the embedding function.
+    """
+    if isinstance(inputs, str):
+        inputs = [inputs]
+    elif isinstance(inputs, pa.Array):
+        inputs = inputs.to_pylist()
+    elif isinstance(inputs, pa.ChunkedArray):
+        inputs = inputs.combine_chunks().to_pylist()
+    else:
+        raise ValueError(f"Input type {type(inputs)} not allowed with text model.")
+
+    if not all(isinstance(x, str) for x in inputs):
+        raise ValueError("Each input should be str.")
+
+    return inputs
+
+
 @register("voyageai")
 class VoyageAIEmbeddingFunction(EmbeddingFunction):
     """
@@ -74,6 +165,11 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
     ]
     multimodal_embedding_models: list = ["voyage-multimodal-3"]
 
+    def _is_multimodal_model(self, model_name: str):
+        return (
+            model_name in self.multimodal_embedding_models or "multimodal" in model_name
+        )
+
     def ndims(self):
         if self.name == "voyage-3-lite":
             return 512
@@ -85,55 +181,12 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
             "voyage-finance-2",
             "voyage-multilingual-2",
             "voyage-law-2",
+            "voyage-multimodal-3",
         ]:
             return 1024
         else:
             raise ValueError(f"Model {self.name} not supported")
 
-    def sanitize_input(self, images: IMAGES) -> Union[List[bytes], np.ndarray]:
-        """
-        Sanitize the input to the embedding function.
-        """
-        if isinstance(images, (str, bytes)):
-            images = [images]
-        elif isinstance(images, pa.Array):
-            images = images.to_pylist()
-        elif isinstance(images, pa.ChunkedArray):
-            images = images.combine_chunks().to_pylist()
-        return images
-
-    def generate_text_embeddings(self, text: str, **kwargs) -> np.ndarray:
-        """
-        Get the embeddings for the given texts
-
-        Parameters
-        ----------
-        texts: list[str] or np.ndarray (of str)
-            The texts to embed
-        input_type: Optional[str]
-
-        truncation: Optional[bool]
-        """
-        client = VoyageAIEmbeddingFunction._get_client()
-        if self.name in self.text_embedding_models:
-            rs = client.embed(texts=[text], model=self.name, **kwargs)
-        elif self.name in self.multimodal_embedding_models:
-            rs = client.multimodal_embed(inputs=[[text]], model=self.name, **kwargs)
-        else:
-            raise ValueError(
-                f"Model {self.name} not supported to generate text embeddings"
-            )
-
-        return rs.embeddings[0]
-
-    def generate_image_embedding(
-        self, image: "PIL.Image.Image", **kwargs
-    ) -> np.ndarray:
-        rs = VoyageAIEmbeddingFunction._get_client().multimodal_embed(
-            inputs=[[image]], model=self.name, **kwargs
-        )
-        return rs.embeddings[0]
-
     def compute_query_embeddings(
         self, query: Union[str, "PIL.Image.Image"], *args, **kwargs
     ) -> List[np.ndarray]:
@@ -144,23 +197,52 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
         ----------
         query : Union[str, PIL.Image.Image]
             The query to embed. A query can be either text or an image.
+
+        Returns
+        -------
+            List[np.array]: the list of embeddings
         """
-        if isinstance(query, str):
+        client = VoyageAIEmbeddingFunction._get_client()
-            return [self.generate_text_embeddings(query, input_type="query")]
+        if self._is_multimodal_model(self.name):
+            result = client.multimodal_embed(
+                inputs=[[query]], model=self.name, input_type="query", **kwargs
+            )
         else:
-            PIL = attempt_import_or_raise("PIL", "pillow")
+            result = client.embed(
-            if isinstance(query, PIL.Image.Image):
+                texts=[query], model=self.name, input_type="query", **kwargs
-                return [self.generate_image_embedding(query, input_type="query")]
+            )
-            else:
+
-                raise TypeError("Only text PIL images supported as query")
+        return [result.embeddings[0]]
 
     def compute_source_embeddings(
-        self, images: IMAGES, *args, **kwargs
+        self, inputs: Union[TEXT, IMAGES], *args, **kwargs
     ) -> List[np.array]:
-        images = self.sanitize_input(images)
+        """
-        return [
+        Compute the embeddings for the inputs
-            self.generate_image_embedding(img, input_type="document") for img in images
+
-        ]
+        Parameters
+        ----------
+        inputs : Union[TEXT, IMAGES]
+            The inputs to embed. The input can be either str, bytes, Path (to an image),
+            PIL.Image or list of these.
+
+        Returns
+        -------
+            List[np.array]: the list of embeddings
+        """
+        client = VoyageAIEmbeddingFunction._get_client()
+        if self._is_multimodal_model(self.name):
+            inputs = sanitize_multimodal_input(inputs)
+            result = client.multimodal_embed(
+                inputs=inputs, model=self.name, input_type="document", **kwargs
+            )
+        else:
+            inputs = sanitize_text_input(inputs)
+            result = client.embed(
+                texts=inputs, model=self.name, input_type="document", **kwargs
+            )
+
+        return result.embeddings
 
     @staticmethod
     def _get_client():

python/python/lancedb/query.py

@@ -4,7 +4,10 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
+import abc
 from concurrent.futures import ThreadPoolExecutor
+from enum import Enum
+from datetime import timedelta
 from typing import (
     TYPE_CHECKING,
     Dict,
@@ -83,6 +86,213 @@ def ensure_vector_query(
         return val
 
 
+class FullTextQueryType(Enum):
+    MATCH = "match"
+    MATCH_PHRASE = "match_phrase"
+    BOOST = "boost"
+    MULTI_MATCH = "multi_match"
+
+
+class FullTextQuery(abc.ABC, pydantic.BaseModel):
+    @abc.abstractmethod
+    def query_type(self) -> FullTextQueryType:
+        """
+        Get the query type of the query.
+
+        Returns
+        -------
+        str
+            The type of the query.
+        """
+
+    @abc.abstractmethod
+    def to_dict(self) -> dict:
+        """
+        Convert the query to a dictionary.
+
+        Returns
+        -------
+        dict
+            The query as a dictionary.
+        """
+
+
+class MatchQuery(FullTextQuery):
+    query: str
+    column: str
+    boost: float = 1.0
+    fuzziness: int = 0
+    max_expansions: int = 50
+
+    def __init__(
+        self,
+        query: str,
+        column: str,
+        *,
+        boost: float = 1.0,
+        fuzziness: int = 0,
+        max_expansions: int = 50,
+    ):
+        """
+        Match query for full-text search.
+
+        Parameters
+        ----------
+        query : str
+            The query string to match against.
+        column : str
+            The name of the column to match against.
+        boost : float, default 1.0
+            The boost factor for the query.
+            The score of each matching document is multiplied by this value.
+        fuzziness : int, optional
+            The maximum edit distance for each term in the match query.
+            Defaults to 0 (exact match).
+            If None, fuzziness is applied automatically by the rules:
+                - 0 for terms with length <= 2
+                - 1 for terms with length <= 5
+                - 2 for terms with length > 5
+        max_expansions : int, optional
+            The maximum number of terms to consider for fuzzy matching.
+            Defaults to 50.
+        """
+        super().__init__(
+            query=query,
+            column=column,
+            boost=boost,
+            fuzziness=fuzziness,
+            max_expansions=max_expansions,
+        )
+
+    def query_type(self) -> FullTextQueryType:
+        return FullTextQueryType.MATCH
+
+    def to_dict(self) -> dict:
+        return {
+            "match": {
+                self.column: {
+                    "query": self.query,
+                    "boost": self.boost,
+                    "fuzziness": self.fuzziness,
+                    "max_expansions": self.max_expansions,
+                }
+            }
+        }
+
+
+class PhraseQuery(FullTextQuery):
+    query: str
+    column: str
+
+    def __init__(self, query: str, column: str):
+        """
+        Phrase query for full-text search.
+
+        Parameters
+        ----------
+        query : str
+            The query string to match against.
+        column : str
+            The name of the column to match against.
+        """
+        super().__init__(query=query, column=column)
+
+    def query_type(self) -> FullTextQueryType:
+        return FullTextQueryType.MATCH_PHRASE
+
+    def to_dict(self) -> dict:
+        return {
+            "match_phrase": {
+                self.column: self.query,
+            }
+        }
+
+
+class BoostQuery(FullTextQuery):
+    positive: FullTextQuery
+    negative: FullTextQuery
+    negative_boost: float = 0.5
+
+    def __init__(
+        self,
+        positive: FullTextQuery,
+        negative: FullTextQuery,
+        *,
+        negative_boost: float = 0.5,
+    ):
+        """
+        Boost query for full-text search.
+
+        Parameters
+        ----------
+        positive : dict
+            The positive query object.
+        negative : dict
+            The negative query object.
+        negative_boost : float
+            The boost factor for the negative query.
+        """
+        super().__init__(
+            positive=positive, negative=negative, negative_boost=negative_boost
+        )
+
+    def query_type(self) -> FullTextQueryType:
+        return FullTextQueryType.BOOST
+
+    def to_dict(self) -> dict:
+        return {
+            "boost": {
+                "positive": self.positive.to_dict(),
+                "negative": self.negative.to_dict(),
+                "negative_boost": self.negative_boost,
+            }
+        }
+
+
+class MultiMatchQuery(FullTextQuery):
+    query: str
+    columns: list[str]
+    boosts: list[float]
+
+    def __init__(
+        self,
+        query: str,
+        columns: list[str],
+        *,
+        boosts: Optional[list[float]] = None,
+    ):
+        """
+        Multi-match query for full-text search.
+
+        Parameters
+        ----------
+        query : str | list[Query]
+            If a string, the query string to match against.
+
+        columns : list[str]
+            The list of columns to match against.
+
+        boosts : list[float], optional
+            The list of boost factors for each column. If not provided,
+            all columns will have the same boost factor.
+        """
+        if boosts is None:
+            boosts = [1.0] * len(columns)
+        super().__init__(query=query, columns=columns, boosts=boosts)
+
+    def query_type(self) -> FullTextQueryType:
+        return FullTextQueryType.MULTI_MATCH
+
+    def to_dict(self) -> dict:
+        return {
+            "multi_match": {
+                "query": self.query,
+                "columns": self.columns,
+                "boost": self.boosts,
+            }
+        }
+
+
 class FullTextSearchQuery(pydantic.BaseModel):
     """A LanceDB Full Text Search Query
 
@@ -92,18 +302,13 @@ class FullTextSearchQuery(pydantic.BaseModel):
         The columns to search
 
         If None, then the table should select the column automatically.
-    query: str
+    query: str | FullTextQuery
-        The query to search for
+        If a string, it is treated as a MatchQuery.
-    limit: Optional[int] = None
+        If a FullTextQuery object, it is used directly.
-        The limit on the number of results to return
-    wand_factor: Optional[float] = None
-        The wand factor to use for the search
     """
 
     columns: Optional[List[str]] = None
-    query: str
+    query: Union[str, FullTextQuery]
-    limit: Optional[int] = None
-    wand_factor: Optional[float] = None
 
 
 class Query(pydantic.BaseModel):
@@ -357,7 +562,7 @@ class LanceQueryBuilder(ABC):
                 table, query, vector_column_name, fts_columns=fts_columns
             )
 
-        if isinstance(query, str):
+        if isinstance(query, (str, FullTextQuery)):
             # fts
             return LanceFtsQueryBuilder(
                 table,
@@ -382,8 +587,10 @@ class LanceQueryBuilder(ABC):
         # If query_type is fts, then query must be a string.
         # otherwise raise TypeError
         if query_type == "fts":
-            if not isinstance(query, str):
+            if not isinstance(query, (str, FullTextQuery)):
-                raise TypeError(f"'fts' queries must be a string: {type(query)}")
+                raise TypeError(
+                    f"'fts' query must be a string or FullTextQuery: {type(query)}"
+                )
             return query, query_type
         elif query_type == "vector":
             query = cls._query_to_vector(table, query, vector_column_name)
@@ -444,7 +651,12 @@ class LanceQueryBuilder(ABC):
         """
         return self.to_pandas()
 
-    def to_pandas(self, flatten: Optional[Union[int, bool]] = None) -> "pd.DataFrame":
+    def to_pandas(
+        self,
+        flatten: Optional[Union[int, bool]] = None,
+        *,
+        timeout: Optional[timedelta] = None,
+    ) -> "pd.DataFrame":
         """
         Execute the query and return the results as a pandas DataFrame.
         In addition to the selected columns, LanceDB also returns a vector
@@ -458,12 +670,15 @@ class LanceQueryBuilder(ABC):
             If flatten is an integer, flatten the nested columns up to the
             specified depth.
             If unspecified, do not flatten the nested columns.
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
         """
-        tbl = flatten_columns(self.to_arrow(), flatten)
+        tbl = flatten_columns(self.to_arrow(timeout=timeout), flatten)
         return tbl.to_pandas()
 
     @abstractmethod
-    def to_arrow(self) -> pa.Table:
+    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
         """
         Execute the query and return the results as an
         [Apache Arrow Table](https://arrow.apache.org/docs/python/generated/pyarrow.Table.html#pyarrow.Table).
@@ -471,34 +686,65 @@ class LanceQueryBuilder(ABC):
         In addition to the selected columns, LanceDB also returns a vector
         and also the "_distance" column which is the distance between the query
         vector and the returned vectors.
+
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
         """
         raise NotImplementedError
 
     @abstractmethod
-    def to_batches(self, /, batch_size: Optional[int] = None) -> pa.RecordBatchReader:
+    def to_batches(
+        self,
+        /,
+        batch_size: Optional[int] = None,
+        *,
+        timeout: Optional[timedelta] = None,
+    ) -> pa.RecordBatchReader:
         """
         Execute the query and return the results as a pyarrow
         [RecordBatchReader](https://arrow.apache.org/docs/python/generated/pyarrow.RecordBatchReader.html)
+
+        Parameters
+        ----------
+        batch_size: int
+            The maximum number of selected records in a RecordBatch object.
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
         """
         raise NotImplementedError
 
-    def to_list(self) -> List[dict]:
+    def to_list(self, *, timeout: Optional[timedelta] = None) -> List[dict]:
         """
         Execute the query and return the results as a list of dictionaries.
 
         Each list entry is a dictionary with the selected column names as keys,
         or all table columns if `select` is not called. The vector and the "_distance"
         fields are returned whether or not they're explicitly selected.
-        """
-        return self.to_arrow().to_pylist()
 
-    def to_pydantic(self, model: Type[LanceModel]) -> List[LanceModel]:
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
+        """
+        return self.to_arrow(timeout=timeout).to_pylist()
+
+    def to_pydantic(
+        self, model: Type[LanceModel], *, timeout: Optional[timedelta] = None
+    ) -> List[LanceModel]:
         """Return the table as a list of pydantic models.
 
         Parameters
         ----------
         model: Type[LanceModel]
             The pydantic model to use.
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
 
         Returns
         -------
@@ -506,19 +752,25 @@ class LanceQueryBuilder(ABC):
         """
         return [
             model(**{k: v for k, v in row.items() if k in model.field_names()})
-            for row in self.to_arrow().to_pylist()
+            for row in self.to_arrow(timeout=timeout).to_pylist()
         ]
 
-    def to_polars(self) -> "pl.DataFrame":
+    def to_polars(self, *, timeout: Optional[timedelta] = None) -> "pl.DataFrame":
         """
         Execute the query and return the results as a Polars DataFrame.
         In addition to the selected columns, LanceDB also returns a vector
         and also the "_distance" column which is the distance between the query
         vector and the returned vector.
+
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
         """
         import polars as pl
 
-        return pl.from_arrow(self.to_arrow())
+        return pl.from_arrow(self.to_arrow(timeout=timeout))
 
     def limit(self, limit: Union[int, None]) -> Self:
         """Set the maximum number of results to return.
@@ -712,13 +964,14 @@ class LanceQueryBuilder(ABC):
         """
         raise NotImplementedError
 
-    def text(self, text: str) -> Self:
+    def text(self, text: str | FullTextQuery) -> Self:
         """Set the text to search for.
 
         Parameters
         ----------
-        text: str
+        text: str | FullTextQuery
-            The text to search for.
+            If a string, it is treated as a MatchQuery.
+            If a FullTextQuery object, it is used directly.
 
         Returns
         -------
@@ -932,7 +1185,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         self._refine_factor = refine_factor
         return self
 
-    def to_arrow(self) -> pa.Table:
+    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
         """
         Execute the query and return the results as an
         [Apache Arrow Table](https://arrow.apache.org/docs/python/generated/pyarrow.Table.html#pyarrow.Table).
@@ -940,8 +1193,14 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         In addition to the selected columns, LanceDB also returns a vector
         and also the "_distance" column which is the distance between the query
         vector and the returned vectors.
+
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
         """
-        return self.to_batches().read_all()
+        return self.to_batches(timeout=timeout).read_all()
 
     def to_query_object(self) -> Query:
         """
@@ -971,7 +1230,13 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
             bypass_vector_index=self._bypass_vector_index,
         )
 
-    def to_batches(self, /, batch_size: Optional[int] = None) -> pa.RecordBatchReader:
+    def to_batches(
+        self,
+        /,
+        batch_size: Optional[int] = None,
+        *,
+        timeout: Optional[timedelta] = None,
+    ) -> pa.RecordBatchReader:
         """
         Execute the query and return the result as a RecordBatchReader object.
 
@@ -979,6 +1244,9 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         ----------
         batch_size: int
             The maximum number of selected records in a RecordBatch object.
+        timeout: timedelta, default None
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
 
         Returns
         -------
@@ -988,7 +1256,9 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         if isinstance(vector[0], np.ndarray):
             vector = [v.tolist() for v in vector]
         query = self.to_query_object()
-        result_set = self._table._execute_query(query, batch_size)
+        result_set = self._table._execute_query(
+            query, batch_size=batch_size, timeout=timeout
+        )
         if self._reranker is not None:
             rs_table = result_set.read_all()
             result_set = self._reranker.rerank_vector(self._str_query, rs_table)
@@ -1084,7 +1354,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
     def __init__(
         self,
         table: "Table",
-        query: str,
+        query: str | FullTextQuery,
         ordering_field_name: Optional[str] = None,
         fts_columns: Optional[Union[str, List[str]]] = None,
     ):
@@ -1127,7 +1397,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
             offset=self._offset,
         )
 
-    def to_arrow(self) -> pa.Table:
+    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
         path, fs, exist = self._table._get_fts_index_path()
         if exist:
             return self.tantivy_to_arrow()
@@ -1139,14 +1409,16 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
                 "Use tantivy-based index instead for now."
             )
         query = self.to_query_object()
-        results = self._table._execute_query(query)
+        results = self._table._execute_query(query, timeout=timeout)
         results = results.read_all()
         if self._reranker is not None:
             results = self._reranker.rerank_fts(self._query, results)
             check_reranker_result(results)
         return results
 
-    def to_batches(self, /, batch_size: Optional[int] = None):
+    def to_batches(
+        self, /, batch_size: Optional[int] = None, timeout: Optional[timedelta] = None
+    ):
         raise NotImplementedError("to_batches on an FTS query")
 
     def tantivy_to_arrow(self) -> pa.Table:
@@ -1251,8 +1523,8 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
 
 
 class LanceEmptyQueryBuilder(LanceQueryBuilder):
-    def to_arrow(self) -> pa.Table:
+    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
-        return self.to_batches().read_all()
+        return self.to_batches(timeout=timeout).read_all()
 
     def to_query_object(self) -> Query:
         return Query(
@@ -1263,9 +1535,11 @@ class LanceEmptyQueryBuilder(LanceQueryBuilder):
             offset=self._offset,
         )
 
-    def to_batches(self, /, batch_size: Optional[int] = None) -> pa.RecordBatchReader:
+    def to_batches(
+        self, /, batch_size: Optional[int] = None, timeout: Optional[timedelta] = None
+    ) -> pa.RecordBatchReader:
         query = self.to_query_object()
-        return self._table._execute_query(query, batch_size)
+        return self._table._execute_query(query, batch_size=batch_size, timeout=timeout)
 
     def rerank(self, reranker: Reranker) -> LanceEmptyQueryBuilder:
         """Rerank the results using the specified reranker.
@@ -1298,7 +1572,7 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
     def __init__(
         self,
         table: "Table",
-        query: Optional[str] = None,
+        query: Optional[Union[str, FullTextQuery]] = None,
         vector_column: Optional[str] = None,
         fts_columns: Optional[Union[str, List[str]]] = None,
     ):
@@ -1328,8 +1602,8 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
         text_query = text or query
         if text_query is None:
             raise ValueError("Text query must be provided for hybrid search.")
-        if not isinstance(text_query, str):
+        if not isinstance(text_query, (str, FullTextQuery)):
-            raise ValueError("Text query must be a string")
+            raise ValueError("Text query must be a string or FullTextQuery")
 
         return vector_query, text_query
 
@@ -1353,7 +1627,7 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
     def to_query_object(self) -> Query:
         raise NotImplementedError("to_query_object not yet supported on a hybrid query")
 
-    def to_arrow(self) -> pa.Table:
+    def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
         vector_query, fts_query = self._validate_query(
             self._query, self._vector, self._text
         )
@@ -1396,9 +1670,11 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
             self._reranker = RRFReranker()
 
         with ThreadPoolExecutor() as executor:
-            fts_future = executor.submit(self._fts_query.with_row_id(True).to_arrow)
+            fts_future = executor.submit(
+                self._fts_query.with_row_id(True).to_arrow, timeout=timeout
+            )
             vector_future = executor.submit(
-                self._vector_query.with_row_id(True).to_arrow
+                self._vector_query.with_row_id(True).to_arrow, timeout=timeout
             )
             fts_results = fts_future.result()
             vector_results = vector_future.result()
@@ -1485,7 +1761,9 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
 
         return results
 
-    def to_batches(self):
+    def to_batches(
+        self, /, batch_size: Optional[int] = None, timeout: Optional[timedelta] = None
+    ):
         raise NotImplementedError("to_batches not yet supported on a hybrid query")
 
     @staticmethod
@@ -1691,7 +1969,7 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
         self._vector = vector
         return self
 
-    def text(self, text: str) -> LanceHybridQueryBuilder:
+    def text(self, text: str | FullTextQuery) -> LanceHybridQueryBuilder:
         self._text = text
         return self
 
@@ -1849,7 +2127,10 @@ class AsyncQueryBase(object):
         return self
 
     async def to_batches(
-        self, *, max_batch_length: Optional[int] = None
+        self,
+        *,
+        max_batch_length: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
         """
         Execute the query and return the results as an Apache Arrow RecordBatchReader.
@@ -1862,34 +2143,56 @@ class AsyncQueryBase(object):
             If not specified, a default batch length is used.
             It is possible for batches to be smaller than the provided length if the
             underlying data is stored in smaller chunks.
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If not specified, no timeout is applied. If the query does not
+            complete within the specified time, an error will be raised.
         """
-        return AsyncRecordBatchReader(await self._inner.execute(max_batch_length))
+        return AsyncRecordBatchReader(
+            await self._inner.execute(max_batch_length, timeout)
+        )
 
-    async def to_arrow(self) -> pa.Table:
+    async def to_arrow(self, timeout: Optional[timedelta] = None) -> pa.Table:
         """
         Execute the query and collect the results into an Apache Arrow Table.
 
         This method will collect all results into memory before returning.  If
         you expect a large number of results, you may want to use
         [to_batches][lancedb.query.AsyncQueryBase.to_batches]
+
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If not specified, no timeout is applied. If the query does not
+            complete within the specified time, an error will be raised.
         """
-        batch_iter = await self.to_batches()
+        batch_iter = await self.to_batches(timeout=timeout)
         return pa.Table.from_batches(
             await batch_iter.read_all(), schema=batch_iter.schema
         )
 
-    async def to_list(self) -> List[dict]:
+    async def to_list(self, timeout: Optional[timedelta] = None) -> List[dict]:
         """
         Execute the query and return the results as a list of dictionaries.
 
         Each list entry is a dictionary with the selected column names as keys,
         or all table columns if `select` is not called. The vector and the "_distance"
         fields are returned whether or not they're explicitly selected.
+
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If not specified, no timeout is applied. If the query does not
+            complete within the specified time, an error will be raised.
         """
-        return (await self.to_arrow()).to_pylist()
+        return (await self.to_arrow(timeout=timeout)).to_pylist()
 
     async def to_pandas(
-        self, flatten: Optional[Union[int, bool]] = None
+        self,
+        flatten: Optional[Union[int, bool]] = None,
+        timeout: Optional[timedelta] = None,
     ) -> "pd.DataFrame":
         """
         Execute the query and collect the results into a pandas DataFrame.
@@ -1918,10 +2221,19 @@ class AsyncQueryBase(object):
             If flatten is an integer, flatten the nested columns up to the
             specified depth.
             If unspecified, do not flatten the nested columns.
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If not specified, no timeout is applied. If the query does not
+            complete within the specified time, an error will be raised.
         """
-        return (flatten_columns(await self.to_arrow(), flatten)).to_pandas()
+        return (
+            flatten_columns(await self.to_arrow(timeout=timeout), flatten)
+        ).to_pandas()
 
-    async def to_polars(self) -> "pl.DataFrame":
+    async def to_polars(
+        self,
+        timeout: Optional[timedelta] = None,
+    ) -> "pl.DataFrame":
         """
         Execute the query and collect the results into a Polars DataFrame.
 
@@ -1930,6 +2242,13 @@ class AsyncQueryBase(object):
         [to_batches][lancedb.query.AsyncQueryBase.to_batches] and convert each batch to
         polars separately.
 
+        Parameters
+        ----------
+        timeout: Optional[timedelta]
+            The maximum time to wait for the query to complete.
+            If not specified, no timeout is applied. If the query does not
+            complete within the specified time, an error will be raised.
+
         Examples
         --------
 
@@ -1945,7 +2264,7 @@ class AsyncQueryBase(object):
         """
         import polars as pl
 
-        return pl.from_arrow(await self.to_arrow())
+        return pl.from_arrow(await self.to_arrow(timeout=timeout))
 
     async def explain_plan(self, verbose: Optional[bool] = False):
         """Return the execution plan for this query.
@@ -2088,7 +2407,7 @@ class AsyncQuery(AsyncQueryBase):
             )
 
     def nearest_to_text(
-        self, query: str, columns: Union[str, List[str], None] = None
+        self, query: str | FullTextQuery, columns: Union[str, List[str], None] = None
     ) -> AsyncFTSQuery:
         """
         Find the documents that are most relevant to the given text query.
@@ -2114,9 +2433,13 @@ class AsyncQuery(AsyncQueryBase):
             columns = [columns]
         if columns is None:
             columns = []
-        return AsyncFTSQuery(
+
-            self._inner.nearest_to_text({"query": query, "columns": columns})
+        if isinstance(query, str):
-        )
+            return AsyncFTSQuery(
+                self._inner.nearest_to_text({"query": query, "columns": columns})
+            )
+        # FullTextQuery object
+        return AsyncFTSQuery(self._inner.nearest_to_text({"query": query.to_dict()}))
 
 
 class AsyncFTSQuery(AsyncQueryBase):
@@ -2212,9 +2535,12 @@ class AsyncFTSQuery(AsyncQueryBase):
             )
 
     async def to_batches(
-        self, *, max_batch_length: Optional[int] = None
+        self,
+        *,
+        max_batch_length: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
-        reader = await super().to_batches()
+        reader = await super().to_batches(timeout=timeout)
         results = pa.Table.from_batches(await reader.read_all(), reader.schema)
         if self._reranker:
             results = self._reranker.rerank_fts(self.get_query(), results)
@@ -2399,7 +2725,7 @@ class AsyncVectorQuery(AsyncQueryBase, AsyncVectorQueryBase):
         return self
 
     def nearest_to_text(
-        self, query: str, columns: Union[str, List[str], None] = None
+        self, query: str | FullTextQuery, columns: Union[str, List[str], None] = None
     ) -> AsyncHybridQuery:
         """
         Find the documents that are most relevant to the given text query,
@@ -2429,14 +2755,21 @@ class AsyncVectorQuery(AsyncQueryBase, AsyncVectorQueryBase):
             columns = [columns]
         if columns is None:
             columns = []
-        return AsyncHybridQuery(
+
-            self._inner.nearest_to_text({"query": query, "columns": columns})
+        if isinstance(query, str):
-        )
+            return AsyncHybridQuery(
+                self._inner.nearest_to_text({"query": query, "columns": columns})
+            )
+        # FullTextQuery object
+        return AsyncHybridQuery(self._inner.nearest_to_text({"query": query.to_dict()}))
 
     async def to_batches(
-        self, *, max_batch_length: Optional[int] = None
+        self,
+        *,
+        max_batch_length: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
-        reader = await super().to_batches()
+        reader = await super().to_batches(timeout=timeout)
         results = pa.Table.from_batches(await reader.read_all(), reader.schema)
         if self._reranker:
             results = self._reranker.rerank_vector(self._query_string, results)
@@ -2492,7 +2825,10 @@ class AsyncHybridQuery(AsyncQueryBase, AsyncVectorQueryBase):
         return self
 
     async def to_batches(
-        self, *, max_batch_length: Optional[int] = None
+        self,
+        *,
+        max_batch_length: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
         fts_query = AsyncFTSQuery(self._inner.to_fts_query())
         vec_query = AsyncVectorQuery(self._inner.to_vector_query())
@@ -2504,8 +2840,8 @@ class AsyncHybridQuery(AsyncQueryBase, AsyncVectorQueryBase):
         vec_query.with_row_id()
 
         fts_results, vector_results = await asyncio.gather(
-            fts_query.to_arrow(),
+            fts_query.to_arrow(timeout=timeout),
-            vec_query.to_arrow(),
+            vec_query.to_arrow(timeout=timeout),
         )
 
         result = LanceHybridQueryBuilder._combine_hybrid_results(

python/python/lancedb/remote/table.py

@@ -355,9 +355,15 @@ class RemoteTable(Table):
         )
 
     def _execute_query(
-        self, query: Query, batch_size: Optional[int] = None
+        self,
+        query: Query,
+        *,
+        batch_size: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader:
-        async_iter = LOOP.run(self._table._execute_query(query, batch_size=batch_size))
+        async_iter = LOOP.run(
+            self._table._execute_query(query, batch_size=batch_size, timeout=timeout)
+        )
 
         def iter_sync():
             try:

python/python/lancedb/table.py

@@ -52,6 +52,7 @@ from .query import (
     AsyncHybridQuery,
     AsyncQuery,
     AsyncVectorQuery,
+    FullTextQuery,
     LanceEmptyQueryBuilder,
     LanceFtsQueryBuilder,
     LanceHybridQueryBuilder,
@@ -919,7 +920,9 @@ class Table(ABC):
     @abstractmethod
     def search(
         self,
-        query: Optional[Union[VEC, str, "PIL.Image.Image", Tuple]] = None,
+        query: Optional[
+            Union[VEC, str, "PIL.Image.Image", Tuple, FullTextQuery]
+        ] = None,
         vector_column_name: Optional[str] = None,
         query_type: QueryType = "auto",
         ordering_field_name: Optional[str] = None,
@@ -1004,7 +1007,11 @@ class Table(ABC):
 
     @abstractmethod
     def _execute_query(
-        self, query: Query, batch_size: Optional[int] = None
+        self,
+        query: Query,
+        *,
+        batch_size: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader: ...
 
     @abstractmethod
@@ -2039,7 +2046,9 @@ class LanceTable(Table):
     @overload
     def search(
         self,
-        query: Optional[Union[VEC, str, "PIL.Image.Image", Tuple]] = None,
+        query: Optional[
+            Union[VEC, str, "PIL.Image.Image", Tuple, FullTextQuery]
+        ] = None,
         vector_column_name: Optional[str] = None,
         query_type: Literal["hybrid"] = "hybrid",
         ordering_field_name: Optional[str] = None,
@@ -2058,7 +2067,9 @@ class LanceTable(Table):
 
     def search(
         self,
-        query: Optional[Union[VEC, str, "PIL.Image.Image", Tuple]] = None,
+        query: Optional[
+            Union[VEC, str, "PIL.Image.Image", Tuple, FullTextQuery]
+        ] = None,
         vector_column_name: Optional[str] = None,
         query_type: QueryType = "auto",
         ordering_field_name: Optional[str] = None,
@@ -2305,9 +2316,15 @@ class LanceTable(Table):
         LOOP.run(self._table.update(values, where=where, updates_sql=values_sql))
 
     def _execute_query(
-        self, query: Query, batch_size: Optional[int] = None
+        self,
+        query: Query,
+        *,
+        batch_size: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader:
-        async_iter = LOOP.run(self._table._execute_query(query, batch_size))
+        async_iter = LOOP.run(
+            self._table._execute_query(query, batch_size=batch_size, timeout=timeout)
+        )
 
         def iter_sync():
             try:
@@ -3134,7 +3151,9 @@ class AsyncTable:
     @overload
     async def search(
         self,
-        query: Optional[Union[VEC, str, "PIL.Image.Image", Tuple]] = None,
+        query: Optional[
+            Union[VEC, str, "PIL.Image.Image", Tuple, FullTextQuery]
+        ] = None,
         vector_column_name: Optional[str] = None,
         query_type: Literal["vector"] = ...,
         ordering_field_name: Optional[str] = None,
@@ -3143,7 +3162,9 @@ class AsyncTable:
 
     async def search(
         self,
-        query: Optional[Union[VEC, str, "PIL.Image.Image", Tuple]] = None,
+        query: Optional[
+            Union[VEC, str, "PIL.Image.Image", Tuple, FullTextQuery]
+        ] = None,
         vector_column_name: Optional[str] = None,
         query_type: QueryType = "auto",
         ordering_field_name: Optional[str] = None,
@@ -3253,6 +3274,8 @@ class AsyncTable:
             if is_embedding(query):
                 vector_query = query
                 query_type = "vector"
+            elif isinstance(query, FullTextQuery):
+                query_type = "fts"
             elif isinstance(query, str):
                 try:
                     (
@@ -3373,13 +3396,15 @@ class AsyncTable:
             async_query = async_query.nearest_to_text(
                 query.full_text_query.query, query.full_text_query.columns
             )
-            if query.full_text_query.limit is not None:
-                async_query = async_query.limit(query.full_text_query.limit)
 
         return async_query
 
     async def _execute_query(
-        self, query: Query, batch_size: Optional[int] = None
+        self,
+        query: Query,
+        *,
+        batch_size: Optional[int] = None,
+        timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader:
         # The sync table calls into this method, so we need to map the
         # query to the async version of the query and run that here. This is only
@@ -3387,7 +3412,9 @@ class AsyncTable:
 
         async_query = self._sync_query_to_async(query)
 
-        return await async_query.to_batches(max_batch_length=batch_size)
+        return await async_query.to_batches(
+            max_batch_length=batch_size, timeout=timeout
+        )
 
     async def _explain_plan(self, query: Query, verbose: Optional[bool]) -> str:
         # This method is used by the sync table

python/python/tests/test_embeddings_slow.py

@@ -12,6 +12,7 @@ import pyarrow as pa
 import pytest
 from lancedb.embeddings import get_registry
 from lancedb.pydantic import LanceModel, Vector
+import requests
 
 # These are integration tests for embedding functions.
 # They are slow because they require downloading models
@@ -516,3 +517,61 @@ def test_voyageai_embedding_function():
 
     tbl.add(df)
     assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()
+
+
+@pytest.mark.slow
+@pytest.mark.skipif(
+    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
+)
+def test_voyageai_multimodal_embedding_function():
+    voyageai = (
+        get_registry().get("voyageai").create(name="voyage-multimodal-3", max_retries=0)
+    )
+
+    class Images(LanceModel):
+        label: str
+        image_uri: str = voyageai.SourceField()  # image uri as the source
+        image_bytes: bytes = voyageai.SourceField()  # image bytes as the source
+        vector: Vector(voyageai.ndims()) = voyageai.VectorField()  # vector column
+        vec_from_bytes: Vector(voyageai.ndims()) = (
+            voyageai.VectorField()
+        )  # Another vector column
+
+    db = lancedb.connect("~/lancedb")
+    table = db.create_table("test", schema=Images, mode="overwrite")
+    labels = ["cat", "cat", "dog", "dog", "horse", "horse"]
+    uris = [
+        "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
+        "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
+        "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
+        "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
+        "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
+        "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
+    ]
+    # get each uri as bytes
+    image_bytes = [requests.get(uri).content for uri in uris]
+    table.add(
+        pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": image_bytes})
+    )
+    assert len(table.to_pandas()["vector"][0]) == voyageai.ndims()
+
+
+@pytest.mark.slow
+@pytest.mark.skipif(
+    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
+)
+def test_voyageai_multimodal_embedding_text_function():
+    voyageai = (
+        get_registry().get("voyageai").create(name="voyage-multimodal-3", max_retries=0)
+    )
+
+    class TextModel(LanceModel):
+        text: str = voyageai.SourceField()
+        vector: Vector(voyageai.ndims()) = voyageai.VectorField()
+
+    df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
+    db = lancedb.connect("~/lancedb")
+    tbl = db.create_table("test", schema=TextModel, mode="overwrite")
+
+    tbl.add(df)
+    assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()

python/python/tests/test_fts.py

@@ -20,7 +20,9 @@ from unittest import mock
 import lancedb as ldb
 from lancedb.db import DBConnection
 from lancedb.index import FTS
+from lancedb.query import BoostQuery, MatchQuery, MultiMatchQuery, PhraseQuery
 import numpy as np
+import pyarrow as pa
 import pandas as pd
 import pytest
 from utils import exception_output
@@ -178,11 +180,47 @@ def test_search_fts(table, use_tantivy):
     results = table.search("puppy").select(["id", "text"]).to_list()
     assert len(results) == 10
 
+    if not use_tantivy:
+        # Test with a query
+        results = (
+            table.search(MatchQuery("puppy", "text"))
+            .select(["id", "text"])
+            .limit(5)
+            .to_list()
+        )
+        assert len(results) == 5
+
+        # Test boost query
+        results = (
+            table.search(
+                BoostQuery(
+                    MatchQuery("puppy", "text"),
+                    MatchQuery("runs", "text"),
+                )
+            )
+            .select(["id", "text"])
+            .limit(5)
+            .to_list()
+        )
+        assert len(results) == 5
+
+        # Test multi match query
+        table.create_fts_index("text2", use_tantivy=use_tantivy)
+        results = (
+            table.search(MultiMatchQuery("puppy", ["text", "text2"]))
+            .select(["id", "text"])
+            .limit(5)
+            .to_list()
+        )
+        assert len(results) == 5
+        assert len(results[0]) == 3  # id, text, _score
+
 
 @pytest.mark.asyncio
 async def test_fts_select_async(async_table):
     tbl = await async_table
     await tbl.create_index("text", config=FTS())
+    await tbl.create_index("text2", config=FTS())
     results = (
         await tbl.query()
         .nearest_to_text("puppy")
@@ -193,6 +231,54 @@ async def test_fts_select_async(async_table):
     assert len(results) == 5
     assert len(results[0]) == 3  # id, text, _score
 
+    # Test with FullTextQuery
+    results = (
+        await tbl.query()
+        .nearest_to_text(MatchQuery("puppy", "text"))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+
+    # Test with BoostQuery
+    results = (
+        await tbl.query()
+        .nearest_to_text(
+            BoostQuery(
+                MatchQuery("puppy", "text"),
+                MatchQuery("runs", "text"),
+            )
+        )
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+
+    # Test with MultiMatchQuery
+    results = (
+        await tbl.query()
+        .nearest_to_text(MultiMatchQuery("puppy", ["text", "text2"]))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+
+    # Test with search() API
+    results = (
+        await (await tbl.search(MatchQuery("puppy", "text")))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+
 
 def test_search_fts_phrase_query(table):
     table.create_fts_index("text", use_tantivy=False, with_position=False)
@@ -207,6 +293,13 @@ def test_search_fts_phrase_query(table):
     assert len(results) > len(phrase_results)
     assert len(phrase_results) > 0
 
+    # Test with a query
+    phrase_results = (
+        table.search(PhraseQuery("puppy runs", "text")).limit(100).to_list()
+    )
+    assert len(results) > len(phrase_results)
+    assert len(phrase_results) > 0
+
 
 @pytest.mark.asyncio
 async def test_search_fts_phrase_query_async(async_table):
@@ -227,6 +320,16 @@ async def test_search_fts_phrase_query_async(async_table):
     assert len(results) > len(phrase_results)
     assert len(phrase_results) > 0
 
+    # Test with a query
+    phrase_results = (
+        await async_table.query()
+        .nearest_to_text(PhraseQuery("puppy runs", "text"))
+        .limit(100)
+        .to_list()
+    )
+    assert len(results) > len(phrase_results)
+    assert len(phrase_results) > 0
+
 
 def test_search_fts_specify_column(table):
     table.create_fts_index("text", use_tantivy=False)
@@ -524,3 +627,32 @@ def test_language(mem_db: DBConnection):
     # Stop words -> no results
     results = table.search("la", query_type="fts").limit(5).to_list()
     assert len(results) == 0
+
+
+def test_fts_on_list(mem_db: DBConnection):
+    data = pa.table(
+        {
+            "text": [
+                ["lance database", "the", "search"],
+                ["lance database"],
+                ["lance", "search"],
+                ["database", "search"],
+                ["unrelated", "doc"],
+            ],
+            "vector": [
+                [1.0, 2.0, 3.0],
+                [4.0, 5.0, 6.0],
+                [7.0, 8.0, 9.0],
+                [10.0, 11.0, 12.0],
+                [13.0, 14.0, 15.0],
+            ],
+        }
+    )
+    table = mem_db.create_table("test", data=data)
+    table.create_fts_index("text", use_tantivy=False)
+
+    res = table.search("lance").limit(5).to_list()
+    assert len(res) == 3
+
+    res = table.search(PhraseQuery("lance database", "text")).limit(5).to_list()
+    assert len(res) == 2

python/python/tests/test_index.py

@@ -31,6 +31,7 @@ async def some_table(db_async):
         {
             "id": list(range(NROWS)),
             "vector": sample_fixed_size_list_array(NROWS, DIM),
+            "fsb": pa.array([bytes([i]) for i in range(NROWS)], pa.binary(1)),
             "tags": [
                 [f"tag{random.randint(0, 8)}" for _ in range(2)] for _ in range(NROWS)
             ],
@@ -85,6 +86,16 @@ async def test_create_scalar_index(some_table: AsyncTable):
     assert len(indices) == 0
 
 
+@pytest.mark.asyncio
+async def test_create_fixed_size_binary_index(some_table: AsyncTable):
+    await some_table.create_index("fsb", config=BTree())
+    indices = await some_table.list_indices()
+    assert str(indices) == '[Index(BTree, columns=["fsb"], name="fsb_idx")]'
+    assert len(indices) == 1
+    assert indices[0].index_type == "BTree"
+    assert indices[0].columns == ["fsb"]
+
+
 @pytest.mark.asyncio
 async def test_create_bitmap_index(some_table: AsyncTable):
     await some_table.create_index("id", config=Bitmap())

python/python/tests/test_query.py

@@ -511,7 +511,8 @@ def test_query_builder_with_different_vector_column():
             columns=["b"],
             vector_column="foo_vector",
         ),
-        None,
+        batch_size=None,
+        timeout=None,
     )
 
 
@@ -1076,3 +1077,67 @@ async def test_query_serialization_async(table_async: AsyncTable):
         full_text_query=FullTextSearchQuery(columns=[], query="foo"),
         with_row_id=False,
     )
+
+
+def test_query_timeout(tmp_path):
+    # Use local directory instead of memory:// to add a bit of latency to
+    # operations so a timeout of zero will trigger exceptions.
+    db = lancedb.connect(tmp_path)
+    data = pa.table(
+        {
+            "text": ["a", "b"],
+            "vector": pa.FixedSizeListArray.from_arrays(
+                pc.random(4).cast(pa.float32()), 2
+            ),
+        }
+    )
+    table = db.create_table("test", data)
+    table.create_fts_index("text", use_tantivy=False)
+
+    with pytest.raises(Exception, match="Query timeout"):
+        table.search().where("text = 'a'").to_list(timeout=timedelta(0))
+
+    with pytest.raises(Exception, match="Query timeout"):
+        table.search([0.0, 0.0]).to_arrow(timeout=timedelta(0))
+
+    with pytest.raises(Exception, match="Query timeout"):
+        table.search("a", query_type="fts").to_pandas(timeout=timedelta(0))
+
+    with pytest.raises(Exception, match="Query timeout"):
+        table.search(query_type="hybrid").vector([0.0, 0.0]).text("a").to_arrow(
+            timeout=timedelta(0)
+        )
+
+
+@pytest.mark.asyncio
+async def test_query_timeout_async(tmp_path):
+    db = await lancedb.connect_async(tmp_path)
+    data = pa.table(
+        {
+            "text": ["a", "b"],
+            "vector": pa.FixedSizeListArray.from_arrays(
+                pc.random(4).cast(pa.float32()), 2
+            ),
+        }
+    )
+    table = await db.create_table("test", data)
+    await table.create_index("text", config=FTS())
+
+    with pytest.raises(Exception, match="Query timeout"):
+        await table.query().where("text != 'a'").to_list(timeout=timedelta(0))
+
+    with pytest.raises(Exception, match="Query timeout"):
+        await table.vector_search([0.0, 0.0]).to_arrow(timeout=timedelta(0))
+
+    with pytest.raises(Exception, match="Query timeout"):
+        await (await table.search("a", query_type="fts")).to_pandas(
+            timeout=timedelta(0)
+        )
+
+    with pytest.raises(Exception, match="Query timeout"):
+        await (
+            table.query()
+            .nearest_to_text("a")
+            .nearest_to([0.0, 0.0])
+            .to_list(timeout=timedelta(0))
+        )

python/python/tests/test_remote_db.py

@@ -444,6 +444,16 @@ def test_query_sync_fts():
             "prefilter": True,
             "with_row_id": True,
             "version": None,
+        } or body == {
+            "full_text_query": {
+                "query": "puppy",
+                "columns": ["description", "name"],
+            },
+            "k": 42,
+            "vector": [],
+            "prefilter": True,
+            "with_row_id": True,
+            "version": None,
         }
 
         return pa.table({"id": [1, 2, 3]})

python/src/query.rs

@@ -2,25 +2,26 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use std::sync::Arc;
+use std::time::Duration;
 
 use arrow::array::make_array;
 use arrow::array::Array;
 use arrow::array::ArrayData;
 use arrow::pyarrow::FromPyArrow;
 use arrow::pyarrow::IntoPyArrow;
-use lancedb::index::scalar::FullTextSearchQuery;
+use lancedb::index::scalar::{FtsQuery, FullTextSearchQuery, MatchQuery, PhraseQuery};
 use lancedb::query::QueryExecutionOptions;
 use lancedb::query::QueryFilter;
 use lancedb::query::{
     ExecutableQuery, Query as LanceDbQuery, QueryBase, Select, VectorQuery as LanceDbVectorQuery,
 };
 use lancedb::table::AnyQuery;
-use pyo3::exceptions::PyNotImplementedError;
 use pyo3::exceptions::PyRuntimeError;
+use pyo3::exceptions::{PyNotImplementedError, PyValueError};
 use pyo3::prelude::{PyAnyMethods, PyDictMethods};
 use pyo3::pymethods;
-use pyo3::types::PyDict;
 use pyo3::types::PyList;
+use pyo3::types::{PyDict, PyString};
 use pyo3::Bound;
 use pyo3::IntoPyObject;
 use pyo3::PyAny;
@@ -31,7 +32,7 @@ use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::arrow::RecordBatchStream;
 use crate::error::PythonErrorExt;
-use crate::util::parse_distance_type;
+use crate::util::{parse_distance_type, parse_fts_query};
 
 // Python representation of full text search parameters
 #[derive(Clone)]
@@ -46,8 +47,8 @@ pub struct PyFullTextSearchQuery {
 impl From<FullTextSearchQuery> for PyFullTextSearchQuery {
     fn from(query: FullTextSearchQuery) -> Self {
         PyFullTextSearchQuery {
-            columns: query.columns,
+            columns: query.columns().into_iter().collect(),
-            query: query.query,
+            query: query.query.query().to_owned(),
             limit: query.limit,
             wand_factor: query.wand_factor,
         }
@@ -236,29 +237,69 @@ impl Query {
     }
 
     pub fn nearest_to_text(&mut self, query: Bound<'_, PyDict>) -> PyResult<FTSQuery> {
-        let query_text = query
+        let fts_query = query
             .get_item("query")?
             .ok_or(PyErr::new::<PyRuntimeError, _>(
                 "Query text is required for nearest_to_text",
-            ))?
+            ))?;
-            .extract::<String>()?;
-        let columns = query
-            .get_item("columns")?
-            .map(|columns| columns.extract::<Vec<String>>())
-            .transpose()?;
 
-        let fts_query = FullTextSearchQuery::new(query_text).columns(columns);
+        let query = if let Ok(query_text) = fts_query.downcast::<PyString>() {
+            let mut query_text = query_text.to_string();
+            let columns = query
+                .get_item("columns")?
+                .map(|columns| columns.extract::<Vec<String>>())
+                .transpose()?;
+
+            let is_phrase =
+                query_text.len() >= 2 && query_text.starts_with('"') && query_text.ends_with('"');
+            let is_multi_match = columns.as_ref().map(|cols| cols.len() > 1).unwrap_or(false);
+
+            if is_phrase {
+                // Remove the surrounding quotes for phrase queries
+                query_text = query_text[1..query_text.len() - 1].to_string();
+            }
+
+            let query: FtsQuery = match (is_phrase, is_multi_match) {
+                (false, _) => MatchQuery::new(query_text).into(),
+                (true, false) => PhraseQuery::new(query_text).into(),
+                (true, true) => {
+                    return Err(PyValueError::new_err(
+                        "Phrase queries cannot be used with multiple columns.",
+                    ));
+                }
+            };
+            let mut query = FullTextSearchQuery::new_query(query);
+            if let Some(cols) = columns {
+                if !cols.is_empty() {
+                    query = query.with_columns(&cols).map_err(|e| {
+                        PyValueError::new_err(format!(
+                            "Failed to set full text search columns: {}",
+                            e
+                        ))
+                    })?;
+                }
+            }
+            query
+        } else if let Ok(query) = fts_query.downcast::<PyDict>() {
+            let query = parse_fts_query(query)?;
+            FullTextSearchQuery::new_query(query)
+        } else {
+            return Err(PyValueError::new_err(
+                "query must be a string or a Query object",
+            ));
+        };
 
         Ok(FTSQuery {
-            fts_query,
             inner: self.inner.clone(),
+            fts_query: query,
         })
     }
 
-    #[pyo3(signature = (max_batch_length=None))]
+    #[pyo3(signature = (max_batch_length=None, timeout=None))]
     pub fn execute(
         self_: PyRef<'_, Self>,
         max_batch_length: Option<u32>,
+        timeout: Option<Duration>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
@@ -266,6 +307,9 @@ impl Query {
             if let Some(max_batch_length) = max_batch_length {
                 opts.max_batch_length = max_batch_length;
             }
+            if let Some(timeout) = timeout {
+                opts.timeout = Some(timeout);
+            }
             let inner_stream = inner.execute_with_options(opts).await.infer_error()?;
             Ok(RecordBatchStream::new(inner_stream))
         })
@@ -337,10 +381,11 @@ impl FTSQuery {
         self.inner = self.inner.clone().postfilter();
     }
 
-    #[pyo3(signature = (max_batch_length=None))]
+    #[pyo3(signature = (max_batch_length=None, timeout=None))]
     pub fn execute(
         self_: PyRef<'_, Self>,
         max_batch_length: Option<u32>,
+        timeout: Option<Duration>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_
             .inner
@@ -352,6 +397,9 @@ impl FTSQuery {
             if let Some(max_batch_length) = max_batch_length {
                 opts.max_batch_length = max_batch_length;
             }
+            if let Some(timeout) = timeout {
+                opts.timeout = Some(timeout);
+            }
             let inner_stream = inner.execute_with_options(opts).await.infer_error()?;
             Ok(RecordBatchStream::new(inner_stream))
         })
@@ -386,7 +434,7 @@ impl FTSQuery {
     }
 
     pub fn get_query(&self) -> String {
-        self.fts_query.query.clone()
+        self.fts_query.query.query().to_owned()
     }
 
     pub fn to_query_request(&self) -> PyQueryRequest {
@@ -474,10 +522,11 @@ impl VectorQuery {
         self.inner = self.inner.clone().bypass_vector_index()
     }
 
-    #[pyo3(signature = (max_batch_length=None))]
+    #[pyo3(signature = (max_batch_length=None, timeout=None))]
     pub fn execute(
         self_: PyRef<'_, Self>,
         max_batch_length: Option<u32>,
+        timeout: Option<Duration>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner.clone();
         future_into_py(self_.py(), async move {
@@ -485,6 +534,9 @@ impl VectorQuery {
             if let Some(max_batch_length) = max_batch_length {
                 opts.max_batch_length = max_batch_length;
             }
+            if let Some(timeout) = timeout {
+                opts.timeout = Some(timeout);
+            }
             let inner_stream = inner.execute_with_options(opts).await.infer_error()?;
             Ok(RecordBatchStream::new(inner_stream))
         })

python/src/util.rs

@@ -3,11 +3,15 @@
 
 use std::sync::Mutex;
 
+use lancedb::index::scalar::{BoostQuery, FtsQuery, MatchQuery, MultiMatchQuery, PhraseQuery};
 use lancedb::DistanceType;
+use pyo3::prelude::{PyAnyMethods, PyDictMethods, PyListMethods};
+use pyo3::types::PyDict;
 use pyo3::{
     exceptions::{PyRuntimeError, PyValueError},
     pyfunction, PyResult,
 };
+use pyo3::{Bound, PyAny};
 
 /// A wrapper around a rust builder
 ///
@@ -59,3 +63,116 @@ pub fn validate_table_name(table_name: &str) -> PyResult<()> {
     lancedb::utils::validate_table_name(table_name)
         .map_err(|e| PyValueError::new_err(e.to_string()))
 }
+
+pub fn parse_fts_query(query: &Bound<'_, PyDict>) -> PyResult<FtsQuery> {
+    let query_type = query.keys().get_item(0)?.extract::<String>()?;
+    let query_value = query
+        .get_item(&query_type)?
+        .ok_or(PyValueError::new_err(format!(
+            "Query type {} not found",
+            query_type
+        )))?;
+    let query_value = query_value.downcast::<PyDict>()?;
+
+    match query_type.as_str() {
+        "match" => {
+            let column = query_value.keys().get_item(0)?.extract::<String>()?;
+            let params = query_value
+                .get_item(&column)?
+                .ok_or(PyValueError::new_err(format!(
+                    "column {} not found",
+                    column
+                )))?;
+            let params = params.downcast::<PyDict>()?;
+
+            let query = params
+                .get_item("query")?
+                .ok_or(PyValueError::new_err("query not found"))?
+                .extract::<String>()?;
+            let boost = params
+                .get_item("boost")?
+                .ok_or(PyValueError::new_err("boost not found"))?
+                .extract::<f32>()?;
+            let fuzziness = params
+                .get_item("fuzziness")?
+                .ok_or(PyValueError::new_err("fuzziness not found"))?
+                .extract::<Option<u32>>()?;
+            let max_expansions = params
+                .get_item("max_expansions")?
+                .ok_or(PyValueError::new_err("max_expansions not found"))?
+                .extract::<usize>()?;
+
+            let query = MatchQuery::new(query)
+                .with_column(Some(column))
+                .with_boost(boost)
+                .with_fuzziness(fuzziness)
+                .with_max_expansions(max_expansions);
+            Ok(query.into())
+        }
+
+        "match_phrase" => {
+            let column = query_value.keys().get_item(0)?.extract::<String>()?;
+            let query = query_value
+                .get_item(&column)?
+                .ok_or(PyValueError::new_err(format!(
+                    "column {} not found",
+                    column
+                )))?
+                .extract::<String>()?;
+
+            let query = PhraseQuery::new(query).with_column(Some(column));
+            Ok(query.into())
+        }
+
+        "boost" => {
+            let positive: Bound<'_, PyAny> = query_value
+                .get_item("positive")?
+                .ok_or(PyValueError::new_err("positive not found"))?;
+            let positive = positive.downcast::<PyDict>()?;
+
+            let negative = query_value
+                .get_item("negative")?
+                .ok_or(PyValueError::new_err("negative not found"))?;
+            let negative = negative.downcast::<PyDict>()?;
+
+            let negative_boost = query_value
+                .get_item("negative_boost")?
+                .ok_or(PyValueError::new_err("negative_boost not found"))?
+                .extract::<f32>()?;
+
+            let positive_query = parse_fts_query(positive)?;
+            let negative_query = parse_fts_query(negative)?;
+            let query = BoostQuery::new(positive_query, negative_query, Some(negative_boost));
+
+            Ok(query.into())
+        }
+
+        "multi_match" => {
+            let query = query_value
+                .get_item("query")?
+                .ok_or(PyValueError::new_err("query not found"))?
+                .extract::<String>()?;
+
+            let columns = query_value
+                .get_item("columns")?
+                .ok_or(PyValueError::new_err("columns not found"))?
+                .extract::<Vec<String>>()?;
+
+            let boost = query_value
+                .get_item("boost")?
+                .ok_or(PyValueError::new_err("boost not found"))?
+                .extract::<Vec<f32>>()?;
+
+            let query =
+                MultiMatchQuery::try_new_with_boosts(query, columns, boost).map_err(|e| {
+                    PyValueError::new_err(format!("Error creating MultiMatchQuery: {}", e))
+                })?;
+            Ok(query.into())
+        }
+
+        _ => Err(PyValueError::new_err(format!(
+            "Unsupported query type: {}",
+            query_type
+        ))),
+    }
+}

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.18.3-beta.0"
+version = "0.19.0-beta.5"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/connection.rs

@@ -142,12 +142,6 @@ impl CreateTableBuilder<true> {
         }
     }
 
-    /// Apply the given write options when writing the initial data
-    pub fn write_options(mut self, write_options: WriteOptions) -> Self {
-        self.request.write_options = write_options;
-        self
-    }
-
     /// Execute the create table operation
     pub async fn execute(self) -> Result<Table> {
         let embedding_registry = self.embedding_registry.clone();
@@ -229,6 +223,12 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
         self
     }
 
+    /// Apply the given write options when writing the initial data
+    pub fn write_options(mut self, write_options: WriteOptions) -> Self {
+        self.request.write_options = write_options;
+        self
+    }
+
     /// Set an option for the storage layer.
     ///
     /// Options already set on the connection will be inherited by the table,

rust/lancedb/src/index/scalar.rs

@@ -80,5 +80,6 @@ impl FtsIndexBuilder {
     }
 }
 
+pub use lance_index::scalar::inverted::query::*;
 pub use lance_index::scalar::inverted::TokenizerConfig;
 pub use lance_index::scalar::FullTextSearchQuery;

rust/lancedb/src/io/object_store.rs

@@ -14,6 +14,9 @@ use object_store::{
 
 use async_trait::async_trait;
 
+#[cfg(test)]
+pub mod io_tracking;
+
 #[derive(Debug)]
 struct MirroringObjectStore {
     primary: Arc<dyn ObjectStore>,

rust/lancedb/src/io/object_store/io_tracking.rs

@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use std::{
+    fmt::{Display, Formatter},
+    sync::{Arc, Mutex},
+};
+
+use bytes::Bytes;
+use futures::stream::BoxStream;
+use lance::io::WrappingObjectStore;
+use object_store::{
+    path::Path, GetOptions, GetResult, ListResult, MultipartUpload, ObjectMeta, ObjectStore,
+    PutMultipartOpts, PutOptions, PutPayload, PutResult, Result as OSResult, UploadPart,
+};
+
+#[derive(Debug, Default)]
+pub struct IoStats {
+    pub read_iops: u64,
+    pub read_bytes: u64,
+    pub write_iops: u64,
+    pub write_bytes: u64,
+}
+
+impl Display for IoStats {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        write!(f, "{:#?}", self)
+    }
+}
+
+#[derive(Debug, Clone)]
+pub struct IoTrackingStore {
+    target: Arc<dyn ObjectStore>,
+    stats: Arc<Mutex<IoStats>>,
+}
+
+impl Display for IoTrackingStore {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        write!(f, "{:#?}", self)
+    }
+}
+
+#[derive(Debug, Default, Clone)]
+pub struct IoStatsHolder(Arc<Mutex<IoStats>>);
+
+impl IoStatsHolder {
+    pub fn incremental_stats(&self) -> IoStats {
+        std::mem::take(&mut self.0.lock().expect("failed to lock IoStats"))
+    }
+}
+
+impl WrappingObjectStore for IoStatsHolder {
+    fn wrap(&self, target: Arc<dyn ObjectStore>) -> Arc<dyn ObjectStore> {
+        Arc::new(IoTrackingStore {
+            target,
+            stats: self.0.clone(),
+        })
+    }
+}
+
+impl IoTrackingStore {
+    pub fn new_wrapper() -> (Arc<dyn WrappingObjectStore>, Arc<Mutex<IoStats>>) {
+        let stats = Arc::new(Mutex::new(IoStats::default()));
+        (Arc::new(IoStatsHolder(stats.clone())), stats)
+    }
+
+    fn record_read(&self, num_bytes: u64) {
+        let mut stats = self.stats.lock().unwrap();
+        stats.read_iops += 1;
+        stats.read_bytes += num_bytes;
+    }
+
+    fn record_write(&self, num_bytes: u64) {
+        let mut stats = self.stats.lock().unwrap();
+        stats.write_iops += 1;
+        stats.write_bytes += num_bytes;
+    }
+}
+
+#[async_trait::async_trait]
+#[deny(clippy::missing_trait_methods)]
+impl ObjectStore for IoTrackingStore {
+    async fn put(&self, location: &Path, bytes: PutPayload) -> OSResult<PutResult> {
+        self.record_write(bytes.content_length() as u64);
+        self.target.put(location, bytes).await
+    }
+
+    async fn put_opts(
+        &self,
+        location: &Path,
+        bytes: PutPayload,
+        opts: PutOptions,
+    ) -> OSResult<PutResult> {
+        self.record_write(bytes.content_length() as u64);
+        self.target.put_opts(location, bytes, opts).await
+    }
+
+    async fn put_multipart(&self, location: &Path) -> OSResult<Box<dyn MultipartUpload>> {
+        let target = self.target.put_multipart(location).await?;
+        Ok(Box::new(IoTrackingMultipartUpload {
+            target,
+            stats: self.stats.clone(),
+        }))
+    }
+
+    async fn put_multipart_opts(
+        &self,
+        location: &Path,
+        opts: PutMultipartOpts,
+    ) -> OSResult<Box<dyn MultipartUpload>> {
+        let target = self.target.put_multipart_opts(location, opts).await?;
+        Ok(Box::new(IoTrackingMultipartUpload {
+            target,
+            stats: self.stats.clone(),
+        }))
+    }
+
+    async fn get(&self, location: &Path) -> OSResult<GetResult> {
+        let result = self.target.get(location).await;
+        if let Ok(result) = &result {
+            let num_bytes = result.range.end - result.range.start;
+            self.record_read(num_bytes as u64);
+        }
+        result
+    }
+
+    async fn get_opts(&self, location: &Path, options: GetOptions) -> OSResult<GetResult> {
+        let result = self.target.get_opts(location, options).await;
+        if let Ok(result) = &result {
+            let num_bytes = result.range.end - result.range.start;
+            self.record_read(num_bytes as u64);
+        }
+        result
+    }
+
+    async fn get_range(&self, location: &Path, range: std::ops::Range<usize>) -> OSResult<Bytes> {
+        let result = self.target.get_range(location, range).await;
+        if let Ok(result) = &result {
+            self.record_read(result.len() as u64);
+        }
+        result
+    }
+
+    async fn get_ranges(
+        &self,
+        location: &Path,
+        ranges: &[std::ops::Range<usize>],
+    ) -> OSResult<Vec<Bytes>> {
+        let result = self.target.get_ranges(location, ranges).await;
+        if let Ok(result) = &result {
+            self.record_read(result.iter().map(|b| b.len() as u64).sum());
+        }
+        result
+    }
+
+    async fn head(&self, location: &Path) -> OSResult<ObjectMeta> {
+        self.record_read(0);
+        self.target.head(location).await
+    }
+
+    async fn delete(&self, location: &Path) -> OSResult<()> {
+        self.record_write(0);
+        self.target.delete(location).await
+    }
+
+    fn delete_stream<'a>(
+        &'a self,
+        locations: BoxStream<'a, OSResult<Path>>,
+    ) -> BoxStream<'a, OSResult<Path>> {
+        self.target.delete_stream(locations)
+    }
+
+    fn list(&self, prefix: Option<&Path>) -> BoxStream<'_, OSResult<ObjectMeta>> {
+        self.record_read(0);
+        self.target.list(prefix)
+    }
+
+    fn list_with_offset(
+        &self,
+        prefix: Option<&Path>,
+        offset: &Path,
+    ) -> BoxStream<'_, OSResult<ObjectMeta>> {
+        self.record_read(0);
+        self.target.list_with_offset(prefix, offset)
+    }
+
+    async fn list_with_delimiter(&self, prefix: Option<&Path>) -> OSResult<ListResult> {
+        self.record_read(0);
+        self.target.list_with_delimiter(prefix).await
+    }
+
+    async fn copy(&self, from: &Path, to: &Path) -> OSResult<()> {
+        self.record_write(0);
+        self.target.copy(from, to).await
+    }
+
+    async fn rename(&self, from: &Path, to: &Path) -> OSResult<()> {
+        self.record_write(0);
+        self.target.rename(from, to).await
+    }
+
+    async fn rename_if_not_exists(&self, from: &Path, to: &Path) -> OSResult<()> {
+        self.record_write(0);
+        self.target.rename_if_not_exists(from, to).await
+    }
+
+    async fn copy_if_not_exists(&self, from: &Path, to: &Path) -> OSResult<()> {
+        self.record_write(0);
+        self.target.copy_if_not_exists(from, to).await
+    }
+}
+
+#[derive(Debug)]
+struct IoTrackingMultipartUpload {
+    target: Box<dyn MultipartUpload>,
+    stats: Arc<Mutex<IoStats>>,
+}
+
+#[async_trait::async_trait]
+impl MultipartUpload for IoTrackingMultipartUpload {
+    async fn abort(&mut self) -> OSResult<()> {
+        self.target.abort().await
+    }
+
+    async fn complete(&mut self) -> OSResult<PutResult> {
+        self.target.complete().await
+    }
+
+    fn put_part(&mut self, payload: PutPayload) -> UploadPart {
+        {
+            let mut stats = self.stats.lock().unwrap();
+            stats.write_iops += 1;
+            stats.write_bytes += payload.content_length() as u64;
+        }
+        self.target.put_part(payload)
+    }
+}

rust/lancedb/src/query.rs

@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::future::Future;
 use std::sync::Arc;
+use std::{future::Future, time::Duration};
 
 use arrow::compute::concat_batches;
 use arrow_array::{make_array, Array, Float16Array, Float32Array, Float64Array};
@@ -25,6 +25,7 @@ use crate::error::{Error, Result};
 use crate::rerankers::rrf::RRFReranker;
 use crate::rerankers::{check_reranker_result, NormalizeMethod, Reranker};
 use crate::table::BaseTable;
+use crate::utils::TimeoutStream;
 use crate::DistanceType;
 use crate::{arrow::SendableRecordBatchStream, table::AnyQuery};
 
@@ -525,12 +526,15 @@ pub struct QueryExecutionOptions {
     ///
     /// By default, this is 1024
     pub max_batch_length: u32,
+    /// Max duration to wait for the query to execute before timing out.
+    pub timeout: Option<Duration>,
 }
 
 impl Default for QueryExecutionOptions {
     fn default() -> Self {
         Self {
             max_batch_length: 1024,
+            timeout: None,
         }
     }
 }
@@ -1007,7 +1011,10 @@ impl VectorQuery {
         self
     }
 
-    pub async fn execute_hybrid(&self) -> Result<SendableRecordBatchStream> {
+    pub async fn execute_hybrid(
+        &self,
+        options: QueryExecutionOptions,
+    ) -> Result<SendableRecordBatchStream> {
         // clone query and specify we want to include row IDs, which can be needed for reranking
         let mut fts_query = Query::new(self.parent.clone());
         fts_query.request = self.request.base.clone();
@@ -1016,7 +1023,10 @@ impl VectorQuery {
         let mut vector_query = self.clone().with_row_id();
 
         vector_query.request.base.full_text_search = None;
-        let (fts_results, vec_results) = try_join!(fts_query.execute(), vector_query.execute())?;
+        let (fts_results, vec_results) = try_join!(
+            fts_query.execute_with_options(options.clone()),
+            vector_query.inner_execute_with_options(options)
+        )?;
 
         let (fts_results, vec_results) = try_join!(
             fts_results.try_collect::<Vec<_>>(),
@@ -1056,7 +1066,7 @@ impl VectorQuery {
             })?;
 
         let mut results = reranker
-            .rerank_hybrid(&fts_query.query, vec_results, fts_results)
+            .rerank_hybrid(&fts_query.query.query(), vec_results, fts_results)
             .await?;
 
         check_reranker_result(&results)?;
@@ -1074,6 +1084,20 @@ impl VectorQuery {
             RecordBatchStreamAdapter::new(results.schema(), stream::iter([Ok(results)])),
         ))
     }
+
+    async fn inner_execute_with_options(
+        &self,
+        options: QueryExecutionOptions,
+    ) -> Result<SendableRecordBatchStream> {
+        let plan = self.create_plan(options.clone()).await?;
+        let inner = execute_plan(plan, Default::default())?;
+        let inner = if let Some(timeout) = options.timeout {
+            TimeoutStream::new_boxed(inner, timeout)
+        } else {
+            inner
+        };
+        Ok(DatasetRecordBatchStream::new(inner).into())
+    }
 }
 
 impl ExecutableQuery for VectorQuery {
@@ -1087,16 +1111,13 @@ impl ExecutableQuery for VectorQuery {
         options: QueryExecutionOptions,
     ) -> Result<SendableRecordBatchStream> {
         if self.request.base.full_text_search.is_some() {
-            let hybrid_result = async move { self.execute_hybrid().await }.boxed().await?;
+            let hybrid_result = async move { self.execute_hybrid(options).await }
+                .boxed()
+                .await?;
             return Ok(hybrid_result);
         }
 
-        Ok(SendableRecordBatchStream::from(
+        self.inner_execute_with_options(options).await
-            DatasetRecordBatchStream::new(execute_plan(
-                self.create_plan(options).await?,
-                Default::default(),
-            )?),
-        ))
     }
 
     async fn explain_plan(&self, verbose: bool) -> Result<String> {

rust/lancedb/src/remote/client.rs

@@ -13,7 +13,7 @@ use reqwest::{
 use crate::error::{Error, Result};
 use crate::remote::db::RemoteOptions;
 
-const REQUEST_ID_HEADER: &str = "x-request-id";
+const REQUEST_ID_HEADER: HeaderName = HeaderName::from_static("x-request-id");
 
 /// Configuration for the LanceDB Cloud HTTP client.
 #[derive(Clone, Debug)]
@@ -299,7 +299,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
     ) -> Result<HeaderMap> {
         let mut headers = HeaderMap::new();
         headers.insert(
-            "x-api-key",
+            HeaderName::from_static("x-api-key"),
             HeaderValue::from_str(api_key).map_err(|_| Error::InvalidInput {
                 message: "non-ascii api key provided".to_string(),
             })?,
@@ -307,7 +307,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
         if region == "local" {
             let host = format!("{}.local.api.lancedb.com", db_name);
             headers.insert(
-                "Host",
+                http::header::HOST,
                 HeaderValue::from_str(&host).map_err(|_| Error::InvalidInput {
                     message: format!("non-ascii database name '{}' provided", db_name),
                 })?,
@@ -315,7 +315,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
         }
         if has_host_override {
             headers.insert(
-                "x-lancedb-database",
+                HeaderName::from_static("x-lancedb-database"),
                 HeaderValue::from_str(db_name).map_err(|_| Error::InvalidInput {
                     message: format!("non-ascii database name '{}' provided", db_name),
                 })?,
@@ -323,7 +323,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
         }
         if db_prefix.is_some() {
             headers.insert(
-                "x-lancedb-database-prefix",
+                HeaderName::from_static("x-lancedb-database-prefix"),
                 HeaderValue::from_str(db_prefix.unwrap()).map_err(|_| Error::InvalidInput {
                     message: format!(
                         "non-ascii database prefix '{}' provided",
@@ -335,7 +335,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
 
         if let Some(v) = options.0.get("account_name") {
             headers.insert(
-                "x-azure-storage-account-name",
+                HeaderName::from_static("x-azure-storage-account-name"),
                 HeaderValue::from_str(v).map_err(|_| Error::InvalidInput {
                     message: format!("non-ascii storage account name '{}' provided", db_name),
                 })?,
@@ -343,7 +343,7 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
         }
         if let Some(v) = options.0.get("azure_storage_account_name") {
             headers.insert(
-                "x-azure-storage-account-name",
+                HeaderName::from_static("x-azure-storage-account-name"),
                 HeaderValue::from_str(v).map_err(|_| Error::InvalidInput {
                     message: format!("non-ascii storage account name '{}' provided", db_name),
                 })?,

rust/lancedb/src/remote/db.rs

@@ -52,6 +52,10 @@ impl ServerVersion {
     pub fn support_multivector(&self) -> bool {
         self.0 >= semver::Version::new(0, 2, 0)
     }
+
+    pub fn support_structural_fts(&self) -> bool {
+        self.0 >= semver::Version::new(0, 3, 0)
+    }
 }
 
 pub const OPT_REMOTE_PREFIX: &str = "remote_database_";

rust/lancedb/src/remote/table.rs

@@ -20,7 +20,7 @@ use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
 use datafusion_physical_plan::{ExecutionPlan, RecordBatchStream, SendableRecordBatchStream};
 use futures::TryStreamExt;
 use http::header::CONTENT_TYPE;
-use http::StatusCode;
+use http::{HeaderName, StatusCode};
 use lance::arrow::json::{JsonDataType, JsonSchema};
 use lance::dataset::scanner::DatasetRecordBatchStream;
 use lance::dataset::{ColumnAlteration, NewColumnTransform, Version};
@@ -44,6 +44,8 @@ use super::client::{HttpSend, RestfulLanceDbClient, Sender};
 use super::db::ServerVersion;
 use super::ARROW_STREAM_CONTENT_TYPE;
 
+const REQUEST_TIMEOUT_HEADER: HeaderName = HeaderName::from_static("x-request-timeout-ms");
+
 #[derive(Debug)]
 pub struct RemoteTable<S: HttpSend = Sender> {
     #[allow(dead_code)]
@@ -155,7 +157,11 @@ impl<S: HttpSend> RemoteTable<S> {
         Ok(Box::pin(RecordBatchStreamAdapter::new(schema, stream)))
     }
 
-    fn apply_query_params(body: &mut serde_json::Value, params: &QueryRequest) -> Result<()> {
+    fn apply_query_params(
+        &self,
+        body: &mut serde_json::Value,
+        params: &QueryRequest,
+    ) -> Result<()> {
         body["prefilter"] = params.prefilter.into();
         if let Some(offset) = params.offset {
             body["offset"] = serde_json::Value::Number(serde_json::Number::from(offset));
@@ -209,10 +215,17 @@ impl<S: HttpSend> RemoteTable<S> {
                     message: "Wand factor is not yet supported in LanceDB Cloud".into(),
                 });
             }
-            body["full_text_query"] = serde_json::json!({
+
-                "columns": full_text_search.columns,
+            if self.server_version.support_structural_fts() {
-                "query": full_text_search.query,
+                body["full_text_query"] = serde_json::json!({
-            })
+                    "query": full_text_search.query.clone(),
+                });
+            } else {
+                body["full_text_query"] = serde_json::json!({
+                    "columns": full_text_search.columns().into_iter().collect::<Vec<_>>(),
+                    "query": full_text_search.query.query(),
+                })
+            }
         }
 
         Ok(())
@@ -223,7 +236,7 @@ impl<S: HttpSend> RemoteTable<S> {
         mut body: serde_json::Value,
         query: &VectorQueryRequest,
     ) -> Result<Vec<serde_json::Value>> {
-        Self::apply_query_params(&mut body, &query.base)?;
+        self.apply_query_params(&mut body, &query.base)?;
 
         // Apply general parameters, before we dispatch based on number of query vectors.
         body["distance_type"] = serde_json::json!(query.distance_type.unwrap_or_default());
@@ -321,9 +334,19 @@ impl<S: HttpSend> RemoteTable<S> {
     async fn execute_query(
         &self,
         query: &AnyQuery,
-        _options: QueryExecutionOptions,
+        options: &QueryExecutionOptions,
     ) -> Result<Vec<Pin<Box<dyn RecordBatchStream + Send>>>> {
-        let request = self.client.post(&format!("/v1/table/{}/query/", self.name));
+        let mut request = self.client.post(&format!("/v1/table/{}/query/", self.name));
+
+        if let Some(timeout) = options.timeout {
+            // Client side timeout
+            request = request.timeout(timeout);
+            // Also send to server, so it can abort the query if it takes too long.
+            // (If it doesn't fit into u64, it's not worth sending anyways.)
+            if let Ok(timeout_ms) = u64::try_from(timeout.as_millis()) {
+                request = request.header(REQUEST_TIMEOUT_HEADER, timeout_ms);
+            }
+        }
 
         let query_bodies = self.prepare_query_bodies(query).await?;
         let requests: Vec<reqwest::RequestBuilder> = query_bodies
@@ -346,7 +369,7 @@ impl<S: HttpSend> RemoteTable<S> {
         match query {
             AnyQuery::Query(query) => {
                 let mut body = base_body.clone();
-                Self::apply_query_params(&mut body, query)?;
+                self.apply_query_params(&mut body, query)?;
                 // Empty vector can be passed if no vector search is performed.
                 body["vector"] = serde_json::Value::Array(Vec::new());
                 Ok(vec![body])
@@ -532,7 +555,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         query: &AnyQuery,
         options: QueryExecutionOptions,
     ) -> Result<Arc<dyn ExecutionPlan>> {
-        let streams = self.execute_query(query, options).await?;
+        let streams = self.execute_query(query, &options).await?;
         if streams.len() == 1 {
             let stream = streams.into_iter().next().unwrap();
             Ok(Arc::new(OneShotExec::new(stream)))
@@ -548,9 +571,9 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
     async fn query(
         &self,
         query: &AnyQuery,
-        _options: QueryExecutionOptions,
+        options: QueryExecutionOptions,
     ) -> Result<DatasetRecordBatchStream> {
-        let streams = self.execute_query(query, _options).await?;
+        let streams = self.execute_query(query, &options).await?;
 
         if streams.len() == 1 {
             Ok(DatasetRecordBatchStream::new(
@@ -1037,6 +1060,7 @@ mod tests {
     use arrow_schema::{DataType, Field, Schema};
     use chrono::{DateTime, Utc};
     use futures::{future::BoxFuture, StreamExt, TryFutureExt};
+    use lance_index::scalar::inverted::query::MatchQuery;
     use lance_index::scalar::FullTextSearchQuery;
     use reqwest::Body;
     use rstest::rstest;
@@ -1683,7 +1707,18 @@ mod tests {
                 "prefilter": true,
                 "version": null
             });
-            assert_eq!(body, expected_body);
+            let expected_body_2 = serde_json::json!({
+                "full_text_query": {
+                    "columns": ["b","a"],
+                    "query": "hello world",
+                },
+                "k": 10,
+                "vector": [],
+                "with_row_id": true,
+                "prefilter": true,
+                "version": null
+            });
+            assert!(body == expected_body || body == expected_body_2);
 
             let data = RecordBatch::try_new(
                 Arc::new(Schema::new(vec![Field::new("a", DataType::Int32, false)])),
@@ -1702,7 +1737,8 @@ mod tests {
             .query()
             .full_text_search(
                 FullTextSearchQuery::new("hello world".into())
-                    .columns(Some(vec!["a".into(), "b".into()])),
+                    .with_columns(&["a".into(), "b".into()])
+                    .unwrap(),
             )
             .with_row_id()
             .limit(10)
@@ -1711,6 +1747,66 @@ mod tests {
             .unwrap();
     }
 
+    #[tokio::test]
+    async fn test_query_structured_fts() {
+        let table =
+            Table::new_with_handler_version("my_table", semver::Version::new(0, 3, 0), |request| {
+                assert_eq!(request.method(), "POST");
+                assert_eq!(request.url().path(), "/v1/table/my_table/query/");
+                assert_eq!(
+                    request.headers().get("Content-Type").unwrap(),
+                    JSON_CONTENT_TYPE
+                );
+
+                let body = request.body().unwrap().as_bytes().unwrap();
+                let body: serde_json::Value = serde_json::from_slice(body).unwrap();
+                let expected_body = serde_json::json!({
+                    "full_text_query": {
+                        "query": {
+                            "match": {
+                                "terms": "hello world",
+                                "column": "a",
+                                "boost": 1.0,
+                                "fuzziness": 0,
+                                "max_expansions": 50,
+                            },
+                        }
+                    },
+                    "k": 10,
+                    "vector": [],
+                    "with_row_id": true,
+                    "prefilter": true,
+                    "version": null
+                });
+                assert_eq!(body, expected_body);
+
+                let data = RecordBatch::try_new(
+                    Arc::new(Schema::new(vec![Field::new("a", DataType::Int32, false)])),
+                    vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
+                )
+                .unwrap();
+                let response_body = write_ipc_file(&data);
+                http::Response::builder()
+                    .status(200)
+                    .header(CONTENT_TYPE, ARROW_FILE_CONTENT_TYPE)
+                    .body(response_body)
+                    .unwrap()
+            });
+
+        let _ = table
+            .query()
+            .full_text_search(FullTextSearchQuery::new_query(
+                MatchQuery::new("hello world".to_owned())
+                    .with_column(Some("a".to_owned()))
+                    .into(),
+            ))
+            .with_row_id()
+            .limit(10)
+            .execute()
+            .await
+            .unwrap();
+    }
+
     #[rstest]
     #[case(DEFAULT_SERVER_VERSION.clone())]
     #[case(semver::Version::new(0, 2, 0))]

rust/lancedb/src/table.rs

@@ -68,7 +68,7 @@ use crate::query::{
 use crate::utils::{
     default_vector_column, supported_bitmap_data_type, supported_btree_data_type,
     supported_fts_data_type, supported_label_list_data_type, supported_vector_data_type,
-    PatchReadParam, PatchWriteParam,
+    PatchReadParam, PatchWriteParam, TimeoutStream,
 };
 
 use self::dataset::DatasetConsistencyWrapper;
@@ -1775,11 +1775,14 @@ impl NativeTable {
         query: &AnyQuery,
         options: QueryExecutionOptions,
     ) -> Result<DatasetRecordBatchStream> {
-        let plan = self.create_plan(query, options).await?;
+        let plan = self.create_plan(query, options.clone()).await?;
-        Ok(DatasetRecordBatchStream::new(execute_plan(
+        let inner = execute_plan(plan, Default::default())?;
-            plan,
+        let inner = if let Some(timeout) = options.timeout {
-            Default::default(),
+            TimeoutStream::new_boxed(inner, timeout)
-        )?))
+        } else {
+            inner
+        };
+        Ok(DatasetRecordBatchStream::new(inner))
     }
 
     /// Check whether the table uses V2 manifest paths.

rust/lancedb/src/table/dataset.rs

@@ -48,7 +48,6 @@ impl DatasetRef {
                 refresh_task,
                 ..
             } => {
-                dataset.checkout_latest().await?;
                 // Replace the refresh task
                 if let Some(refresh_task) = refresh_task {
                     refresh_task.abort();
@@ -372,3 +371,48 @@ impl DerefMut for DatasetWriteGuard<'_> {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use arrow_schema::{DataType, Field, Schema};
+    use lance::{dataset::WriteParams, io::ObjectStoreParams};
+
+    use super::*;
+
+    use crate::{connect, io::object_store::io_tracking::IoStatsHolder, table::WriteOptions};
+
+    #[tokio::test]
+    async fn test_iops_open_strong_consistency() {
+        let db = connect("memory://")
+            .read_consistency_interval(Some(Duration::ZERO))
+            .execute()
+            .await
+            .expect("Failed to connect to database");
+        let io_stats = IoStatsHolder::default();
+
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+
+        let table = db
+            .create_empty_table("test", schema)
+            .write_options(WriteOptions {
+                lance_write_params: Some(WriteParams {
+                    store_params: Some(ObjectStoreParams {
+                        object_store_wrapper: Some(Arc::new(io_stats.clone())),
+                        ..Default::default()
+                    }),
+                    ..Default::default()
+                }),
+            })
+            .execute()
+            .await
+            .unwrap();
+
+        io_stats.incremental_stats();
+
+        // We should only need 1 read IOP to check the schema: looking for the
+        // latest version.
+        table.schema().await.unwrap();
+        let stats = io_stats.incremental_stats();
+        assert_eq!(stats.read_iops, 1);
+    }
+}

rust/lancedb/src/utils.rs

@@ -3,14 +3,20 @@
 
 use std::sync::Arc;
 
-use arrow_schema::{DataType, Schema};
+use arrow_array::RecordBatch;
+use arrow_schema::{DataType, Schema, SchemaRef};
+use datafusion_common::{DataFusionError, Result as DataFusionResult};
+use datafusion_execution::RecordBatchStream;
+use futures::{FutureExt, Stream};
 use lance::arrow::json::JsonDataType;
 use lance::dataset::{ReadParams, WriteParams};
 use lance::index::vector::utils::infer_vector_dim;
 use lance::io::{ObjectStoreParams, WrappingObjectStore};
 use lazy_static::lazy_static;
+use std::pin::Pin;
 
 use crate::error::{Error, Result};
+use datafusion_physical_plan::SendableRecordBatchStream;
 
 lazy_static! {
     static ref TABLE_NAME_REGEX: regex::Regex = regex::Regex::new(r"^[a-zA-Z0-9_\-\.]+$").unwrap();
@@ -135,6 +141,7 @@ pub fn supported_btree_data_type(dtype: &DataType) -> bool {
                 | DataType::Date32
                 | DataType::Date64
                 | DataType::Timestamp(_, _)
+                | DataType::FixedSizeBinary(_)
         )
 }
 
@@ -151,7 +158,17 @@ pub fn supported_label_list_data_type(dtype: &DataType) -> bool {
 }
 
 pub fn supported_fts_data_type(dtype: &DataType) -> bool {
-    matches!(dtype, DataType::Utf8 | DataType::LargeUtf8)
+    supported_fts_data_type_impl(dtype, false)
+}
+
+fn supported_fts_data_type_impl(dtype: &DataType, in_list: bool) -> bool {
+    match (dtype, in_list) {
+        (DataType::Utf8 | DataType::LargeUtf8, _) => true,
+        (DataType::List(field) | DataType::LargeList(field), false) => {
+            supported_fts_data_type_impl(field.data_type(), true)
+        }
+        _ => false,
+    }
 }
 
 pub fn supported_vector_data_type(dtype: &DataType) -> bool {
@@ -177,11 +194,97 @@ pub fn string_to_datatype(s: &str) -> Option<DataType> {
     (&json_type).try_into().ok()
 }
 
+enum TimeoutState {
+    NotStarted {
+        timeout: std::time::Duration,
+    },
+    Started {
+        deadline: Pin<Box<tokio::time::Sleep>>,
+        timeout: std::time::Duration,
+    },
+    Completed,
+}
+
+/// A `Stream` wrapper that implements a timeout.
+///
+/// The timeout starts when the first `poll_next` is called. As soon as the timeout
+/// duration has passed, the stream will return an `Err` indicating a timeout error
+/// for the next poll.
+pub struct TimeoutStream {
+    inner: SendableRecordBatchStream,
+    state: TimeoutState,
+}
+
+impl TimeoutStream {
+    pub fn new(inner: SendableRecordBatchStream, timeout: std::time::Duration) -> Self {
+        Self {
+            inner,
+            state: TimeoutState::NotStarted { timeout },
+        }
+    }
+
+    pub fn new_boxed(
+        inner: SendableRecordBatchStream,
+        timeout: std::time::Duration,
+    ) -> SendableRecordBatchStream {
+        Box::pin(Self::new(inner, timeout))
+    }
+
+    fn timeout_error(timeout: &std::time::Duration) -> DataFusionError {
+        DataFusionError::Execution(format!("Query timeout after {} ms", timeout.as_millis()))
+    }
+}
+
+impl RecordBatchStream for TimeoutStream {
+    fn schema(&self) -> SchemaRef {
+        self.inner.schema()
+    }
+}
+
+impl Stream for TimeoutStream {
+    type Item = DataFusionResult<RecordBatch>;
+
+    fn poll_next(
+        mut self: std::pin::Pin<&mut Self>,
+        cx: &mut std::task::Context<'_>,
+    ) -> std::task::Poll<Option<Self::Item>> {
+        match &mut self.state {
+            TimeoutState::NotStarted { timeout } => {
+                if timeout.is_zero() {
+                    return std::task::Poll::Ready(Some(Err(Self::timeout_error(timeout))));
+                }
+                let deadline = Box::pin(tokio::time::sleep(*timeout));
+                self.state = TimeoutState::Started {
+                    deadline,
+                    timeout: *timeout,
+                };
+                self.poll_next(cx)
+            }
+            TimeoutState::Started { deadline, timeout } => match deadline.poll_unpin(cx) {
+                std::task::Poll::Ready(_) => {
+                    let err = Self::timeout_error(timeout);
+                    self.state = TimeoutState::Completed;
+                    std::task::Poll::Ready(Some(Err(err)))
+                }
+                std::task::Poll::Pending => {
+                    let inner = Pin::new(&mut self.inner);
+                    inner.poll_next(cx)
+                }
+            },
+            TimeoutState::Completed => std::task::Poll::Ready(None),
+        }
+    }
+}
+
 #[cfg(test)]
 mod tests {
-    use super::*;
+    use arrow_array::Int32Array;
+    use arrow_schema::Field;
+    use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
+    use futures::{stream, StreamExt};
+    use tokio::time::sleep;
 
-    use arrow_schema::{DataType, Field};
+    use super::*;
 
     #[test]
     fn test_guess_default_column() {
@@ -248,4 +351,85 @@ mod tests {
         let expected = DataType::Int32;
         assert_eq!(string_to_datatype(string), Some(expected));
     }
+
+    fn sample_batch() -> RecordBatch {
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            "col1",
+            DataType::Int32,
+            false,
+        )]));
+        RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
+        )
+        .unwrap()
+    }
+
+    #[tokio::test]
+    async fn test_timeout_stream() {
+        let batch = sample_batch();
+        let schema = batch.schema();
+        let mock_stream = stream::iter(vec![Ok(batch.clone()), Ok(batch.clone())]);
+
+        let sendable_stream: SendableRecordBatchStream =
+            Box::pin(RecordBatchStreamAdapter::new(schema.clone(), mock_stream));
+        let timeout_duration = std::time::Duration::from_millis(10);
+        let mut timeout_stream = TimeoutStream::new(sendable_stream, timeout_duration);
+
+        // Poll the stream to get the first batch
+        let first_result = timeout_stream.next().await;
+        assert!(first_result.is_some());
+        assert!(first_result.unwrap().is_ok());
+
+        // Sleep for the timeout duration
+        sleep(timeout_duration).await;
+
+        // Poll the stream again and ensure it returns a timeout error
+        let second_result = timeout_stream.next().await.unwrap();
+        assert!(second_result.is_err());
+        assert!(second_result
+            .unwrap_err()
+            .to_string()
+            .contains("Query timeout"));
+    }
+
+    #[tokio::test]
+    async fn test_timeout_stream_zero_duration() {
+        let batch = sample_batch();
+        let schema = batch.schema();
+        let mock_stream = stream::iter(vec![Ok(batch.clone()), Ok(batch.clone())]);
+
+        let sendable_stream: SendableRecordBatchStream =
+            Box::pin(RecordBatchStreamAdapter::new(schema.clone(), mock_stream));
+
+        // Setup similar to test_timeout_stream
+        let timeout_duration = std::time::Duration::from_secs(0);
+        let mut timeout_stream = TimeoutStream::new(sendable_stream, timeout_duration);
+
+        // First poll should immediately return a timeout error
+        let result = timeout_stream.next().await.unwrap();
+        assert!(result.is_err());
+        assert!(result.unwrap_err().to_string().contains("Query timeout"));
+    }
+
+    #[tokio::test]
+    async fn test_timeout_stream_completes_normally() {
+        let batch = sample_batch();
+        let schema = batch.schema();
+        let mock_stream = stream::iter(vec![Ok(batch.clone()), Ok(batch.clone())]);
+
+        let sendable_stream: SendableRecordBatchStream =
+            Box::pin(RecordBatchStreamAdapter::new(schema.clone(), mock_stream));
+
+        // Setup a stream with 2 batches
+        // Use a longer timeout that won't trigger
+        let timeout_duration = std::time::Duration::from_secs(1);
+        let mut timeout_stream = TimeoutStream::new(sendable_stream, timeout_duration);
+
+        // Both polls should return data normally
+        assert!(timeout_stream.next().await.unwrap().is_ok());
+        assert!(timeout_stream.next().await.unwrap().is_ok());
+        // Stream should be empty now
+        assert!(timeout_stream.next().await.is_none());
+    }
 }