<p align="center">
<img src="https://github.com/ENDEVSOLS/Long-Trainer/blob/master/assets/longtrainer-logo.png?raw=true" alt="LongTrainer Logo">
</p>
<h1 align="center">LongTrainer - Production-Ready LangChain</h1>
<p align="center">
<a href="https://pypi.org/project/longtrainer/">
<img src="https://img.shields.io/pypi/v/longtrainer" alt="PyPI Version">
</a>
<a href="https://pepy.tech/project/longtrainer">
<img src="https://static.pepy.tech/badge/longtrainer" alt="Total Downloads">
</a>
<a href="https://pepy.tech/project/longtrainer">
<img src="https://static.pepy.tech/badge/longtrainer/month" alt="Monthly Downloads">
</a>
<a href="https://colab.research.google.com/drive/1HE30D5q5onD8sfS50-06XPDXnbdvnjIy?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab">
</a>
</p>
<hr />
<p align="center">
<a href="https://endevsols.com/longtrainer-the-next-evolution-in-production-ready-langchain-frameworks/">
Visit Blog Post
</a>
</p>
<p align="center">
<a class="github-button" href="https://github.com/ENDEVSOLS/Long-Trainer" data-color-scheme="no-preference: light; light: light; dark: dark;" data-size="large" data-show-count="true" aria-label="Star ENDEVSOLS/Long-Trainer on GitHub">Star</a>
<a class="github-button" href="https://github.com/ENDEVSOLS" data-color-scheme="no-preference: light; light: light; dark: dark;" data-size="large" data-show-count="true" aria-label="Follow @ENDEVSOLS on GitHub">Follow @ENDEVSOLS</a>
</p>
# Official Documentation
Explore the comprehensive [LongTrainer Documentation](https://endevsols.github.io/Long-Trainer/) for detailed
instructions on installation, features, and API usage.
# Installation
Introducing LongTrainer, a sophisticated extension of the LangChain framework designed specifically for managing
multiple bots and providing isolated, context-aware chat sessions. Ideal for developers and businesses looking to
integrate complex conversational AI into their systems, LongTrainer simplifies the deployment and customization of LLMs.
```markdown
pip install longtrainer
```
## Installation Instructions for Required Libraries and Tools
### 1. Linux (Ubuntu/Debian)
To install the required packages on a Linux system (specifically Ubuntu or Debian), you can use the apt package manager.
The following command installs several essential libraries and tools:
```markdown
sudo apt install libmagic-dev poppler-utils tesseract-ocr qpdf libreoffice pandoc
```
### 2. macOS
On macOS, you can install these packages using brew, the Homebrew package manager. If you don't have Homebrew installed,
you can install it from brew.sh.
```markdown
brew install libmagic poppler tesseract qpdf libreoffice pandoc
```
# Features 🌟
- ✅ **Long Memory:** Retains context effectively for extended interactions.
- ✅ **Multi-Bot Management:** Easily configure and manage multiple bots within a single framework, perfect for scaling
across various use cases
- ✅ **Isolated Chat Sessions:** Each bot operates within its own session, ensuring interactions remain distinct and
contextually relevant without overlap.
- ✅ **Context-Aware Interactions:** Utilize enhanced memory capabilities to maintain context over extended dialogues,
significantly improving user experience
- ✅ **Scalable Architecture:** Designed to scale effortlessly with your needs, whether you're handling hundreds of users
or just a few.
- ✅ **Enhanced Customization:** Tailor the behavior to fit specific needs.
- ✅ **Memory Management:** Efficient handling of chat histories and contexts.
- ✅ **GPT Vision Support:** Integration Context Aware GPT-powered visual models.
- ✅ **Different Data Formats:** Supports various data input formats.
- ✅ **VectorStore Management:** Advanced management of vector storage for efficient retrieval.
## Diverse Use Cases:
- ✅ **Enterprise Solutions:** Streamline customer interactions, automate responses, and manage multiple departmental
bots from a single platform.
- ✅ **Educational Platforms:** Enhance learning experiences with AI tutors capable of maintaining context throughout
sessions.
- ✅ **Healthcare Applications:** Support patient management with bots that provide consistent, context-aware
interactions.
## Works for All Langchain Supported LLM and Embeddings
- ✅ OpenAI (default)
- ✅ VertexAI
- ✅ HuggingFace
- ✅ AWS Bedrock
- ✅ Groq
- ✅ TogetherAI
# Example
VertexAI LLMs
```python
from longtrainer.trainer import LongTrainer
from langchain_community.llms import VertexAI
llm = VertexAI()
trainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', llm=llm)
```
TogetherAI LLMs
```python
from longtrainer.trainer import LongTrainer
from langchain_community.llms import Together
llm = Together(
model="togethercomputer/RedPajama-INCITE-7B-Base",
temperature=0.7,
max_tokens=128,
top_k=1,
# together_api_key="..."
)
trainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', llm=llm)
```
## Usage Example 🚀
Here's a quick start guide on how to use LongTrainer:
```python
from longtrainer.trainer import LongTrainer
import os
# Set your OpenAI API key
os.environ["OPENAI_API_KEY"] = "sk-"
# Initialize LongTrainer
trainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', ensemble=True, encrypt_chats=True)
bot_id = trainer.initialize_bot_id()
print('Bot ID: ', bot_id)
# Add Data
path = 'path/to/your/data'
trainer.add_document_from_path(path, bot_id)
# Initialize Bot
trainer.create_bot(bot_id)
# Start a New Chat
chat_id = trainer.new_chat(bot_id)
# Send a Query and Get a Response
query = 'Your query here'
response = trainer.get_response(query, bot_id, chat_id)
print('Response: ', response)
```
Here's a guide on how to use Vision Chat:
```python
chat_id = trainer.new_vision_chat(bot_id)
query = 'Your query here'
image_paths = ['nvidia.jpg']
response = trainer.get_vision_response(query, image_paths, str(bot_id), str(vision_id))
print('Response: ', response)
```
List Chats and Display Chat History:
```python
trainer.list_chats(bot_id)
trainer.get_chat_by_id(chat_id=chat_id)
```
This project is still under active development. Community feedback and contributions are highly appreciated.
## Citation
If you utilize this repository, please consider citing it with:
```
@misc{longtrainer,
author = {Endevsols},
title = {LongTrainer: Production-Ready LangChain},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/ENDEVSOLS/Long-Trainer}},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/ENDEVSOLS/Long-Trainer",
"name": "longtrainer",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Endevsols",
"author_email": "technology@endevsols.com",
"download_url": "https://files.pythonhosted.org/packages/59/e1/65ca0778c96e06c6ae74f8954e8cbb57b5cadcf91e1a35bd8a8021393775/longtrainer-0.3.4.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img src=\"https://github.com/ENDEVSOLS/Long-Trainer/blob/master/assets/longtrainer-logo.png?raw=true\" alt=\"LongTrainer Logo\">\n</p>\n\n<h1 align=\"center\">LongTrainer - Production-Ready LangChain</h1>\n\n<p align=\"center\">\n <a href=\"https://pypi.org/project/longtrainer/\">\n <img src=\"https://img.shields.io/pypi/v/longtrainer\" alt=\"PyPI Version\">\n </a>\n <a href=\"https://pepy.tech/project/longtrainer\">\n <img src=\"https://static.pepy.tech/badge/longtrainer\" alt=\"Total Downloads\">\n </a>\n <a href=\"https://pepy.tech/project/longtrainer\">\n <img src=\"https://static.pepy.tech/badge/longtrainer/month\" alt=\"Monthly Downloads\">\n </a>\n <a href=\"https://colab.research.google.com/drive/1HE30D5q5onD8sfS50-06XPDXnbdvnjIy?usp=sharing\">\n <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open in Colab\">\n </a>\n</p>\n<hr />\n<p align=\"center\">\n <a href=\"https://endevsols.com/longtrainer-the-next-evolution-in-production-ready-langchain-frameworks/\">\n Visit Blog Post\n </a>\n</p>\n\n<p align=\"center\">\n <a class=\"github-button\" href=\"https://github.com/ENDEVSOLS/Long-Trainer\" data-color-scheme=\"no-preference: light; light: light; dark: dark;\" data-size=\"large\" data-show-count=\"true\" aria-label=\"Star ENDEVSOLS/Long-Trainer on GitHub\">Star</a>\n <a class=\"github-button\" href=\"https://github.com/ENDEVSOLS\" data-color-scheme=\"no-preference: light; light: light; dark: dark;\" data-size=\"large\" data-show-count=\"true\" aria-label=\"Follow @ENDEVSOLS on GitHub\">Follow @ENDEVSOLS</a>\n</p>\n\n\n# Official Documentation\n\nExplore the comprehensive [LongTrainer Documentation](https://endevsols.github.io/Long-Trainer/) for detailed\ninstructions on installation, features, and API usage.\n\n# Installation\n\nIntroducing LongTrainer, a sophisticated extension of the LangChain framework designed specifically for managing\nmultiple bots and providing isolated, context-aware chat sessions. Ideal for developers and businesses looking to\nintegrate complex conversational AI into their systems, LongTrainer simplifies the deployment and customization of LLMs.\n\n```markdown\npip install longtrainer\n```\n\n## Installation Instructions for Required Libraries and Tools\n\n### 1. Linux (Ubuntu/Debian)\n\nTo install the required packages on a Linux system (specifically Ubuntu or Debian), you can use the apt package manager.\nThe following command installs several essential libraries and tools:\n\n```markdown\nsudo apt install libmagic-dev poppler-utils tesseract-ocr qpdf libreoffice pandoc\n```\n\n### 2. macOS\n\nOn macOS, you can install these packages using brew, the Homebrew package manager. If you don't have Homebrew installed,\nyou can install it from brew.sh.\n\n```markdown\nbrew install libmagic poppler tesseract qpdf libreoffice pandoc\n```\n\n# Features \ud83c\udf1f\n\n- \u2705 **Long Memory:** Retains context effectively for extended interactions.\n- \u2705 **Multi-Bot Management:** Easily configure and manage multiple bots within a single framework, perfect for scaling\n across various use cases\n- \u2705 **Isolated Chat Sessions:** Each bot operates within its own session, ensuring interactions remain distinct and\n contextually relevant without overlap.\n- \u2705 **Context-Aware Interactions:** Utilize enhanced memory capabilities to maintain context over extended dialogues,\n significantly improving user experience\n- \u2705 **Scalable Architecture:** Designed to scale effortlessly with your needs, whether you're handling hundreds of users\n or just a few.\n- \u2705 **Enhanced Customization:** Tailor the behavior to fit specific needs.\n- \u2705 **Memory Management:** Efficient handling of chat histories and contexts.\n- \u2705 **GPT Vision Support:** Integration Context Aware GPT-powered visual models.\n- \u2705 **Different Data Formats:** Supports various data input formats.\n- \u2705 **VectorStore Management:** Advanced management of vector storage for efficient retrieval.\n\n## Diverse Use Cases:\n\n- \u2705 **Enterprise Solutions:** Streamline customer interactions, automate responses, and manage multiple departmental\n bots from a single platform.\n- \u2705 **Educational Platforms:** Enhance learning experiences with AI tutors capable of maintaining context throughout\n sessions.\n- \u2705 **Healthcare Applications:** Support patient management with bots that provide consistent, context-aware\n interactions.\n\n## Works for All Langchain Supported LLM and Embeddings\n\n- \u2705 OpenAI (default)\n- \u2705 VertexAI\n- \u2705 HuggingFace\n- \u2705 AWS Bedrock\n- \u2705 Groq\n- \u2705 TogetherAI\n\n# Example\n\nVertexAI LLMs\n\n```python\nfrom longtrainer.trainer import LongTrainer\nfrom langchain_community.llms import VertexAI\n\nllm = VertexAI()\n\ntrainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', llm=llm)\n```\n\nTogetherAI LLMs\n\n```python\nfrom longtrainer.trainer import LongTrainer\nfrom langchain_community.llms import Together\n\nllm = Together(\n model=\"togethercomputer/RedPajama-INCITE-7B-Base\",\n temperature=0.7,\n max_tokens=128,\n top_k=1,\n # together_api_key=\"...\"\n)\n\ntrainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', llm=llm)\n\n```\n\n## Usage Example \ud83d\ude80\n\nHere's a quick start guide on how to use LongTrainer:\n\n```python\nfrom longtrainer.trainer import LongTrainer\nimport os\n\n# Set your OpenAI API key\nos.environ[\"OPENAI_API_KEY\"] = \"sk-\"\n\n# Initialize LongTrainer\ntrainer = LongTrainer(mongo_endpoint='mongodb://localhost:27017/', ensemble=True, encrypt_chats=True)\nbot_id = trainer.initialize_bot_id()\nprint('Bot ID: ', bot_id)\n\n# Add Data\npath = 'path/to/your/data'\ntrainer.add_document_from_path(path, bot_id)\n\n# Initialize Bot\ntrainer.create_bot(bot_id)\n\n# Start a New Chat\nchat_id = trainer.new_chat(bot_id)\n\n# Send a Query and Get a Response\nquery = 'Your query here'\nresponse = trainer.get_response(query, bot_id, chat_id)\nprint('Response: ', response)\n ```\n\nHere's a guide on how to use Vision Chat:\n\n```python\nchat_id = trainer.new_vision_chat(bot_id)\n\nquery = 'Your query here'\nimage_paths = ['nvidia.jpg']\nresponse = trainer.get_vision_response(query, image_paths, str(bot_id), str(vision_id))\nprint('Response: ', response)\n```\n\nList Chats and Display Chat History:\n\n```python\ntrainer.list_chats(bot_id)\n\ntrainer.get_chat_by_id(chat_id=chat_id)\n```\n\nThis project is still under active development. Community feedback and contributions are highly appreciated.\n\n## Citation\n\nIf you utilize this repository, please consider citing it with:\n\n```\n@misc{longtrainer,\n author = {Endevsols},\n title = {LongTrainer: Production-Ready LangChain},\n year = {2023},\n publisher = {GitHub},\n journal = {GitHub repository},\n howpublished = {\\url{https://github.com/ENDEVSOLS/Long-Trainer}},\n}\n```\n\n",
"bugtrack_url": null,
"license": null,
"summary": "Production Ready LangChain",
"version": "0.3.4",
"project_urls": {
"Homepage": "https://github.com/ENDEVSOLS/Long-Trainer"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "98a4ec4384079e9ca1ee19b6abe211b5c6ee92b80f0072a9494a40d0e0081595",
"md5": "c75889470b2710713e090277ad444388",
"sha256": "c8f7a773f390f4229423d2d318382111d7e63556d9baa1e5f27cafc0202b6b2f"
},
"downloads": -1,
"filename": "longtrainer-0.3.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c75889470b2710713e090277ad444388",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 22389,
"upload_time": "2024-12-17T13:18:09",
"upload_time_iso_8601": "2024-12-17T13:18:09.440671Z",
"url": "https://files.pythonhosted.org/packages/98/a4/ec4384079e9ca1ee19b6abe211b5c6ee92b80f0072a9494a40d0e0081595/longtrainer-0.3.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "59e165ca0778c96e06c6ae74f8954e8cbb57b5cadcf91e1a35bd8a8021393775",
"md5": "2331a8bc868503d0be392fc40c75f39a",
"sha256": "17ee9f7ce24fb7d242f2eea005cad8f369838104ca440d2290cc5efd89a92e25"
},
"downloads": -1,
"filename": "longtrainer-0.3.4.tar.gz",
"has_sig": false,
"md5_digest": "2331a8bc868503d0be392fc40c75f39a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 23138,
"upload_time": "2024-12-17T13:18:13",
"upload_time_iso_8601": "2024-12-17T13:18:13.483519Z",
"url": "https://files.pythonhosted.org/packages/59/e1/65ca0778c96e06c6ae74f8954e8cbb57b5cadcf91e1a35bd8a8021393775/longtrainer-0.3.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-17 13:18:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ENDEVSOLS",
"github_project": "Long-Trainer",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "langchain-core",
"specs": [
[
"==",
"0.3.17"
]
]
},
{
"name": "openai",
"specs": [
[
"==",
"1.54.4"
]
]
},
{
"name": "faiss-cpu",
"specs": [
[
"==",
"1.9.0"
]
]
},
{
"name": "tiktoken",
"specs": [
[
"==",
"0.8.0"
]
]
},
{
"name": "wikipedia",
"specs": [
[
"==",
"1.4.0"
]
]
},
{
"name": "langchain",
"specs": [
[
"==",
"0.3.0"
]
]
},
{
"name": "youtube-transcript-api",
"specs": [
[
"==",
"0.6.2"
]
]
},
{
"name": "pytube",
"specs": [
[
"==",
"15.0.0"
]
]
},
{
"name": "pypdf",
"specs": [
[
"==",
"5.1.0"
]
]
},
{
"name": "docx2txt",
"specs": [
[
"==",
"0.8"
]
]
},
{
"name": "fastapi",
"specs": [
[
"==",
"0.115.5"
]
]
},
{
"name": "uvicorn",
"specs": [
[
"==",
"0.32.0"
]
]
},
{
"name": "pydantic",
"specs": [
[
"==",
"2.9.2"
]
]
},
{
"name": "pandas",
"specs": [
[
"==",
"2.2.3"
]
]
},
{
"name": "pymongo",
"specs": [
[
"==",
"4.10.1"
]
]
},
{
"name": "python-docx",
"specs": [
[
"==",
"1.1.2"
]
]
},
{
"name": "langchain-openai",
"specs": [
[
"==",
"0.2.8"
]
]
},
{
"name": "langchain-community",
"specs": [
[
"==",
"0.3.0"
]
]
},
{
"name": "cryptography",
"specs": [
[
"==",
"43.0.3"
]
]
},
{
"name": "duckduckgo-search",
"specs": [
[
"==",
"6.3.5"
]
]
},
{
"name": "python-magic",
"specs": [
[
"==",
"0.4.27"
]
]
},
{
"name": "unstructured",
"specs": [
[
"==",
"0.15.7"
]
]
},
{
"name": "unstructured",
"specs": []
},
{
"name": "langchain-unstructured",
"specs": []
}
],
"lcname": "longtrainer"
}
JSON
