From d0a8dde12c98cfe6671749e9a04a9c76cae4c29e Mon Sep 17 00:00:00 2001 From: "hotdata-automation[bot]" <267177015+hotdata-automation[bot]@users.noreply.github.com> Date: Thu, 15 Oct 2026 05:57:59 +0000 Subject: [PATCH] feat(query): add arrow ipc stream response format --- CHANGELOG.md | 1 + docs/QueryApi.md | 4 ++-- src/apis/query_api.rs | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7aadda4..42bb0c6 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed +- feat(query): add arrow ipc stream response format - chore(query): clarify write statement handling in dialect parameter - chore(indexes): clarify vector index constraints and algorithms - chore(indexes): clarify vector precision documentation diff --git a/docs/QueryApi.md b/docs/QueryApi.md index ec7e9ab..652a1b6 100644 --- a/docs/QueryApi.md +++ b/docs/QueryApi.md @@ -13,7 +13,7 @@ Method | HTTP request | Description > models::QueryResponse query(query_request, x_database_id) Execute SQL query -Execute a SQL query scoped to a database. A database is the only window into catalogs: the query sees only that database's auto `default` catalog plus any catalogs explicitly attached to it. Select the database with EITHER the `X-Database-Id` header OR the `database_id` body field (exactly one must be given; if both are sent and disagree, that's a 400). Use standard Postgres-compatible SQL; reference the default catalog as `default..` (or just `.
` / `
`) and attached catalogs by their alias. Results are returned inline and a `result_id` is provided for later retrieval via the Results API. Set `async: true` to execute asynchronously — returns a query run ID for polling. Optionally set `async_after_ms` to attempt synchronous execution first, falling back to async if the query exceeds the timeout. +Execute a SQL query scoped to a database. A database is the only window into catalogs: the query sees only that database's auto `default` catalog plus any catalogs explicitly attached to it. Select the database with EITHER the `X-Database-Id` header OR the `database_id` body field (exactly one must be given; if both are sent and disagree, that's a 400). Use standard Postgres-compatible SQL; reference the default catalog as `default..
` (or just `.
` / `
`) and attached catalogs by their alias. Results are returned inline and a `result_id` is provided for later retrieval via the Results API. Set `async: true` to execute asynchronously — returns a query run ID for polling. Optionally set `async_after_ms` to attempt synchronous execution first, falling back to async if the query exceeds the timeout. To receive the rows as an Arrow IPC stream instead of JSON, send `Accept: application/vnd.apache.arrow.stream` (without also listing `application/json`). A query that completes within the request then returns 200 with an Arrow IPC stream body (schema, record batches, end-of-stream), and the values the JSON body would carry are sent as response headers: `X-Query-Run-Id`, `X-Result-Id` (when the result was saved), `X-Total-Row-Count`, `X-Execution-Time-Ms`, and `X-Query-Warning` (when there is a warning). Arrow keeps `±Inf` and `NaN` float values as they are. An Arrow response always holds the whole result: if the result is larger than an inline response can hold, the request returns 202 with the query run ticket and an `X-Result-Id` header instead, and the full result is read from `GET /v1/results/{id}?format=arrow` once it is ready. A query that goes async, and every error, return the same JSON bodies as without the header. ### Parameters @@ -34,7 +34,7 @@ Name | Type | Description | Required | Notes ### HTTP request headers - **Content-Type**: application/json -- **Accept**: application/json +- **Accept**: application/json, application/vnd.apache.arrow.stream [[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md) diff --git a/src/apis/query_api.rs b/src/apis/query_api.rs index ea1f1c3..47015a8 100644 --- a/src/apis/query_api.rs +++ b/src/apis/query_api.rs @@ -25,7 +25,7 @@ pub enum QueryError { UnknownValue(serde_json::Value), } -/// Execute a SQL query scoped to a database. A database is the only window into catalogs: the query sees only that database's auto `default` catalog plus any catalogs explicitly attached to it. Select the database with EITHER the `X-Database-Id` header OR the `database_id` body field (exactly one must be given; if both are sent and disagree, that's a 400). Use standard Postgres-compatible SQL; reference the default catalog as `default..
` (or just `.
` / `
`) and attached catalogs by their alias. Results are returned inline and a `result_id` is provided for later retrieval via the Results API. Set `async: true` to execute asynchronously — returns a query run ID for polling. Optionally set `async_after_ms` to attempt synchronous execution first, falling back to async if the query exceeds the timeout. +/// Execute a SQL query scoped to a database. A database is the only window into catalogs: the query sees only that database's auto `default` catalog plus any catalogs explicitly attached to it. Select the database with EITHER the `X-Database-Id` header OR the `database_id` body field (exactly one must be given; if both are sent and disagree, that's a 400). Use standard Postgres-compatible SQL; reference the default catalog as `default..
` (or just `.
` / `
`) and attached catalogs by their alias. Results are returned inline and a `result_id` is provided for later retrieval via the Results API. Set `async: true` to execute asynchronously — returns a query run ID for polling. Optionally set `async_after_ms` to attempt synchronous execution first, falling back to async if the query exceeds the timeout. To receive the rows as an Arrow IPC stream instead of JSON, send `Accept: application/vnd.apache.arrow.stream` (without also listing `application/json`). A query that completes within the request then returns 200 with an Arrow IPC stream body (schema, record batches, end-of-stream), and the values the JSON body would carry are sent as response headers: `X-Query-Run-Id`, `X-Result-Id` (when the result was saved), `X-Total-Row-Count`, `X-Execution-Time-Ms`, and `X-Query-Warning` (when there is a warning). Arrow keeps `±Inf` and `NaN` float values as they are. An Arrow response always holds the whole result: if the result is larger than an inline response can hold, the request returns 202 with the query run ticket and an `X-Result-Id` header instead, and the full result is read from `GET /v1/results/{id}?format=arrow` once it is ready. A query that goes async, and every error, return the same JSON bodies as without the header. pub async fn query( configuration: &configuration::Configuration, query_request: models::QueryRequest,