+
+
@@ -41,450 +40,87 @@
-
-
-**English** | [中文版](README_CN.md)
-
----
+**English** | [中文](README_CN.md)
-## 🚀 What is OceanBase seekdb?
-
-**OceanBase seekdb** is an AI-native search database that unifies relational, vector, text, JSON and GIS in a single engine, enabling hybrid search and in-database AI workflows.
-
----
-
-## 🔥 Why OceanBase seekdb?
-
-| **Feature** | **seekdb** | **OceanBase** | **Chroma** | **Milvus** | **MySQL 9.0** | **PostgreSQL
+pgvector** | **DuckDB** | **Elasticsearch** |
-| ------------------------ |:--------------------:|:-------------:|:----------:|:----------:|:-----------------------:|:----------------------------:|:----------:|:-----------------------------------:|
-| **Embedded** | ✅ | ❌ | ✅ | ✅ | ❌[1] | ❌ | ✅ | ❌ |
-| **Single-Node** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
-| **Distributed** | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ |
-| **MySQL Compatible** | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ |
-| **Vector Search** | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ |
-| **Full-Text Search** | ✅ | ✅ | ✅ | ⚠️ | ✅ | ✅ | ✅ | ✅ |
-| **Hybrid Search** | ✅ | ✅ | ✅ | ✅ | ❌ | ⚠️ | ❌ | ✅ |
-| **OLTP** | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ |
-| **OLAP** | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ⚠️ |
-| **License** | Apache 2.0 | MulanPubL 2.0 | Apache 2.0 | Apache 2.0 | GPL 2.0 | PostgreSQL License | MIT | AGPLv3
+SSPLv1
+Elastic 2.0 |
-> [1] Embedded capability is removed in MySQL 8.0
-> - ✅ Supported
-> - ❌ Not Supported
-> - ⚠️ Limited
-
-## ✨ Key Features
-
-### Build fast + Hybrid search + Multi model
-1. **Build fast:** From prototype to production in minutes: create AI apps using Python, run VectorDBBench on 1C2G.
-2. **Hybrid Search:** Combine vector search, full-text search and relational query in a single statement.
-3. **Multi-Model:** Support relational, vector, text, JSON and GIS in a single engine.
+## What is OceanBase seekdb?
+OceanBase seekdb is an open-source database that does vector search, full-text search, and SQL in one engine. Embedding, reranking, and LLM inference are built in, so a RAG pipeline can stay in one place instead of calling out to separate services. It uses the OceanBase engine and speaks MySQL protocol; existing MySQL clients and migrations work as-is.
-### AI inside + SQL inside
-1. **AI Inside:** Run embedding, reranking, LLM inference and prompt management inside the database, supporting a complete document-in/data-out RAG workflow.
-2. **SQL Inside:** Powered by the proven OceanBase engine, delivering real-time writes and queries with full ACID compliance, and seamless MySQL ecosystem compatibility.
+## Quick Start
-
-
----
-
-## 🎬 Quick Start
-
-### Installation
-
-Choose your platform:
-
-
-
-
-🐍 Python (Recommended for AI/ML)
+Install the Python client:
```bash
pip install -U pyseekdb
```
-
-
-
-🐳 Docker (Quick Testing)
-
-```bash
-docker run -d \
- --name seekdb \
- -p 2881:2881 \
- -p 2886:2886 \
- -v ./data:/var/lib/oceanbase \
- oceanbase/seekdb:latest
-```
-Please refer to the [document](https://github.com/oceanbase/docker-images/blob/main/seekdb/README.md) of this docker image for details.
-
-
-
-
-
-### 🎯 AI Search Example
-
-Build a semantic search system in 5 minutes:
-
-📦 Binary (Standalone)
-
-```bash
-# Linux
-rpm -ivh seekdb-1.x.x.x-xxxxxxx.el8.x86_64.rpm
-```
-Please replace the version number with the actual RPM package version.
-
-
-
-
-🗄️ 🐍 Python SDK
-
-```bash
-# install sdk first
-pip install -U pyseekdb
-```
+Example: create a collection, add documents, and query by text. Embeddings are generated by the database or the SDK.
```python
-"""
-this example demonstrates the most common operations with embedding functions:
-1. Create a client connection
-2. Create a collection with embedding function
-3. Add data using documents (embeddings auto-generated)
-4. Query using query texts (embeddings auto-generated)
-5. Print query results
-
-This is a minimal example to get you started quickly with embedding functions.
-"""
-
import pyseekdb
-from pyseekdb import DefaultEmbeddingFunction
-
-# ==================== Step 1: Create Client Connection ====================
-# You can use embedded mode, server mode, or OceanBase mode
-# For this example, we'll use server mode (you can change to embedded or OceanBase)
-
-# Embedded mode (local SeekDB)
-client = pyseekdb.Client(
- path="./seekdb.db",
- database="test"
-)
-# Alternative: Server mode (connecting to remote SeekDB server)
-# client = pyseekdb.Client(
-# host="127.0.0.1",
-# port=2881,
-# database="test",
-# user="root",
-# password=""
-# )
-
-# Alternative: Remote server mode (OceanBase Server)
-# client = pyseekdb.Client(
-# host="127.0.0.1",
-# port=2881,
-# tenant="test", # OceanBase default tenant
-# database="test",
-# user="root",
-# password=""
-# )
-
-# ==================== Step 2: Create a Collection with Embedding Function ====================
-# A collection is like a table that stores documents with vector embeddings
-collection_name = "my_simple_collection"
-
-# Create collection with default embedding function
-# The embedding function will automatically convert documents to embeddings
-collection = client.create_collection(
- name=collection_name,
- #embedding_function=DefaultEmbeddingFunction() # Uses default model (384 dimensions)
-)
-
-print(f"Created collection '{collection_name}' with dimension: {collection.dimension}")
-print(f"Embedding function: {collection.embedding_function}")
-
-# ==================== Step 3: Add Data to Collection ====================
-# With embedding function, you can add documents directly without providing embeddings
-# The embedding function will automatically generate embeddings from documents
-documents = [
- "Machine learning is a subset of artificial intelligence",
- "Python is a popular programming language",
- "Vector databases enable semantic search",
- "Neural networks are inspired by the human brain",
- "Natural language processing helps computers understand text"
-]
+client = pyseekdb.Client(path="./seekdb.db", database="test")
+collection = client.create_collection("docs")
-ids = ["id1", "id2", "id3", "id4", "id5"]
-
-# Add data with documents only - embeddings will be auto-generated by embedding function
collection.add(
- ids=ids,
- documents=documents, # embeddings will be automatically generated
- metadatas=[
- {"category": "AI", "index": 0},
- {"category": "Programming", "index": 1},
- {"category": "Database", "index": 2},
- {"category": "AI", "index": 3},
- {"category": "NLP", "index": 4}
- ]
+ ids=["1", "2", "3"],
+ documents=[
+ "Machine learning is a subset of AI.",
+ "Vector databases enable semantic search.",
+ "Natural language processing helps computers understand text.",
+ ],
)
-print(f"\nAdded {len(documents)} documents to collection")
-print("Note: Embeddings were automatically generated from documents using the embedding function")
-
-# ==================== Step 4: Query the Collection ====================
-# With embedding function, you can query using text directly
-# The embedding function will automatically convert query text to query vector
-
-# Query using text - query vector will be auto-generated by embedding function
-query_text = "artificial intelligence and machine learning"
-
-results = collection.query(
- query_texts=query_text, # Query text - will be embedded automatically
- n_results=3 # Return top 3 most similar documents
-)
-
-print(f"\nQuery: '{query_text}'")
-print(f"Query results: {len(results['ids'][0])} items found")
-
-# ==================== Step 5: Print Query Results ====================
-for i in range(len(results['ids'][0])):
- print(f"\nResult {i+1}:")
- print(f" ID: {results['ids'][0][i]}")
- print(f" Distance: {results['distances'][0][i]:.4f}")
- if results.get('documents'):
- print(f" Document: {results['documents'][0][i]}")
- if results.get('metadatas'):
- print(f" Metadata: {results['metadatas'][0][i]}")
-
-# ==================== Step 6: Cleanup ====================
-# Delete the collection
-client.delete_collection(collection_name)
-print(f"\nDeleted collection '{collection_name}'")
-
-```
-Please refer to the [User Guide](https://github.com/oceanbase/pyseekdb) for more details.
-
-
-
-
-## 📚 Use Cases
-
-🗄️ SQL
-
-```sql
--- Create table with vector column
-CREATE TABLE articles (
- id INT PRIMARY KEY,
- title TEXT,
- content TEXT,
- embedding VECTOR(384),
- FULLTEXT INDEX idx_fts(content) WITH PARSER ik,
- VECTOR INDEX idx_vec (embedding) WITH(DISTANCE=l2, TYPE=hnsw, LIB=vsag)
- ) ORGANIZATION = HEAP;
-
--- Insert documents with embeddings
--- Note: Embeddings should be pre-computed using your embedding model
-INSERT INTO articles (id, title, content, embedding)
-VALUES
- (1, 'AI and Machine Learning', 'Artificial intelligence is transforming...', '[0.1, 0.2, ...]'),
- (2, 'Database Systems', 'Modern databases provide high performance...', '[0.3, 0.4, ...]'),
- (3, 'Vector Search', 'Vector databases enable semantic search...', '[0.5, 0.6, ...]');
-
--- Example: Hybrid search combining vector and full-text
--- Replace '[query_embedding]' with your actual query embedding vector
-SELECT
- title,
- content,
- l2_distance(embedding, '[query_embedding]') AS vector_distance,
- MATCH(content) AGAINST('your keywords' IN NATURAL LANGUAGE MODE) AS text_score
-FROM articles
-WHERE MATCH(content) AGAINST('your keywords' IN NATURAL LANGUAGE MODE)
-ORDER BY vector_distance APPROXIMATE
-LIMIT 10;
+results = collection.query(query_texts="what is AI?", n_results=2)
+print(results["documents"])
```
-We suggest developers use sqlalchemy to access data by SQL for python developers.
-
-
-
- 📖 RAG & Knowledge Retrieval
-
-Large language models are limited by their training data. RAG introduces timely and trusted external knowledge to improve answer quality and reduce hallucination. seekdb enhances search accuracy through vector search, full-text search, hybrid search, built-in AI functions, and efficient indexing, while multi-level access control safeguards data privacy across heterogeneous knowledge sources.
-1. Enterprise QA
-2. Customer support
-3. Industry insights
-4. Personal knowledge
-
-
-
+## Capabilities
- 🔍 Semantic Search Engine
-Traditional keyword search struggles to capture intent. Semantic search leverages embeddings and vector search to understand meaning and connect text, images, and other modalities. seekdb's hybrid search and multi-model querying deliver more precise, context-aware results across complex search scenarios.
-1. Product search
-2. Text-to-image
-3. Image-to-product
+Other options: [Docker](https://github.com/oceanbase/docker-images/blob/main/seekdb/README.md) or [binary (RPM)](https://www.oceanbase.ai/docs/seekdb-overview/). Documentation: [seekdb](https://www.oceanbase.ai/docs/seekdb-overview/) and [pyseekdb](https://github.com/oceanbase/pyseekdb).
-
-
+- **RAG and knowledge bases** — Enterprise QA, customer support, internal docs; hybrid search with built-in embedding, rerank, and LLM.
+- **Semantic search** — Product search, text-to-image, image-to-product; vector and full-text in one engine.
+- **AI agents** — One store for memory, tool results, and RAG; metadata and vector/text search with built-in AI functions.
+- **AI-assisted coding** — Code and docs in the same DB; semantic and keyword search, multi-project isolation.
+- **Edge and embedded** — Lightweight embedded or micro-server mode; optional sync to OceanBase cloud.
+- **Enterprise apps** — Add vector/search/AI to existing MySQL-compatible apps with minimal migration.
- 🎯 Agentic AI Applications
+| Area | Description |
+|------|-------------|
+| Built-in AI | `AI_EMBED`, `AI_RERANK`, `AI_COMPLETE`, and prompt templates; run embedding and LLM from SQL. |
+| Hybrid search | One query can combine vector, full-text, and relational filters; RRF or LLM rerank; filters pushed to storage. |
+| Vector and full-text | Dense and sparse vectors (L2, IP, cosine), HNSW/IVF indexes, BM25 full-text with phrase and boolean. |
+| SQL | OceanBase engine, ACID, MySQL protocol; works with standard MySQL clients and migration tools. |
+| Deployment | Embedded (e.g. pyseekdb), single-node server, or [OceanBase](https://www.oceanbase.com/) for scale-out. |
-Agentic AI requires memory, planning, perception, and reasoning. seekdb provides a unified foundation for agents through metadata management, vector/text/mixed queries, multimodal data processing, RAG, built-in AI functions and inference, and robust privacy controls—enabling scalable, production-grade agent systems.
-1. Personal assistants
-2. Enterprise automation
-3. Vertical agents
-4. Agent platforms
+## Use Cases
-
-
+Supports LangChain, LangGraph, LlamaIndex, Dify, Coze, FastGPT, DB-GPT, Hugging Face, Firecrawl, Spring AI Alibaba, Jina, Ragas, Instructor, Baseten, Cloudflare Workers AI, and others. See the [documentation](https://www.oceanbase.ai/docs/seekdb-overview/) for integration guides.
- 💻 AI-Assisted Coding & Development
+More: [Use cases on oceanbase.ai](https://www.oceanbase.ai/).
-AI-powered coding combines natural-language understanding and code semantic analysis to enable generation, completion, debugging, testing, and refactoring. seekdb enhances code intelligence with semantic search, multi-model storage for code and documents, isolated multi-project management, and time-travel queries—supporting both local and cloud IDE environments.
-1. IDE plugins
-2. Design-to-web
-3. Local IDEs
-4. Web IDEs
+## Ecosystem
-
-
+## Development
-
- ⬆️ Enterprise Application Intelligence
+## Community & Support
-AI transforms enterprise systems from passive tools into proactive collaborators. seekdb provides a unified AI-ready storage layer, fully compatible with MySQL syntax and views, and accelerates mixed workloads with parallel execution and hybrid row-column storage. Legacy applications gain intelligent capabilities with minimal migration across office, workflow, and business analytics scenarios.
-1. Document intelligence
-2. Business insights
-3. Finance systems
+- [Discord](https://discord.gg/74cF8vbNEs)
+- [GitHub Discussions](https://github.com/oceanbase/seekdb/discussions)
+- [Forum (中文)](https://ask.oceanbase.com/)
-
-
-
----
-
-## 🌟 Ecosystem & Integrations
-
- 📱 On-Device & Edge AI Applications
-
-Edge devices—from mobile to vehicle and industrial terminals—operate with constrained compute and storage. seekdb's lightweight architecture supports embedded and micro-server modes, delivering full SQL, JSON, and hybrid search under low resource usage. It integrates seamlessly with OceanBase cloud services to enable unified edge-to-cloud intelligent systems.
-1. Personal assistants
-2. In-vehicle systems
-3. AI education
-4. Companion robots
-5. Healthcare devices
-
-
-
-
-
----
-
-
-## 🤝 Community & Support
-
-
-
----
-
-## 🛠️ Development
-
-### Build from Source
-
-Before building, please install the required toolchain and dependencies for your operating system. See [Install Toolchain](docs/developer-guide/en/toolchain.md) for detailed instructions.
+To build from source, install the toolchain first. See [toolchain](docs/developer-guide/en/toolchain.md) and [developer guide](docs/developer-guide/en/README.md):
```bash
-# Clone the repository
-git clone https://github.com/oceanbase/seekdb.git
-cd seekdb
+git clone https://github.com/oceanbase/seekdb.git && cd seekdb
bash build.sh debug --init --make
-mkdir ~/seekdb
-mkdir ~/seekdb/bin
-cp build_debug/src/observer/seekdb ~/seekdb/bin
-cd ~/seekdb
-./bin/seekdb
```
-In this example, the working director is $HOME/seekdb, please use a fresh director for testing, Please see the [Developer Guide](docs/developer-guide/en/README.md) for detailed instructions.
-
-### Contributing
-
-We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) to get started.
-
----
-
-
-## 📄 License
-
-OceanBase seekdb is licensed under the [Apache License, Version 2.0](LICENSE).
+The developer guide describes how to run and where build outputs go. To contribute: [CONTRIBUTING.md](CONTRIBUTING.md).
+## License
+[Apache License, Version 2.0](LICENSE).
diff --git a/README_CN.md b/README_CN.md
index ebd12ba46..29db5609d 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -2,9 +2,9 @@
# 
-
-Please refer to the [User Guide](https://www.oceanbase.ai/docs/seekdb-overview/) for more details.
-
-
-
- 
+
-
+
- 
+
@@ -36,408 +36,89 @@
-
-
- 
- 
- 
-