feat: add bytehouse as graph database backend#1509
Open
white-cc wants to merge 1 commit into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Adds ByteHouse (ClickHouse-compatible) as an additional memos.graph_dbs backend, wiring it into the config system and backend factory so it can be selected via API/env configuration.
Changes:
- Introduce
ByteHouseGraphDBimplementation (DDL, node/edge ops, vector search, counts, export/import). - Add
ByteHouseGraphDBConfigand register"bytehouse"in graph DB config + factory maps. - Add API config builder +
.env.examplevariables and a new ByteHouse test module.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 14 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/graph_dbs/test_bytehouse.py | Adds ByteHouse backend tests (currently unguarded integration-style). |
| src/memos/graph_dbs/factory.py | Registers "bytehouse" backend in GraphStoreFactory. |
| src/memos/graph_dbs/bytehouse.py | Implements ByteHouse graph DB backend (schema, CRUD, search, utilities). |
| src/memos/configs/graph_db.py | Adds ByteHouseGraphDBConfig and registers it in config factory. |
| src/memos/api/handlers/config_builders.py | Exposes ByteHouse config in API graph DB config builder. |
| src/memos/api/config.py | Adds APIConfig.get_bytehouse_config() and includes ByteHouse in backend map. |
| docker/.env.example | Documents ByteHouse-related environment variables. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+864
to
+886
| def get_bytehouse_config(user_id: str | None = None) -> dict[str, Any]: | ||
| """Get ByteHouse configuration.""" | ||
| use_multi_db = os.getenv("BYTEHOUSE_USE_MULTI_DB", "false").lower() == "true" | ||
|
|
||
| if use_multi_db: | ||
| db_name = f"memos{user_id.replace('-', '')}" if user_id else "memos_default" | ||
| else: | ||
| db_name = os.getenv("BYTEHOUSE_DB_NAME", "shared_memos_db") | ||
| user_name = ( | ||
| f"memos{user_id.replace('-', '')}" if user_id else "memos_default" | ||
| ) | ||
|
|
||
| return { | ||
| "host": os.getenv("BYTEHOUSE_HOST", "localhost"), | ||
| "port": int(os.getenv("BYTEHOUSE_PORT", "9000")), | ||
| "user": os.getenv("BYTEHOUSE_USER", "default"), | ||
| "password": os.getenv("BYTEHOUSE_PASSWORD", ""), | ||
| "db_name": db_name, | ||
| "user_name": user_name, | ||
| "use_multi_db": use_multi_db, | ||
| "auto_create": True, | ||
| "embedding_dimension": int(os.getenv("EMBEDDING_DIMENSION", "1024")), | ||
| } |
Comment on lines
+49
to
+58
| # Create ClickHouse client | ||
| self.client = clickhouse_connect.get_client( | ||
| host=config.host, | ||
| port=config.port, | ||
| username="bytehouse", | ||
| password=config.password, | ||
| secure=True, | ||
| compress=False, | ||
| autogenerate_session_id=False, | ||
| ) |
Comment on lines
+142
to
+149
| def _build_user_name_and_kb_ids_condition( | ||
| self, user_name: str, knowledgebase_ids: list[str] | ||
| ) -> str: | ||
| """Build ClickHouse condition for user_name and knowledgebase_ids.""" | ||
| if not knowledgebase_ids: | ||
| return f"user_name = '{user_name}'" | ||
| else: | ||
| return f"user_name IN ['{'\',\''.join(knowledgebase_ids)}','{user_name}']" |
Comment on lines
+338
to
+346
| # Delete edges using INSERT with _delete_flag_ = 1 (only unique key needed) | ||
| if edge_result: | ||
| edge_values = [(edge_id, user_name, 1) for (edge_id) in edge_result] | ||
| self.client.insert( | ||
| f"{self.db_name}.edges", | ||
| edge_values, | ||
| column_names=["id", "user_name", "_delete_flag_"], | ||
| column_type_names=["String", "String", "UInt8"], | ||
| ) |
| for row in result: | ||
| result_set.add(row[0]) | ||
| result_set.add(row[1]) | ||
| result_set.remove(id) |
Comment on lines
+681
to
+709
| def get_by_metadata( | ||
| self, | ||
| filters: list[dict[str, Any]], | ||
| status: str | None = None, | ||
| user_name: str | None = None, | ||
| filter: dict | None = None, | ||
| knowledgebase_ids: list[str] | None = None, | ||
| user_name_flag: bool = True, | ||
| ) -> list[str]: | ||
| """Get node IDs matching metadata filters.""" | ||
| user_name = user_name or self.user_name | ||
|
|
||
| conditions = [] | ||
| params = {} | ||
|
|
||
| conditions.append( | ||
| self._build_user_name_and_kb_ids_condition(user_name, knowledgebase_ids) | ||
| ) | ||
|
|
||
| if status: | ||
| conditions.append(f"JSONExtractString(properties, 'status') = '{status}'") | ||
|
|
||
| where_clause = " AND ".join(conditions) | ||
|
|
||
| try: | ||
| result = self.client.query( | ||
| f"SELECT id FROM {self.db_name}.memories WHERE {where_clause}" | ||
| ).result_set | ||
| return [row[0] for row in result] |
Comment on lines
+358
to
+363
| cols = "id, memory, properties, created_at, updated_at" | ||
| if include_embedding: | ||
| cols += ", embedding" | ||
| result = self.client.query( | ||
| f"SELECT {cols} FROM {self.db_name}.memories WHERE id = '{id}' AND user_name = '{user_name}'", | ||
| ).result_set |
Comment on lines
+7
to
+11
| from datetime import datetime | ||
| from dotenv import load_dotenv | ||
|
|
||
| from memos.configs.graph_db import ByteHouseGraphDBConfig | ||
| from memos.graph_dbs.bytehouse import ByteHouseGraphDB, _prepare_node_metadata |
Comment on lines
+103
to
+111
| graph_db.add_node(node_id, memory, metadata, user_name="test_delete") | ||
|
|
||
| result = graph_db.get_node(node_id, user_name="test_delete") | ||
| assert result is not None | ||
|
|
||
| graph_db.delete_node(node_id, user_name="test_delete") | ||
|
|
||
| result = graph_db.get_node(node_id, user_name="test_delete") | ||
| assert result is None |
Comment on lines
+249
to
+250
| - memos_memories: Main table for memory nodes (id, memory, properties JSONB, embedding vector) | ||
| - memos_edges: Edge table for relationships (source_id, target_id, type) |
Contributor
|
执行创建表结构，错误在于 UNIQUE KEY 和 CnchMergeTree 引擎是 ByteHouse 云服务特有的语法，而开源 ClickHouse 不支持它们 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
add ByteHouse as graph database backend
Type of change
Please delete options that are not relevant.
How Has This Been Tested?