Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/epsilla-cloud/vectordb
Epsilla is a high performance Vector Database Management System. Try out hosted Epsilla at https://cloud.epsilla.com/
https://github.com/epsilla-cloud/vectordb
ai chatgpt data data-science database embeddings embeddings-similarity infrastructure llms machine-learning neural-network neural-search rag retrieval search-engine vector-database vector-search
Last synced: about 2 months ago
JSON representation
Epsilla is a high performance Vector Database Management System. Try out hosted Epsilla at https://cloud.epsilla.com/
- Host: GitHub
- URL: https://github.com/epsilla-cloud/vectordb
- Owner: epsilla-cloud
- License: gpl-3.0
- Created: 2023-07-09T02:28:31.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-05-20T20:48:58.000Z (4 months ago)
- Last Synced: 2024-05-20T23:18:13.941Z (4 months ago)
- Topics: ai, chatgpt, data, data-science, database, embeddings, embeddings-similarity, infrastructure, llms, machine-learning, neural-network, neural-search, rag, retrieval, search-engine, vector-database, vector-search
- Language: C++
- Homepage: https://www.epsilla.com
- Size: 964 KB
- Stars: 875
- Watchers: 4
- Forks: 36
- Open Issues: 11
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-vector-search - Epsilla - A High Performance Vector Database Management System, Hippocampus For AI
- awesome-ChatGPT-repositories - vectordb - Epsilla is a high performance Vector Database Management System. Try out hosted Epsilla at https://cloud.epsilla.com/ (Others)
- awesome-chatgpt - epsilla-cloud/vectordb - Epsilla is a high-performance vector database management system designed for scalable and cost-effective vector search, with a focus on memory retention in Large Language Models. (SDK, Libraries, Frameworks / Other sdk/libraries)
README
**A 10x faster, cheaper, and better vector database**
Documentation •
Discord •
Twitter •
Blog •
YouTube •
Feedback
Epsilla is an open-source vector database. Our focus is on ensuring scalability, high performance, and cost-effectiveness of vector search. EpsillaDB bridges the gap between information retrieval and memory retention in Large Language Models.
## Quick Start using Docker
**1. Run Backend in Docker**
```shell
docker pull epsilla/vectordb
docker run --pull=always -d -p 8888:8888 -v /data:/data epsilla/vectordb
```
**2. Interact with Python Client**
```shell
pip install pyepsilla
```
```python
from pyepsilla import vectordb
client = vectordb.Client(host='localhost', port='8888')
client.load_db(db_name="MyDB", db_path="/data/epsilla")
client.use_db(db_name="MyDB")
client.create_table(
table_name="MyTable",
table_fields=[
{"name": "ID", "dataType": "INT", "primaryKey": True},
{"name": "Doc", "dataType": "STRING"},
],
indices=[
{"name": "Index", "field": "Doc"},
]
)
client.insert(
table_name="MyTable",
records=[
{"ID": 1, "Doc": "Jupiter is the largest planet in our solar system."},
{"ID": 2, "Doc": "Cheetahs are the fastest land animals, reaching speeds over 60 mph."},
{"ID": 3, "Doc": "Vincent van Gogh painted the famous work \"Starry Night.\""},
{"ID": 4, "Doc": "The Amazon River is the longest river in the world."},
{"ID": 5, "Doc": "The Moon completes one orbit around Earth every 27 days."},
],
)
client.query(
table_name="MyTable",
query_text="Celestial bodies and their characteristics",
limit=2
)
# Result
# {
# 'message': 'Query search successfully.',
# 'result': [
# {'Doc': 'Jupiter is the largest planet in our solar system.', 'ID': 1},
# {'Doc': 'The Moon completes one orbit around Earth every 27 days.', 'ID': 5}
# ],
# 'statusCode': 200
# }
```
## Features:
* High performance and production-scale similarity search for embedding vectors.
* Full fledged database management system with familiar database, table, and field concepts. Vector is just another field type.
* Metadata filtering.
* Hybrid search with a fusion of dense and sparse vectors.
* Built-in embedding support, with natural language in natural language out search experience.
* Cloud native architecture with compute storage separation, serverless, and multi-tenancy.
* Rich ecosystem integrations including LangChain and LlamaIndex.
* Python/JavaScript/Ruby clients, and REST API interface.
Epsilla's core is written in C++ and leverages the advanced academic parallel graph traversal techniques for vector indexing, achieving 10 times faster vector search than HNSW while maintaining precision levels of over 99.9%.
## Epsilla Cloud
Try our fully managed vector DBaaS at Epsilla Cloud
## (Experimental) Use Epsilla as a python library without starting a docker image
**1. Build Epsilla Python Bindings lib package**
```shell
cd engine/scripts
(If on Ubuntu, run this first: bash setup-dev.sh)
bash install_oatpp_modules.sh
cd ..
bash build.sh
ls -lh build/*.so
```
**2. Run test with python bindings lib "epsilla.so" "libvectordb_dylib.so in the folder "build" built in the previous step**
```shell
cd engine
export PYTHONPATH=./build/
export DB_PATH=/tmp/db33
python3 test/bindings/python/test.py
```
Here are some sample code:
```python
import epsilla
epsilla.load_db(db_name="db", db_path="/data/epsilla")
epsilla.use_db(db_name="db")
epsilla.create_table(
table_name="MyTable",
table_fields=[
{"name": "ID", "dataType": "INT", "primaryKey": True},
{"name": "Doc", "dataType": "STRING"},
{"name": "EmbeddingEuclidean", "dataType": "VECTOR_FLOAT", "dimensions": 4, "metricType": "EUCLIDEAN"}
]
)
epsilla.insert(
table_name="MyTable",
records=[
{"ID": 1, "Doc": "Berlin", "EmbeddingEuclidean": [0.05, 0.61, 0.76, 0.74]},
{"ID": 2, "Doc": "London", "EmbeddingEuclidean": [0.19, 0.81, 0.75, 0.11]},
{"ID": 3, "Doc": "Moscow", "EmbeddingEuclidean": [0.36, 0.55, 0.47, 0.94]}
]
)
(code, response) = epsilla.query(
table_name="MyTable",
query_field="EmbeddingEuclidean",
response_fields=["ID", "Doc", "EmbeddingEuclidean"],
query_vector=[0.35, 0.55, 0.47, 0.94],
filter="ID < 6",
limit=10,
with_distance=True
)
print(code, response)
```