mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-04 23:00:30 +08:00
197b142cef
## What Adds [**SereneDB**](https://serenedb.com) as a selectable doc-store engine on **both** RAGFlow paths: - the **Go** `DocEngine` (`internal/engine/serenedb`), alongside Elasticsearch and Infinity; - the **Python** `DocStoreConnection` (`rag/utils/serenedb_conn.py`) + `DOC_ENGINE=serenedb` registration. SereneDB is a PostgreSQL-wire engine (DuckDB execution) whose single inverted index carries **both** a scored text column (`@@`, BM25) and an IVF vector column (`<#>`, inner product), so hybrid search is one SQL statement. The Go engine connects with `database/sql` + `lib/pq` (already a dependency, no new module); the Python connector uses psycopg2 (already a dependency). ## Storage model One table per tenant with `kb_id` as a filter column - the **Elasticsearch / OceanBase** model, not Infinity's per-dataset tables. This keeps BM25 statistics (IDF, avgdl) computed over the whole tenant corpus (global IDF). Both connectors use this identical layout, so they are storage- and retrieval-compatible: `hybrid` proxy routing and Python↔Go switching are safe. On the Python side the connector is wired as OceanBase's plain-SQL sibling (chunk_data JSON metadata, inline chunk vectors, verbatim ES field names); the ES tokenizer path is unchanged. Metadata stays one table per tenant (`ragflow_doc_meta_<tenant>`). The query shapes mirror the Python connector, including the five empirically-found landmines: the scored dictionary needs `frequency + norm` (else `BM25()` silently returns 0.0), the `@@` query is the tokenized query, the scored lexical branch matches one column, vectors use an L2-normalized shadow column with `ip`/`sq8`, and the similarity threshold goes directly in the ANN scan's `WHERE`. **Minimum engine version: SereneDB 26.07.4.** --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
59 lines
1.9 KiB
Go
59 lines
1.9 KiB
Go
//
|
|
// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
//
|
|
|
|
package serenedb
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"regexp"
|
|
"strings"
|
|
)
|
|
|
|
const runSQLDefaultLimit = 1024
|
|
|
|
var (
|
|
selectPrefixRe = regexp.MustCompile(`(?i)^(select|with)\b`)
|
|
hasLimitRe = regexp.MustCompile(`(?i)\blimit\b`)
|
|
)
|
|
|
|
// boundRunSQL trims a statement and appends a default LIMIT to unbounded
|
|
// SELECT/WITH queries so the text-to-SQL path cannot stream an entire table.
|
|
// Pure for tests.
|
|
func boundRunSQL(sqlText string, limit int) string {
|
|
txt := strings.TrimSpace(sqlText)
|
|
txt = strings.TrimRight(txt, ";")
|
|
if limit > 0 && selectPrefixRe.MatchString(txt) && !hasLimitRe.MatchString(txt) {
|
|
txt = fmt.Sprintf("%s LIMIT %d", txt, limit)
|
|
}
|
|
return txt
|
|
}
|
|
|
|
// RunSQL executes a text-to-SQL query directly against SereneDB and returns the
|
|
// rows as maps. SereneDB speaks SQL natively, so unlike the Infinity engine no
|
|
// psql subprocess or field-alias rewrite is needed.
|
|
func (e *serenedbEngine) RunSQL(ctx context.Context, tableName string, sqlText string, kbIDs []string, format string) ([]map[string]interface{}, error) {
|
|
query := boundRunSQL(sqlText, runSQLDefaultLimit)
|
|
rows, err := e.queryMaps(ctx, query)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("serenedb: run sql: %w", err)
|
|
}
|
|
if rows == nil {
|
|
rows = []map[string]interface{}{}
|
|
}
|
|
return rows, nil
|
|
}
|