Skip to content
Grounding of biomedical named entities with contextual disambiguation
Python Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Gilda: Grounding Integrating Learned Disambiguation

License Build Documentation


Gilda is deployed as a web service at (see Usage instructions below), it only needs to be installed if used locally.

The recommended method to install Gilda is via Github as:

pip install git+

Note that Gilda uses a single large resource file for grounding, which is automatically downloaded into the ~/.gilda/<version> folder during runtime. Given some additional dependencies, the grounding resource file can also be regenerated locally by running python -m gilda.generate_terms.


Gilda can either be used as a REST service (recommended) or programmatically via its Python API. An introduction Jupyter notebook for using Gilda as a service is available at

The REST service accepts POST requests with a JSON header on the /ground endpoint. There is a public REST service running on AWS but the service can also be run locally as

python -m

Below is an example request using curl:

curl -X POST -H "Content-Type: application/json" -d '{"text": "kras"}' http://localhost:8001/ground

The same request using Python's request package would be as follows:'http://localhost:8001/ground', json={'text': 'kras'})

The above requests can also be used to interact with the public service, by using the appropriate URL instead of localhost:8001.

As for using Gilda as a Python package, the documentation at provides detailed descriptions of each module of Gilda and their usage.


The development of Gilda is funded under the DARPA Communicating with Computers program (ARO grant W911NF-15-1-0544).

You can’t perform that action at this time.