[](https://youtu.be/M860LUfwiQc)
## About
LeapTable is an experimental agent framework powered by GPT-4 that operates on dataframes.
Leaptable unleashes the future with AI Agents that work for you. These virtual assistants automate workflows,
search the web, explore LinkedIn, and more - with human-like intelligence but without human limitations.
Leaptable combines an effortless a low-code database, dozens of tireless AI agents and powerful Language Models like
GPT, so you can manage data smarter, not harder. Let AI Agents do the work so you can focus on insights.
[Installation](#installation) | [Quick Start](#quick-start) | [Documentation](#documentation)
## Installation
By far the easiest way to install the LeapTable server is to use docker.
```sql
wget https://git.leaptable.co/docker-compose.yaml
docker compose -p leaptable -d
```
https://discord.gg/KkFzHRTF5K
### Install reframe client
```shell
pip install leaptable
```
## LeapTable strives to be
* 🥽 Transparent - through logging, and metrics that create visibility into the inner operations.
* 🤸🏾 Flexible - AI Agents and tools are independent of each other, allowing you to create workflows easily.
* 🧩 Composable. LeapTable are simply executable python functions and classes with a well defined interface. You can easily construct sophisticated agents from basic building blocks. These building blocks can be obtained from our ecosystem or you can develop custom ones that are specific to your organization.
* 🛹 Incrementally adoptable - By using existing technologies such as Docker, Kubernetes and Celery Aigent enables you to seamlessly adopt it with your organization. From simple ZeroShot agents to sophisticated multi-step AI agents each component can be integrated into your existing workflows.
* 🔨 Reusable - once a tool is running, it can be utilized by various agents, thereby reducing operational overhead, increasing throughput and making tools easy to reason about.
* 🏎️ Fast by taking advantage of data parallelism and prompt sequencing in a manner increases efficiency and reduces the overall number of expensive API calls made to LLM endpoints.
* 🏟️ Rich ecosystem that enables your to pick and choose which tools and agents to deploy. Through contributions from open source developers, we are making great progress to develop a robust ecosystem of tools so that you always have a tool for the job.
# Features
* 🌐 Internet access for searches and information gathering
* 📥 Long-term and short-term memory management
* 🧠 GPT-4 & Anthropic instances for text generation
* 🔗 Access to popular websites and platforms
* 🗃️ File storage and summarization with GPT-3.5
* 🔌 Extensibility with Plugins
## Documentation
More documentation is available here: [https://leaptable.co/docs](https://to.leaptable.is/f0Ms)
Raw data
{
"_id": null,
"home_page": "https://leaptable.us/docs/",
"name": "leaptable",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9,<4.0",
"maintainer_email": "",
"keywords": "leaptable,agents,dataframes,client",
"author": "LeapTable Team",
"author_email": "pypi@leaptable.us",
"download_url": "https://files.pythonhosted.org/packages/22/02/bc633801e5ad26e4c21bed85df017a871d2222751004b6c116f35bd5e1ec/leaptable-0.0.1.tar.gz",
"platform": null,
"description": "[](https://youtu.be/M860LUfwiQc)\n\n## About\n\n\nLeapTable is an experimental agent framework powered by GPT-4 that operates on dataframes.\n\nLeaptable unleashes the future with AI Agents that work for you. These virtual assistants automate workflows,\nsearch the web, explore LinkedIn, and more - with human-like intelligence but without human limitations.\nLeaptable combines an effortless a low-code database, dozens of tireless AI agents and powerful Language Models like\nGPT, so you can manage data smarter, not harder. Let AI Agents do the work so you can focus on insights.\n\n\n\n\n[Installation](#installation) | [Quick Start](#quick-start) | [Documentation](#documentation)\n\n## Installation\n\nBy far the easiest way to install the LeapTable server is to use docker.\n\n```sql\nwget https://git.leaptable.co/docker-compose.yaml\ndocker compose -p leaptable -d\n```\n\nhttps://discord.gg/KkFzHRTF5K\n\n### Install reframe client\n```shell\npip install leaptable\n```\n\n## LeapTable strives to be\n\n* \ud83e\udd7d Transparent - through logging, and metrics that create visibility into the inner operations.\n* \ud83e\udd38\ud83c\udffe Flexible - AI Agents and tools are independent of each other, allowing you to create workflows easily.\n* \ud83e\udde9 Composable. LeapTable are simply executable python functions and classes with a well defined interface. You can easily construct sophisticated agents from basic building blocks. These building blocks can be obtained from our ecosystem or you can develop custom ones that are specific to your organization.\n* \ud83d\udef9 Incrementally adoptable - By using existing technologies such as Docker, Kubernetes and Celery Aigent enables you to seamlessly adopt it with your organization. From simple ZeroShot agents to sophisticated multi-step AI agents each component can be integrated into your existing workflows.\n* \ud83d\udd28 Reusable - once a tool is running, it can be utilized by various agents, thereby reducing operational overhead, increasing throughput and making tools easy to reason about.\n* \ud83c\udfce\ufe0f Fast by taking advantage of data parallelism and prompt sequencing in a manner increases efficiency and reduces the overall number of expensive API calls made to LLM endpoints.\n* \ud83c\udfdf\ufe0f Rich ecosystem that enables your to pick and choose which tools and agents to deploy. Through contributions from open source developers, we are making great progress to develop a robust ecosystem of tools so that you always have a tool for the job.\n\n# Features\n* \ud83c\udf10 Internet access for searches and information gathering\n* \ud83d\udce5 Long-term and short-term memory management \n* \ud83e\udde0 GPT-4 & Anthropic instances for text generation \n* \ud83d\udd17 Access to popular websites and platforms \n* \ud83d\uddc3\ufe0f File storage and summarization with GPT-3.5 \n* \ud83d\udd0c Extensibility with Plugins\n\n## Documentation\n\nMore documentation is available here: [https://leaptable.co/docs](https://to.leaptable.is/f0Ms)\n",
"bugtrack_url": null,
"license": "",
"summary": "Create, run and manage your intelligent LLM agents on dataframes.",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://leaptable.us/docs/",
"Repository": "https://github.com/peterwnjenga/leaptable"
},
"split_keywords": [
"leaptable",
"agents",
"dataframes",
"client"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "df5c9c0a16bbfa6866c0c129896f81dae4869939408c28623af6098198ed27e7",
"md5": "f67ba20570b72b444eb3052bb8b8779c",
"sha256": "53f5219a83aaac4bafff4cffc9f64f7e3833f5c34430157931c35e85340ef5b4"
},
"downloads": -1,
"filename": "leaptable-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f67ba20570b72b444eb3052bb8b8779c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9,<4.0",
"size": 114427,
"upload_time": "2023-09-16T05:57:26",
"upload_time_iso_8601": "2023-09-16T05:57:26.032988Z",
"url": "https://files.pythonhosted.org/packages/df/5c/9c0a16bbfa6866c0c129896f81dae4869939408c28623af6098198ed27e7/leaptable-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2202bc633801e5ad26e4c21bed85df017a871d2222751004b6c116f35bd5e1ec",
"md5": "dbd29c5badf289f1c462518477aeb784",
"sha256": "0d41e084e5418e60aa56b3124b69096d23bd425d07cd1837bbe42e64ddd53cdc"
},
"downloads": -1,
"filename": "leaptable-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "dbd29c5badf289f1c462518477aeb784",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9,<4.0",
"size": 80938,
"upload_time": "2023-09-16T05:57:29",
"upload_time_iso_8601": "2023-09-16T05:57:29.139099Z",
"url": "https://files.pythonhosted.org/packages/22/02/bc633801e5ad26e4c21bed85df017a871d2222751004b6c116f35bd5e1ec/leaptable-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-16 05:57:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "peterwnjenga",
"github_project": "leaptable",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "leaptable"
}
JSON
