feat(serenedb): add SereneDB doc-store engine (Go + Python connectors) (#17375)

## 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>
This commit is contained in:
deadtrickster
2026-08-04 08:16:39 +02:00
committed by GitHub
parent 74f6355791
commit 197b142cef
26 changed files with 3933 additions and 12 deletions

View File

@@ -23,6 +23,7 @@ import (
type DocEngineConfig struct {
ES ElasticsearchConfig `mapstructure:"es"`
Infinity InfinityConfig `mapstructure:"infinity"`
SereneDB SereneDBConfig `mapstructure:"serenedb"`
}
// ElasticsearchConfig Elasticsearch configuration
@@ -41,12 +42,66 @@ type InfinityConfig struct {
DocMetaMappingFileName string `mapstructure:"doc_meta_mapping_file_name"`
}
// SereneDBConfig SereneDB configuration. SereneDB speaks the PostgreSQL wire
// protocol, so the engine connects with database/sql + lib/pq.
type SereneDBConfig struct {
Host string `mapstructure:"host"`
Port int `mapstructure:"port"`
User string `mapstructure:"user"`
Password string `mapstructure:"password"`
DBName string `mapstructure:"db_name"`
// SSLMode is the lib/pq sslmode; empty defaults to "disable" for a trusted
// local deployment. Set it (e.g. "require") to encrypt the connection.
SSLMode string `mapstructure:"ssl_mode"`
}
func (c *Config) ParseDocEngineConfig(v *viper.Viper) error {
c.parseInfinityConfig(v)
c.parseElasticsearchConfig(v)
c.parseSereneDBConfig(v)
return nil
}
func (c *Config) parseSereneDBConfig(v *viper.Viper) {
// Default SereneDB config
c.docEngine.SereneDB.Host = "localhost"
c.docEngine.SereneDB.Port = 5432
c.docEngine.SereneDB.User = "postgres"
c.docEngine.SereneDB.DBName = "default_db"
if !v.IsSet("serenedb") {
return
}
sub := v.Sub("serenedb")
if sub == nil {
return
}
if sub.IsSet("host") {
c.docEngine.SereneDB.Host = sub.GetString("host")
}
if sub.IsSet("port") {
c.docEngine.SereneDB.Port = sub.GetInt("port")
}
if sub.IsSet("user") {
c.docEngine.SereneDB.User = sub.GetString("user")
}
if sub.IsSet("password") {
c.docEngine.SereneDB.Password = sub.GetString("password")
}
if sub.IsSet("db_name") {
c.docEngine.SereneDB.DBName = sub.GetString("db_name")
}
if sub.IsSet("ssl_mode") {
c.docEngine.SereneDB.SSLMode = sub.GetString("ssl_mode")
}
}
func (c *Config) parseInfinityConfig(v *viper.Viper) {
// Default Infinity config
c.docEngine.Infinity.URI = "localhost:23817"
@@ -142,3 +197,7 @@ func (i InfinityConfig) ExportConfigs() map[string]interface{} {
infinityConfigs["doc_meta_mapping_file_name"] = i.DocMetaMappingFileName
return infinityConfigs
}
func (c *Config) GetSereneDBConfig() SereneDBConfig {
return c.docEngine.SereneDB
}