Feat: add OceanBase doc engine

common/settings.py

@@ -27,6 +27,7 @@
 import rag.utils
 import rag.utils.es_conn
 import rag.utils.infinity_conn
+import rag.utils.ob_conn
 import rag.utils.opensearch_conn
 from rag.utils.azure_sas_conn import RAGFlowAzureSasBlob
 from rag.utils.azure_spn_conn import RAGFlowAzureSpnBlob
@@ -103,6 +104,7 @@
 AZURE = {}
 S3 = {}
 MINIO = {}
+OB = {}
 OSS = {}
 OS = {}
 
@@ -227,7 +229,7 @@ def init_settings():
     FEISHU_OAUTH = get_base_config("oauth", {}).get("feishu")
     OAUTH_CONFIG = get_base_config("oauth", {})
 
-    global DOC_ENGINE, docStoreConn, ES, OS, INFINITY
+    global DOC_ENGINE, docStoreConn, ES, OB, OS, INFINITY
     DOC_ENGINE = os.environ.get("DOC_ENGINE", "elasticsearch")
     # DOC_ENGINE = os.environ.get('DOC_ENGINE', "opensearch")
     lower_case_doc_engine = DOC_ENGINE.lower()
@@ -240,6 +242,9 @@ def init_settings():
     elif lower_case_doc_engine == "opensearch":
         OS = get_base_config("os", {})
         docStoreConn = rag.utils.opensearch_conn.OSConnection()
+    elif lower_case_doc_engine == "oceanbase":
+        OB = get_base_config("oceanbase", {})
+        docStoreConn = rag.utils.ob_conn.OBConnection()
     else:
         raise Exception(f"Not supported doc engine: {DOC_ENGINE}")
 

conf/service_conf.yaml

@@ -28,6 +28,14 @@ os:
 infinity:
   uri: 'localhost:23817'
   db_name: 'default_db'
+oceanbase:
+  scheme: 'oceanbase' # set 'mysql' to create connection using mysql config
+  config:
+    db_name: 'test'
+    user: 'root@ragflow'
+    password: 'infini_rag_flow'
+    host: 'localhost'
+    port: 2881
 redis:
   db: 1
   password: 'infini_rag_flow'

docker/.env

@@ -7,6 +7,7 @@
 # Available options:
 # - `elasticsearch` (default)
 # - `infinity` (https://github.com/infiniflow/infinity)
+# - `oceanbase` (https://github.com/oceanbase/oceanbase)
 # - `opensearch` (https://github.com/opensearch-project/OpenSearch)
 DOC_ENGINE=${DOC_ENGINE:-elasticsearch}
 
@@ -62,6 +63,27 @@ INFINITY_THRIFT_PORT=23817
 INFINITY_HTTP_PORT=23820
 INFINITY_PSQL_PORT=5432
 
+# The hostname where the OceanBase service is exposed
+OCEANBASE_HOST=oceanbase
+# The port used to expose the OceanBase service
+OCEANBASE_PORT=2881
+# The username for OceanBase
+OCEANBASE_USER=root@ragflow
+# The password for OceanBase
+OCEANBASE_PASSWORD=infini_rag_flow
+# The doc database of the OceanBase service to use
+OCEANBASE_DOC_DBNAME=ragflow_doc
+
+# OceanBase container configuration
+OB_CLUSTER_NAME=${OB_CLUSTER_NAME:-ragflow}
+OB_TENANT_NAME=${OB_TENANT_NAME:-ragflow}
+OB_SYS_PASSWORD=${OCEANBASE_PASSWORD:-infini_rag_flow}
+OB_TENANT_PASSWORD=${OCEANBASE_PASSWORD:-infini_rag_flow}
+OB_MEMORY_LIMIT=${OB_MEMORY_LIMIT:-10G}
+OB_SYSTEM_MEMORY=${OB_SYSTEM_MEMORY:-2G}
+OB_DATAFILE_SIZE=${OB_DATAFILE_SIZE:-20G}
+OB_LOG_DISK_SIZE=${OB_LOG_DISK_SIZE:-20G}
+
 # The password for MySQL.
 MYSQL_PASSWORD=infini_rag_flow
 # The hostname where the MySQL service is exposed

docker/README.md

@@ -138,6 +138,15 @@ The [.env](./.env) file contains important environment variables for Docker.
   - `password`: The password for MinIO.
   - `host`: The MinIO serving IP *and* port inside the Docker container. Defaults to `minio:9000`.
 
+- `oceanbase`
+  - `scheme`: The connection scheme. Set to `mysql` to use mysql config, or other values to use config below.
+  - `config`:
+    - `db_name`: The OceanBase database name.
+    - `user`: The username for OceanBase.
+    - `password`: The password for OceanBase.
+    - `host`: The hostname of the OceanBase service.
+    - `port`: The port of OceanBase.
+
 - `oss`
   - `access_key`: The access key ID used to authenticate requests to the OSS service.
   - `secret_key`: The secret access key used to authenticate requests to the OSS service.

docker/docker-compose-base.yml

@@ -96,6 +96,31 @@ services:
       retries: 120
     restart: on-failure
 
+  oceanbase:
+    profiles:
+      - oceanbase
+    image: oceanbase/oceanbase-ce:4.4.1.0-100000032025101610
+    volumes:
+      - ./oceanbase/data:/root/ob
+      - ./oceanbase/conf:/root/.obd/cluster
+      - ./oceanbase/init.d:/root/boot/init.d
+    ports:
+      - ${OCEANBASE_PORT:-2881}:2881
+    env_file: .env
+    environment:
+      - MODE=normal
+      - OB_SERVER_IP=127.0.0.1
+    mem_limit: ${MEM_LIMIT}
+    healthcheck:
+      test: [ 'CMD-SHELL', 'obclient -h127.0.0.1 -P2881 -uroot@${OB_TENANT_NAME:-ragflow} -p${OB_TENANT_PASSWORD:-infini_rag_flow} -e "CREATE DATABASE IF NOT EXISTS ${OCEANBASE_DOC_DBNAME:-ragflow_doc};"' ]
+      interval: 10s
+      retries: 30
+      start_period: 30s
+      timeout: 10s
+    networks:
+      - ragflow
+    restart: on-failure
+
   sandbox-executor-manager:
     profiles:
       - sandbox
@@ -256,6 +281,8 @@ volumes:
     driver: local
   infinity_data:
     driver: local
+  ob_data:
+    driver: local
   mysql_data:
     driver: local
   minio_data:

docker/oceanbase/init.d/vec_memory.sql

@@ -0,0 +1 @@
+ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;

docker/service_conf.yaml.template

@@ -28,6 +28,14 @@ os:
 infinity:
   uri: '${INFINITY_HOST:-infinity}:23817'
   db_name: 'default_db'
+oceanbase:
+  scheme: 'oceanbase' # set 'mysql' to create connection using mysql config
+  config:
+    db_name: '${OCEANBASE_DOC_DBNAME:-test}'
+    user: '${OCEANBASE_USER:-root@ragflow}'
+    password: '${OCEANBASE_PASSWORD:-infini_rag_flow}'
+    host: '${OCEANBASE_HOST:-oceanbase}'
+    port: ${OCEANBASE_PORT:-2881}
 redis:
   db: 1
   password: '${REDIS_PASSWORD:-infini_rag_flow}'

pyproject.toml

@@ -146,6 +146,7 @@ dependencies = [
     "captcha>=0.7.1",
     "pip>=25.2",
     "pypandoc>=1.16",
+    "pyobvector==0.2.18",
 ]
 
 [dependency-groups]

rag/nlp/query.py

@@ -83,6 +83,7 @@ def add_space_between_eng_zh(txt):
         return txt
 
     def question(self, txt, tbl="qa", min_match: float = 0.6):
+        original_query = txt
         txt = FulltextQueryer.add_space_between_eng_zh(txt)
         txt = re.sub(
             r"[ :|\r\n\t,，。？?/`!！&^%%()\[\]{}<>]+",
@@ -127,7 +128,7 @@ def question(self, txt, tbl="qa", min_match: float = 0.6):
                 q.append(txt)
             query = " ".join(q)
             return MatchTextExpr(
-                self.query_fields, query, 100
+                self.query_fields, query, 100, {"original_query": original_query}
             ), keywords
 
         def need_fine_grained_tokenize(tk):
@@ -212,7 +213,7 @@ def need_fine_grained_tokenize(tk):
             if not query:
                 query = otxt
             return MatchTextExpr(
-                self.query_fields, query, 100, {"minimum_should_match": min_match}
+                self.query_fields, query, 100, {"minimum_should_match": min_match, "original_query": original_query}
             ), keywords
         return None, keywords
 
@@ -259,6 +260,7 @@ def paragraph(self, content_tks: str, keywords: list = [], keywords_topn=30):
             content_tks = [c.strip() for c in content_tks.strip() if c.strip()]
         tks_w = self.tw.weights(content_tks, preprocess=False)
 
+        origin_keywords = keywords.copy()
         keywords = [f'"{k.strip()}"' for k in keywords]
         for tk, w in sorted(tks_w, key=lambda x: x[1] * -1)[:keywords_topn]:
             tk_syns = self.syn.lookup(tk)
@@ -274,4 +276,4 @@ def paragraph(self, content_tks: str, keywords: list = [], keywords_topn=30):
                 keywords.append(f"{tk}^{w}")
 
         return MatchTextExpr(self.query_fields, " ".join(keywords), 100,
-                             {"minimum_should_match": min(3, len(keywords) // 10)})
+                             {"minimum_should_match": min(3, len(keywords) / 10), "original_query": " ".join(origin_keywords)})