| Name | sigmund JSON |
| Version |
0.16.7
JSON |
| download |
| home_page | None |
| Summary | AI-based chatbot that provides sensible answers based on documentation |
| upload_time | 2024-05-02 08:58:20 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
ai
chatbot
llm
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Sigmund AI
Copyright 2023-2024 Sebastiaan Mathôt
A Python library and web app for an LLM-based chatbot with many capabilities.
Features:
- __Privacy__: all messages and uploaded attachments are encrypted so that no-one can listen in on your conversation
- __Knowledge__: access to documentation
- __Continuous conversation__: conversations are summarized when they become too long to fit into the prompt
- __Tool use__:
- __Code execution__: ability to execute Python and R code
- __Google Scholar search__: ability to search for articles on Google Scholar
- __Attachments__: ability to read attachments
- __Download__: ability to download pages and files as attachments
Sigmund is not a large language model itself. Rather it uses third-party models. Currently, models from [OpenAI](https://openai.com), [Anthropic](https://www.anthropic.com/), and [Mistral](https://mistral.ai/) are supported. API keys from these respective providers are required.
By default, Sigmund is configured to act as an assistant for OpenSesame, a program for creating psychology/ cognitive-neuroscience experiments. However, the software can easily be reconfigured for a different purpose.
## What can Sigmund do? And how does Sigmund work?
For a description of how Sigmund works, see: <https://sigmundai.eu/about>. This page describes the default configuration.
## Configuration
See `sigmund/config.py` for configuration instructions.
## Dependencies
For Python dependencies, see `pyproject.toml`. In addition to these, `pandoc` is required for the ability to read attachments, and a local `redis` server needs to run for persistent data between sessions.
## Running (development)
Download the source code, and in the folder of the source code execute the following:
```
# Specify API keys for model providers. Even when using Anthropic (Claude) or
# Mistral, an OpenAI key is provided when document search is enabled
export OPENAI_API_KEY = 'your key here'
export ANTHROPIC_API_KEY = 'your key here'
export MISTRAL_API_KEY = 'your key here'
pip install . # install dependencies
python index_library.py # build library (documentation) index
python app.py # start the app
```
Next, access the app (by default) through:
```
https://127.0.0.1:5000/
```
## Running (production)
In production, the server is generally not run by directly calling the app. There are many ways to run a Flask app in production. One way is to use gunicorn to start the app, and then use an nginx web server as a proxy that reroutes requests to the app. When taking this route, make sure to set up nginx with a large `client_max_body_size` (to allow attachment uploading) and disable `proxy_cache` and `proxy_buffering` (to allow status messages to be streamed while Sigmund is answering).
## License
Sigmund is distributed under the terms of the GNU General Public License 3. The full license should be included in the file `COPYING`, or can be obtained from:
- <http://www.gnu.org/licenses/gpl.txt>
Raw data
{
"_id": null,
"home_page": null,
"name": "sigmund",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, chatbot, llm",
"author": null,
"author_email": "Sebastiaan Math\u00f4t <s.mathot@cogsci.nl>",
"download_url": "https://files.pythonhosted.org/packages/7a/cb/d72cb3b1f83cde206b26c1641834dc7347d88d1861a6c9e2f61064036ecc/sigmund-0.16.7.tar.gz",
"platform": null,
"description": "# Sigmund AI\n\nCopyright 2023-2024 Sebastiaan Math\u00f4t\n\nA Python library and web app for an LLM-based chatbot with many capabilities.\n\nFeatures:\n\n- __Privacy__: all messages and uploaded attachments are encrypted so that no-one can listen in on your conversation\n- __Knowledge__: access to documentation\n- __Continuous conversation__: conversations are summarized when they become too long to fit into the prompt\n- __Tool use__:\n - __Code execution__: ability to execute Python and R code\n - __Google Scholar search__: ability to search for articles on Google Scholar\n - __Attachments__: ability to read attachments\n - __Download__: ability to download pages and files as attachments\n \nSigmund is not a large language model itself. Rather it uses third-party models. Currently, models from [OpenAI](https://openai.com), [Anthropic](https://www.anthropic.com/), and [Mistral](https://mistral.ai/) are supported. API keys from these respective providers are required.\n\nBy default, Sigmund is configured to act as an assistant for OpenSesame, a program for creating psychology/ cognitive-neuroscience experiments. However, the software can easily be reconfigured for a different purpose.\n\n\n## What can Sigmund do? And how does Sigmund work?\n\nFor a description of how Sigmund works, see: <https://sigmundai.eu/about>. This page describes the default configuration.\n\n\n## Configuration\n\nSee `sigmund/config.py` for configuration instructions.\n\n\n## Dependencies\n\nFor Python dependencies, see `pyproject.toml`. In addition to these, `pandoc` is required for the ability to read attachments, and a local `redis` server needs to run for persistent data between sessions.\n\n\n## Running (development)\n\nDownload the source code, and in the folder of the source code execute the following:\n\n```\n# Specify API keys for model providers. Even when using Anthropic (Claude) or\n# Mistral, an OpenAI key is provided when document search is enabled\nexport OPENAI_API_KEY = 'your key here'\nexport ANTHROPIC_API_KEY = 'your key here'\nexport MISTRAL_API_KEY = 'your key here'\npip install . # install dependencies\npython index_library.py # build library (documentation) index\npython app.py # start the app\n```\n\nNext, access the app (by default) through:\n\n```\nhttps://127.0.0.1:5000/\n```\n\n\n## Running (production)\n\nIn production, the server is generally not run by directly calling the app. There are many ways to run a Flask app in production. One way is to use gunicorn to start the app, and then use an nginx web server as a proxy that reroutes requests to the app. When taking this route, make sure to set up nginx with a large `client_max_body_size` (to allow attachment uploading) and disable `proxy_cache` and `proxy_buffering` (to allow status messages to be streamed while Sigmund is answering).\n\n\n## License\n\nSigmund is distributed under the terms of the GNU General Public License 3. The full license should be included in the file `COPYING`, or can be obtained from:\n\n- <http://www.gnu.org/licenses/gpl.txt>\n",
"bugtrack_url": null,
"license": null,
"summary": "AI-based chatbot that provides sensible answers based on documentation",
"version": "0.16.7",
"project_urls": {
"Documentation": "https://sigmundai.eu",
"Source": "https://github.com/smathot/sigmundai"
},
"split_keywords": [
"ai",
" chatbot",
" llm"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2063536cc8dc9f5bb9b5ef899e1d280d28c1a5248590b598569431bec6e54314",
"md5": "0d7dd56dd117d74c43851136ca41d7ab",
"sha256": "675897c86a06e8b2d673bb62f310182706832879760c451ab649af0deba87c2e"
},
"downloads": -1,
"filename": "sigmund-0.16.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0d7dd56dd117d74c43851136ca41d7ab",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 6180302,
"upload_time": "2024-05-02T08:58:18",
"upload_time_iso_8601": "2024-05-02T08:58:18.670268Z",
"url": "https://files.pythonhosted.org/packages/20/63/536cc8dc9f5bb9b5ef899e1d280d28c1a5248590b598569431bec6e54314/sigmund-0.16.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7acbd72cb3b1f83cde206b26c1641834dc7347d88d1861a6c9e2f61064036ecc",
"md5": "99ee24efed65acd61386eeb86a874d0f",
"sha256": "d9f53317509d7244db40d37b949c6cbe72aeb5313b32c04e962cacf59882dfc3"
},
"downloads": -1,
"filename": "sigmund-0.16.7.tar.gz",
"has_sig": false,
"md5_digest": "99ee24efed65acd61386eeb86a874d0f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 6168398,
"upload_time": "2024-05-02T08:58:20",
"upload_time_iso_8601": "2024-05-02T08:58:20.530173Z",
"url": "https://files.pythonhosted.org/packages/7a/cb/d72cb3b1f83cde206b26c1641834dc7347d88d1861a6c9e2f61064036ecc/sigmund-0.16.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-02 08:58:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "smathot",
"github_project": "sigmundai",
"github_not_found": true,
"lcname": "sigmund"
}
