This tutorial will show you how to build a chemical search system with Milvus.


Intel® Core™ i7-7700K CPU @ 4.20GHz




Ubuntu 18.04


Milvus 0.10.0
mols-search-webserver 0.7.0
mols-search-webclient 0.3.0

The previous configuration has been tested and this scenario is also supported in Windows.

Data source: The data source contains compressed SDF files. You need to convert these files to SMILES files. We already prepared a SMILE file containing 10,000 chemical structures test_1w.smi. You can use wget to download the file:

$ wget

1. Run Milvus Docker

This demo uses Milvus 0.10.0 CPU version. Refer to to learn how to install and run Milvus.

2. Run mols-search-webserver docker

$ docker run -d -v <DATAPATH>:/tmp/data -p 35001:5000 -e "MILVUS_HOST=" -e "MILVUS_PORT=19530" milvusbootcamp/mols-search-webserver:0.7.0

Refer to the following table for detailed parameter description:

-v DATAPATH:/tmp/data

-v specifies directory mapping between the host and the docker image. Please change DATAPATH to the location of test_1w.smi.

-p 35001:5000

-p specifies pot mapping between the host and the image.


-e specifies the system parameter mapping between the host and the image. Pease update to the IP address of the Milvus docker.

-e "MILVUS_PORT=19530"

Update 19530 to the port of Milvus docker.

3. Run mols-search-webclient docker

$ docker run -d -p 8001:80 -e API_URL= milvusbootcamp/mols-search-webclient:0.3.0

Note: Please update to the IP address of the Milvus docker.

4. Launch a browser

# Please update IP address and port per your previous configurations

Click CLEAR ALL to remove all chemical structure data.