mirror of
https://github.com/scylladb/scylladb.git
synced 2026-04-22 01:20:39 +00:00
aea7b6a66b
Add to DescribeTable's output for VectorIndexes two fields - IndexStatus and Backfilling - which are intended to exactly mirror these two fields that exist for GlobalSecondaryIndexes: When a vector index is added, IndexStatus is "CREATING" before the index is usable, and "ACTIVE" when it is finally usable for a Query. During "CREATING" phase, "Backfilling" may be set to true when the index is currently being backfilled (the table is scaned and an index is built). A user is expected to call DescribeTable in a loop after creating a vector index (via either CreateTable and UpdateTable) and only call Query on the index after the IndexStatus is finally ACTIVE. Calling Query earlier, while IndexStatus is still CREATING, will result in an error. In the current implementation, Alternator does not track the state of the vector index, so it needs to contact the vector store to inquire about the state of the index - using a new function introduced in this patch that uses an existing vector-store API. This makes DescribeTable slower on tables that have vector indexes, because the vector store is contacted on every DescribeTable call. Signed-off-by: Nadav Har'El <nyh@scylladb.com>
111 lines
3.8 KiB
C++
111 lines
3.8 KiB
C++
/*
|
|
* Copyright (C) 2025-present ScyllaDB
|
|
*/
|
|
|
|
/*
|
|
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.1
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "dht/decorated_key.hh"
|
|
#include "keys/keys.hh"
|
|
#include "seastarx.hh"
|
|
#include "error.hh"
|
|
#include "utils/rjson.hh"
|
|
#include <seastar/core/shared_future.hh>
|
|
#include <seastar/core/shared_ptr.hh>
|
|
#include <seastar/http/reply.hh>
|
|
#include <seastar/core/sharded.hh>
|
|
#include <expected>
|
|
|
|
class schema;
|
|
namespace db {
|
|
class config;
|
|
}
|
|
|
|
namespace seastar::net {
|
|
class inet_address;
|
|
}
|
|
|
|
namespace vector_search {
|
|
|
|
struct primary_key {
|
|
dht::decorated_key partition;
|
|
clustering_key_prefix clustering;
|
|
};
|
|
|
|
/// A client with the vector-store service.
|
|
class vector_store_client final : public seastar::peering_sharded_service<vector_store_client> {
|
|
struct impl;
|
|
std::unique_ptr<impl> _impl;
|
|
|
|
public:
|
|
using config = db::config;
|
|
using vs_vector = std::vector<float>;
|
|
using host_name = sstring;
|
|
using index_name = sstring;
|
|
using keyspace_name = sstring;
|
|
using limit = std::size_t;
|
|
using port_number = std::uint16_t;
|
|
using primary_keys = std::vector<primary_key>;
|
|
using schema_ptr = lw_shared_ptr<schema const>;
|
|
using status_type = http::reply::status_type;
|
|
|
|
using disabled = disabled_error;
|
|
using aborted = aborted_error;
|
|
using addr_unavailable = addr_unavailable_error;
|
|
using service_unavailable = service_unavailable_error;
|
|
using service_error = service_error;
|
|
using service_reply_format_error = service_reply_format_error;
|
|
|
|
using ann_error = std::variant<disabled, aborted, addr_unavailable, service_unavailable, service_error, service_reply_format_error>;
|
|
using ann_error_visitor = error_visitor;
|
|
|
|
explicit vector_store_client(config const& cfg);
|
|
~vector_store_client();
|
|
|
|
/// Start background tasks.
|
|
void start_background_tasks();
|
|
|
|
/// Stop the service.
|
|
auto stop() -> future<>;
|
|
|
|
/// Check if the vector_store_client is disabled.
|
|
auto is_disabled() const -> bool;
|
|
|
|
/// The operational status of a single vector index, as reported by the vector store.
|
|
enum class index_status {
|
|
/// The index is not yet ready: initializing, not yet discovered, or the
|
|
/// vector store is unreachable.
|
|
creating,
|
|
/// The index is performing the initial full scan of the base table
|
|
/// (backfilling). Queries may be served but results are incomplete.
|
|
backfilling,
|
|
/// The index has completed the initial scan and is fully operational.
|
|
serving,
|
|
};
|
|
|
|
/// Query the vector store for the current status of a specific vector index.
|
|
auto get_index_status(keyspace_name keyspace, index_name name, abort_source& as) -> future<index_status>;
|
|
|
|
/// Request the vector store service for the primary keys of the nearest neighbors
|
|
auto ann(keyspace_name keyspace, index_name name, schema_ptr schema, vs_vector vs_vector, limit limit, const rjson::value& filter, abort_source& as)
|
|
-> future<std::expected<primary_keys, ann_error>>;
|
|
|
|
private:
|
|
friend struct vector_store_client_tester;
|
|
};
|
|
|
|
/// A tester for the vector_store_client, used for testing purposes.
|
|
struct vector_store_client_tester {
|
|
static void set_dns_refresh_interval(vector_store_client& vsc, std::chrono::milliseconds interval);
|
|
static void set_wait_for_client_timeout(vector_store_client& vsc, std::chrono::milliseconds timeout);
|
|
static void set_dns_resolver(vector_store_client& vsc, std::function<future<std::vector<net::inet_address>>(sstring const&)> resolver);
|
|
static void trigger_dns_resolver(vector_store_client& vsc);
|
|
static auto resolve_hostname(vector_store_client& vsc, abort_source& as) -> future<std::vector<net::inet_address>>;
|
|
static unsigned truststore_reload_count(vector_store_client& vsc);
|
|
};
|
|
|
|
} // namespace vector_search
|