| Name | ontogpt JSON |
| Version |
1.0.17
JSON |
| download |
| home_page | None |
| Summary | OntoGPT is a Python package for extracting structured information from text with large language models (LLMs), instruction prompts, and ontology-based grounding. |
| upload_time | 2025-08-15 19:54:52 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | !=3.9.7,<3.14,>=3.9 |
| license | BSD-3 |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# OntoGPT
[](https://zenodo.org/badge/latestdoi/13996/monarch-initiative/ontogpt)
## Introduction
_OntoGPT_ is a Python package for extracting structured information from text with large language models (LLMs), _instruction prompts_, and ontology-based grounding.
[For more details, please see the full documentation.](https://monarch-initiative.github.io/ontogpt/)
## Quick Start
OntoGPT runs on the command line, though there's also a minimal web app interface (see `Web Application` section below).
1. Ensure you have Python 3.9 or greater installed.
2. Install with `pip`:
```bash
pip install ontogpt
```
3. Set your OpenAI API key:
```bash
runoak set-apikey -e openai <your openai api key>
```
4. See the list of all OntoGPT commands:
```bash
ontogpt --help
```
5. Try a simple example of information extraction:
```bash
echo "One treatment for high blood pressure is carvedilol." > example.txt
ontogpt extract -i example.txt -t drug
```
OntoGPT will retrieve the necessary ontologies and output results to the command line. Your output will provide all extracted objects under the heading `extracted_object`.
## Web Application
There is a bare bones web application for running OntoGPT and viewing results.
First, install the required dependencies with `pip` by running the following command:
```bash
pip install ontogpt[web]
```
Then run this command to start the web application:
```bash
web-ontogpt
```
NOTE: We do not recommend hosting this webapp publicly without authentication.
## Model APIs
OntoGPT uses the `litellm` package (<https://litellm.vercel.app/>) to interface with LLMs.
This means most APIs are supported, including OpenAI, Azure, Anthropic, Mistral, Replicate, and beyond.
The model name to use may be found from the command `ontogpt list-models` - use the name in the first column with the `--model` option.
In most cases, this will require setting the API key for a particular service as above:
```bash
runoak set-apikey -e anthropic-key <your anthropic api key>
```
Some endpoints, such as OpenAI models through Azure, require setting additional details. These may be set similarly:
```bash
runoak set-apikey -e azure-key <your azure api key>
runoak set-apikey -e azure-base <your azure endpoint url>
runoak set-apikey -e azure-version <your azure api version, e.g. "2023-05-15">
```
These details may also be set as environment variables as follows:
```bash
export AZURE_API_KEY="my-azure-api-key"
export AZURE_API_BASE="https://example-endpoint.openai.azure.com"
export AZURE_API_VERSION="2023-05-15"
```
## Open Models
Open LLMs may be retrieved and run through the `ollama` package (<https://ollama.com/>).
You will need to install `ollama` (see the [GitHub repo](https://github.com/ollama/ollama)), and you may need to start it as a service with a command like `ollama serve` or `sudo systemctl start ollama`.
Then retrieve a model with `ollama pull <modelname>`, e.g., `ollama pull llama3`.
The model may then be used in OntoGPT by prefixing its name with `ollama/`, e.g., `ollama/llama3`, along with the `--model` option.
Some ollama models may not be listed in `ontogpt list-models` but the full list of downloaded LLMs can be seen with `ollama list` command.
## Evaluations
OntoGPT's functions have been evaluated on test data. Please see the full documentation for details on these evaluations and how to reproduce them.
## Related Projects
* [TALISMAN](https://github.com/monarch-initiative/talisman/), a tool for generating summaries of functions enriched within a gene set. TALISMAN uses OntoGPT to work with LLMs.
## Tutorials and Presentations
* Presentation: "Staying grounded: assembling structured biological knowledge with help from large language models" - presented by Harry Caufield as part of the AgBioData Consortium webinar series (September 2023)
* [Slides](https://docs.google.com/presentation/d/1rMQVWaMju-ucYFif5nx4Xv3bNX2SVI_w89iBIT1bkV4/edit?usp=sharing)
* [Video](https://www.youtube.com/watch?v=z38lI6WyBsY)
* Presentation: "Transforming unstructured biomedical texts with large language models" - presented by Harry Caufield as part of the BOSC track at ISMB/ECCB 2023 (July 2023)
* [Slides](https://docs.google.com/presentation/d/1LsOTKi-rXYczL9vUTHB1NDkaEqdA9u3ZFC5ANa0x1VU/edit?usp=sharing)
* [Video](https://www.youtube.com/watch?v=a34Yjz5xPp4)
* Presentation: "OntoGPT: A framework for working with ontologies and large language models" - talk by Chris Mungall at Joint Food Ontology Workgroup (May 2023)
* [Slides](https://docs.google.com/presentation/d/1CosJJe8SqwyALyx85GWkw9eOT43B4HwDlAY2CmkmJgU/edit)
* [Video](https://www.youtube.com/watch?v=rt3wobA9hEs&t=1955s)
## Citation
The information extraction approach used in OntoGPT, SPIRES, is described further in: Caufield JH, Hegde H, Emonet V, Harris NL, Joachimiak MP, Matentzoglu N, et al. Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning. _Bioinformatics_, Volume 40, Issue 3, March 2024, btae104, [https://doi.org/10.1093/bioinformatics/btae104](https://doi.org/10.1093/bioinformatics/btae104).
## Acknowledgements
This project is part of the [Monarch Initiative](https://monarchinitiative.org/). We also gratefully acknowledge [Bosch Research](https://www.bosch.com/research) for their support of this research project.
Raw data
{
"_id": null,
"home_page": null,
"name": "ontogpt",
"maintainer": null,
"docs_url": null,
"requires_python": "!=3.9.7,<3.14,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Chris Mungall <cjmungall@lbl.gov>, \"J. Harry Caufield\" <jhc@lbl.gov>",
"download_url": "https://files.pythonhosted.org/packages/cc/48/22d27ddc6fbce42c6f1a09a6e499d6975a3de67bfbf7c4bc102dbaeca912/ontogpt-1.0.17.tar.gz",
"platform": null,
"description": "# OntoGPT\n\n\n\n[](https://zenodo.org/badge/latestdoi/13996/monarch-initiative/ontogpt)\n\n\n## Introduction\n\n_OntoGPT_ is a Python package for extracting structured information from text with large language models (LLMs), _instruction prompts_, and ontology-based grounding.\n\n[For more details, please see the full documentation.](https://monarch-initiative.github.io/ontogpt/)\n\n## Quick Start\n\nOntoGPT runs on the command line, though there's also a minimal web app interface (see `Web Application` section below).\n\n1. Ensure you have Python 3.9 or greater installed.\n2. Install with `pip`:\n\n ```bash\n pip install ontogpt\n ```\n\n3. Set your OpenAI API key:\n\n ```bash\n runoak set-apikey -e openai <your openai api key>\n ```\n\n4. See the list of all OntoGPT commands:\n\n ```bash\n ontogpt --help\n ```\n\n5. Try a simple example of information extraction:\n\n ```bash\n echo \"One treatment for high blood pressure is carvedilol.\" > example.txt\n ontogpt extract -i example.txt -t drug\n ```\n\n OntoGPT will retrieve the necessary ontologies and output results to the command line. Your output will provide all extracted objects under the heading `extracted_object`.\n\n## Web Application\n\nThere is a bare bones web application for running OntoGPT and viewing results.\n\nFirst, install the required dependencies with `pip` by running the following command:\n\n```bash\npip install ontogpt[web]\n```\n\nThen run this command to start the web application:\n\n```bash\nweb-ontogpt\n```\n\nNOTE: We do not recommend hosting this webapp publicly without authentication.\n\n## Model APIs\n\nOntoGPT uses the `litellm` package (<https://litellm.vercel.app/>) to interface with LLMs.\n\nThis means most APIs are supported, including OpenAI, Azure, Anthropic, Mistral, Replicate, and beyond.\n\nThe model name to use may be found from the command `ontogpt list-models` - use the name in the first column with the `--model` option.\n\nIn most cases, this will require setting the API key for a particular service as above:\n\n```bash\nrunoak set-apikey -e anthropic-key <your anthropic api key>\n```\n\nSome endpoints, such as OpenAI models through Azure, require setting additional details. These may be set similarly:\n\n```bash\nrunoak set-apikey -e azure-key <your azure api key>\nrunoak set-apikey -e azure-base <your azure endpoint url>\nrunoak set-apikey -e azure-version <your azure api version, e.g. \"2023-05-15\">\n```\n\nThese details may also be set as environment variables as follows:\n\n```bash\nexport AZURE_API_KEY=\"my-azure-api-key\"\nexport AZURE_API_BASE=\"https://example-endpoint.openai.azure.com\"\nexport AZURE_API_VERSION=\"2023-05-15\"\n```\n\n## Open Models\n\nOpen LLMs may be retrieved and run through the `ollama` package (<https://ollama.com/>).\n\nYou will need to install `ollama` (see the [GitHub repo](https://github.com/ollama/ollama)), and you may need to start it as a service with a command like `ollama serve` or `sudo systemctl start ollama`.\n\nThen retrieve a model with `ollama pull <modelname>`, e.g., `ollama pull llama3`.\n\nThe model may then be used in OntoGPT by prefixing its name with `ollama/`, e.g., `ollama/llama3`, along with the `--model` option.\n\nSome ollama models may not be listed in `ontogpt list-models` but the full list of downloaded LLMs can be seen with `ollama list` command.\n\n## Evaluations\n\nOntoGPT's functions have been evaluated on test data. Please see the full documentation for details on these evaluations and how to reproduce them.\n\n## Related Projects\n\n* [TALISMAN](https://github.com/monarch-initiative/talisman/), a tool for generating summaries of functions enriched within a gene set. TALISMAN uses OntoGPT to work with LLMs.\n\n## Tutorials and Presentations\n\n* Presentation: \"Staying grounded: assembling structured biological knowledge with help from large language models\" - presented by Harry Caufield as part of the AgBioData Consortium webinar series (September 2023)\n * [Slides](https://docs.google.com/presentation/d/1rMQVWaMju-ucYFif5nx4Xv3bNX2SVI_w89iBIT1bkV4/edit?usp=sharing)\n * [Video](https://www.youtube.com/watch?v=z38lI6WyBsY)\n* Presentation: \"Transforming unstructured biomedical texts with large language models\" - presented by Harry Caufield as part of the BOSC track at ISMB/ECCB 2023 (July 2023)\n * [Slides](https://docs.google.com/presentation/d/1LsOTKi-rXYczL9vUTHB1NDkaEqdA9u3ZFC5ANa0x1VU/edit?usp=sharing)\n * [Video](https://www.youtube.com/watch?v=a34Yjz5xPp4)\n* Presentation: \"OntoGPT: A framework for working with ontologies and large language models\" - talk by Chris Mungall at Joint Food Ontology Workgroup (May 2023)\n * [Slides](https://docs.google.com/presentation/d/1CosJJe8SqwyALyx85GWkw9eOT43B4HwDlAY2CmkmJgU/edit)\n * [Video](https://www.youtube.com/watch?v=rt3wobA9hEs&t=1955s)\n\n## Citation\n\nThe information extraction approach used in OntoGPT, SPIRES, is described further in: Caufield JH, Hegde H, Emonet V, Harris NL, Joachimiak MP, Matentzoglu N, et al. Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning. _Bioinformatics_, Volume 40, Issue 3, March 2024, btae104, [https://doi.org/10.1093/bioinformatics/btae104](https://doi.org/10.1093/bioinformatics/btae104).\n\n## Acknowledgements\n\nThis project is part of the [Monarch Initiative](https://monarchinitiative.org/). We also gratefully acknowledge [Bosch Research](https://www.bosch.com/research) for their support of this research project.\n",
"bugtrack_url": null,
"license": "BSD-3",
"summary": "OntoGPT is a Python package for extracting structured information from text with large language models (LLMs), instruction prompts, and ontology-based grounding.",
"version": "1.0.17",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "952763d3580318070036e04bac4b1f2762bc6e3960272923c48872f034c131fc",
"md5": "a41a363c5a4c311e3d18af96ecd0747d",
"sha256": "bd158f6e471b48da7d3755a7f685c841b692c793f0a27600fd77038ef3769cd5"
},
"downloads": -1,
"filename": "ontogpt-1.0.17-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a41a363c5a4c311e3d18af96ecd0747d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "!=3.9.7,<3.14,>=3.9",
"size": 311052,
"upload_time": "2025-08-15T19:54:50",
"upload_time_iso_8601": "2025-08-15T19:54:50.321232Z",
"url": "https://files.pythonhosted.org/packages/95/27/63d3580318070036e04bac4b1f2762bc6e3960272923c48872f034c131fc/ontogpt-1.0.17-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "cc4822d27ddc6fbce42c6f1a09a6e499d6975a3de67bfbf7c4bc102dbaeca912",
"md5": "3c9d1924ef7d54942367f457b54e907d",
"sha256": "9db70afd2e11cd6f93dac951e3e3d19412c6a1c28a3d332ad4a714dd6c0ebeba"
},
"downloads": -1,
"filename": "ontogpt-1.0.17.tar.gz",
"has_sig": false,
"md5_digest": "3c9d1924ef7d54942367f457b54e907d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "!=3.9.7,<3.14,>=3.9",
"size": 203114,
"upload_time": "2025-08-15T19:54:52",
"upload_time_iso_8601": "2025-08-15T19:54:52.123335Z",
"url": "https://files.pythonhosted.org/packages/cc/48/22d27ddc6fbce42c6f1a09a6e499d6975a3de67bfbf7c4bc102dbaeca912/ontogpt-1.0.17.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-15 19:54:52",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "ontogpt"
}
