- Update version tags in README files (including translations) from
v0.27.1 to v0.27.2
- Modify Docker image references and documentation to reflect new
version
- Update version badges and image descriptions
- Maintain consistency across all language variants of README files
Fix OAuth callback URL examples in docs — now use /api/v1/auth/oauth/<channel>/callback (was stale /v1/user/oauth/callback).
Co-authored-by: 谢金城 <xiejincheng@xgd.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### Summary
Both configuration guides document the API server's port as `port`:
- `docs/administrator/configurations/configurations.md:152`
- `docker/README.md:190`
The key in `docker/service_conf.yaml.template:5` is `http_port`
## Summary
Fix entrypoint.sh restart loops where non-zero exits would terminate the subshell instead of retrying (root cause of #18542). Now wraps each binary with set +e / set -e to capture exit status and log it before restarting. Applied to 6 loops. Complementary to #17196.
Co-authored-by: skbs-eng <skbs-eng@users.noreply.github.com>
### Summary
download_deps.py downloads NLTK data into ragflow_deps/nltk_data (see
ragflow_deps/download_deps.py); point NLTK_DATA there directly instead
of a stale top-level ./nltk_data so this matches what's actually
populated.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
configurations.md and backup_and_migration.md cross-linked each other
via /migration#... and /configurations#s3-tigris. These host-absolute
paths match no route on the docs site (real pages live under
/administrator/...) and 404 on GitHub. Point them at the sibling
markdown files so both Docusaurus and GitHub can resolve them; the
existing anchors are preserved.
---------
Co-authored-by: jindou <jindou@local>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.26.4 to v0.27.0
- Modify Docker image references and documentation to reflect new
version
- Update version badges and image descriptions
- Maintain consistency across all language variants of README files
### Type of change
- [x] Documentation Update
### Summary
Closes#18019.
Pigsty renamed its community MinIO fork from `pgsty/minio` to
`pgsty/silo` on 2026-08-06 ([announcement in the repo
README](https://github.com/pgsty/silo#readme)). `pgsty/minio` is frozen
at `RELEASE.2026-08-04T00-00-00Z` — all further releases, including
security fixes, ship as `pgsty/silo`. RAGFlow still pins the old name,
so it is now parked on an image that no longer gets updates.
## Problem
In the default deployment (`API_PROXY_SCHEME=python`), the nginx config
generated from `docker/nginx/ragflow.conf.python` uses:
```nginx
proxy_pass http://localhost:9381; # admin
proxy_pass http://localhost:9380; # api
```
Inside the RAGFlow container, `/etc/hosts` maps `localhost` to both
`127.0.0.1` and `::1`:
```
127.0.0.1 localhost
::1 localhost ip6-localhost ip6-loopback
```
But the backend services (`ragflow_server.py` on 9380, admin server on
9381) only listen on IPv4 (`127.0.0.1`). When nginx resolves `localhost`
to `::1`, the upstream connection fails and nginx falls back to the IPv4
address - each fallback adds ~1 second of latency.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Ports dataset knowledge compilation (wiki/graph/tree/mindmap) to the Go
scheduler with a status contract, aligns wiki storage/retrieval with
Python, sizes prompts by content_length, and resolves embedding batch
size from provider capability.
Ports the dataset knowledge compilation (wiki/graph/tree/mindmap) to the
Go scheduler with a status contract, aligns wiki storage/retrieval with
Python, and sizes prompts by content_length.
## 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>
xugangqiang
Liu An
Lynn
Wang Qi
Yuanhao Lyu
maoyifeng
buua436
jay77721
Leon Yin
MarMar Labs
Sandskbs-eng
Paul Y HuiandJin Hai
Rootkit
zws202606
Mpider-San
Haruko386
qinling0210
YeeandJin Hai
Zhichang Yu
deadtricksterandClaude Opus 4.8
euvre