Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

docs: Add SurrealDB to storage documentation (#3163)

Sarthak Bhardwaj32cdd2f1f54d
diff --git a/docs/mintlify/key_modules/storages.mdx b/docs/mintlify/key_modules/storages.mdx
index 1512235c7..2a6a1cf6e 100644
--- a/docs/mintlify/key_modules/storages.mdx
+++ b/docs/mintlify/key_modules/storages.mdx
@@ -61,9 +61,13 @@ The <b>Storage</b> module in CAMEL-AI gives you a **unified interface for saving
- Schema-based, semantic search, hybrid queries
**ChromaStorage**
- - For [ChromaDB](https://www.trychroma.com/) (AI-native open-source embedding database)
+ - For [ChromaDB](https://www.trychroma.com/) (AI-native open-source embedding database)
- Simple API, scales from notebook to production
+ **SurrealStorage**
+ - For [SurrealDB](https://surrealdb.com/) (scalable, distributed database with WebSocket support)
+ - Efficient vector storage and similarity search with real-time updates
+
**PgVectorStorage**
- For [PostgreSQL with pgvector](https://github.com/pgvector/pgvector) (open-source vector engine)
- Leverages PostgreSQL for vector search
@@ -298,6 +302,56 @@ Here are practical usage patterns for each storage type—pick the ones you need
---
+<Card title="SurrealDB Vector Storage" icon="database">
+ <b>Use for:</b> Scalable, distributed vector storage with WebSocket support.
+ <b>Perfect for:</b> Real-time vector search with distributed deployments and SQL-like querying.
+
+ <Tabs>
+ <Tab title="Python Example">
+ ```python
+ import os
+ from camel.storages import SurrealStorage, VectorDBQuery, VectorRecord
+
+ # Set environment variables for SurrealDB connection
+ os.environ["SURREAL_URL"] = "ws://localhost:8000/rpc"
+ os.environ["SURREAL_PASSWORD"] = "your_password"
+
+ # Create SurrealStorage instance with WebSocket connection
+ surreal_storage = SurrealStorage(
+ url=os.getenv("SURREAL_URL"),
+ table="camel_vectors",
+ namespace="ns",
+ database="db",
+ user="root",
+ password=os.getenv("SURREAL_PASSWORD"),
+ vector_dim=4,
+ )
+
+ # Add vector records
+ surreal_storage.add([
+ VectorRecord(vector=[-0.1, 0.1, -0.1, 0.1], payload={'key1': 'value1'}),
+ VectorRecord(vector=[-0.1, 0.1, 0.1, 0.1], payload={'key2': 'value2'}),
+ ])
+
+ # Query similar vectors
+ query_results = surreal_storage.query(VectorDBQuery(query_vector=[0.1, 0.2, 0.1, 0.1], top_k=1))
+ for result in query_results:
+ print(result.record.payload, result.similarity)
+
+ # Clear all vectors
+ surreal_storage.clear()
+ ```
+ </Tab>
+ <Tab title="Output">
+ ```markdown
+ >>> {'key2': 'value2'} 0.5669467095138407
+ ```
+ </Tab>
+ </Tabs>
+</Card>
+
+---
+
<Card title="OceanBase Vector Storage" icon="earth-oceania">
<b>Use for:</b> Massive vector storage with advanced analytics.
<b>Perfect for:</b> Batch operations, cloud or on-prem setups, and high-throughput search.