LLMFlex

A python package for developing AI applications with local LLMs.

Stars: 94

Visit

LLMFlex is a python package designed for developing AI applications with local Large Language Models (LLMs). It provides classes to load LLM models, embedding models, and vector databases to create AI-powered solutions with prompt engineering and RAG techniques. The package supports multiple LLMs with different generation configurations, embedding toolkits, vector databases, chat memories, prompt templates, custom tools, and a chatbot frontend interface. Users can easily create LLMs, load embeddings toolkit, use tools, chat with models in a Streamlit web app, and serve an OpenAI API with a GGUF model. LLMFlex aims to offer a simple interface for developers to work with LLMs and build private AI solutions using local resources.

README:

LLMFlex

A python package for developing AI applications with local LLMs

LLMFlex is a python package that allows python developers to work with different large language models (LLM) and do prompt engineering with a simple interface. It favours free and local resources instead of using paid APIs to develop truly local and private AI-powered solutions.

It provides classes to load LLM models, embedding models, and vector databases to create LLM powered applications with your own prompt engineering and RAG techniques. With a one-liner command, you can load a chatbot interface to chat with the LLM or serve a model as OpenAI API as well.

Installing LLMFlex

Creating a virtual environment before installing the package is highly recommended. Also make sure you have installed Pytorch and llama-cpp-python with the correct installation method according to your hardware configuration before installing LLMFlex. Please visit the links provided for the respective packages for more detailed installation guides.

After you have done the above steps, you can easily install llmflex with pip.

pip install llmflex

You can also install ExLlamaV2, AutoAWQ, and AutoGPTQ if you have CUDA devices. Please visit the links provided for the respective packages for more detailed installation guides.

Features

1. Multilple LLMs with different genration configurations from one model

Unlike Langchain, you can create multiple LLMs with different temperature, max new tokens, stop words etc. with the same underlying model without loading the model several times using the LlmFactory class. This can be useful when you create your own agent with different LLM tasks which requires different configurations.

2. Langchain compatibility with enhanced performances

All the LLMs created with LlmFactory are langchain compatible, and can be seamlessly integrated in your existing Langchain code. All the LLM classes are re-implementations of some langchain LLM classes which support more efficient streaming and stop words management, all with a unified interface.

3. Multiple model formats support

Multiple model formats are all supported, and the loading process are all handled in the LlmFactory class, so it is just plug and play. Supported formats:

PyTorch (using transformers)
GGUF (using llama-cpp-python)
AWQ (using transformers)
GPTQ (using transformers)
OpenAI API (Work with any local servers that serve models with OpenAI API format)
EXL2 (using exllamav2)

4. Embedding Toolkits

Bundled classes for using embedding models which contains the embedding model and a tokens-count-based text splitter using the embedding model.

5. Vector database

Utilising Embedding toolkits and FAISS, a VectorDatabase class can allow you to store and search texts for your RAG tasks.

6. Chat memories

Chat memory classes for storing chat memory on disk.

BaseChatMemory
Memory class without using any embedding models or vector databases.
LongShortTermChatMemory
Memory class using an underlying VectorDatabase to maintain long term memory along with the most recent memory.

7. Prompt template

A PromptTemplate class is implemented to format your prompt with different prompt formats for models from different sources. Some presets like Llama2, ChatML, Vicuna, and more are already implemented, but you can alway add your own prompt format template.

8. Custom tools

A base class BaseTool for creating llm powered tools. A BrowserTool powered by DuckDuckGo is implemented as an example.

9. Chatbot frontend interface

If you simply want to play with a model, there is a streamlit frontend chatbot that allows you to chat with a model with different generation configurations. You can switch between chat histories and prompt format, and you can set your system prompt and other model text generation sampling configurations in the webapp.

Using LLMFlex

1. Create LLMs

This is how you can start with any text generation model on HuggingFace with your machine.

from llmflex import LlmFactory

# Load the model from Huggingface
model = LlmFactory("TheBloke/OpenHermes-2.5-Mistral-7B-GGUF")

# Create a llm
llm = model(temperature=0.7, max_new_tokens=512, stop=['```'])

# Use the LLM for your task
prompt = """Instruction:
Write a python script to load a Pandas Dataframe from the csv file 'test.csv'

Solution:
```python
"""
script = llm.invoke(prompt)
print(script)

# Or if you prefer to generate the output with token streamming.
for token in llm.stream(prompt):
    print(token, end="")

2. Load embeddings toolkit and create vector database

To load an embedding model and use a vector database:

from llmflex.Embeddings import HuggingfaceEmbeddingsToolkit
from llmflex.VectorDBs import FaissVectorDatabase

# Loading the embedding model toolkit
embeddings = HuggingfaceEmbeddingsToolkit(model_id="thenlper/gte-small")

# Create a vector database
food = ["Apple", "Banana", "Pork"]
vectordb = FaissVectorDatabase.from_texts(embeddings=embeddings, texts=food)

# Do semantic search on the vector database
print(vectordb.search("Beef"))

3. Use tools

A WebSearchTool class is implemented as an example to build a tool with LLMFlex. The tool is using DuckDuckGo by default. Here is how you can use it:

from llmflex.Tools import BrowserTool

# Create a broswer tool with the embeddings toolkit created earlier
tool = BrowserTool(embeddings=embeddings)

# Run the tool
tool(search_query='Install python')

4. Chat with the model in a Streamlit web app

If you just want a GUI to start chatting with your LLM model with both long term and short term memory, type this command in the terminal:

llmflex interface

If you want to configure the llm model, embedding model, text splitter, and reranker, create a config file and modify it first:

# Create a config file for the webapp
llmflex create-app-config

after modifying the file, run the following:

llmflex interface --config_dir chatbot_config.yaml

You will see a streamlit frontend, use it to chat with the LLM model.

5. Serve an OpenAI API with a GGUF model

To serve a GGUF model with OpenAI API:

llmflex serve --model_id TheBloke/OpenHermes-2.5-Mistral-7B-GGUF --model_file openhermes-2.5-mistral-7b.Q6_K.gguf --context_size 4096

Documentations

Python documentation for all the classes, methods, and functions is provided in the ./docs directory in this repository.

License

This project is licensed under the terms of the MIT license.

For Tasks:

Click tags to check more tools for each tasks

create llms load embeddings use tools chat with models serve openai api

For Jobs:

python developer ai engineer machine learning engineer data scientist natural language processing specialist

Alternative AI tools for LLMFlex

Similar Open Source Tools

LLMFlex

github

: 94

truss

Truss is a tool that simplifies the process of serving AI/ML models in production. It provides a consistent and easy-to-use interface for packaging, testing, and deploying models, regardless of the framework they were created with. Truss also includes a live reload server for fast feedback during development, and a batteries-included model serving environment that eliminates the need for Docker and Kubernetes configuration.

github

: 966

aioli

Aioli is a library for running genomics command-line tools in the browser using WebAssembly. It creates a single WebWorker to run all WebAssembly tools, shares a filesystem across modules, and efficiently mounts local files. The tool encapsulates each module for loading, does WebAssembly feature detection, and communicates with the WebWorker using the Comlink library. Users can deploy new releases and versions, and benefit from code reuse by porting existing C/C++/Rust/etc tools to WebAssembly for browser use.

github

: 100

minimal-llm-ui

This minimalistic UI serves as a simple interface for Ollama models, enabling real-time interaction with Local Language Models (LLMs). Users can chat with models, switch between different LLMs, save conversations, and create parameter-driven prompt templates. The tool is built using React, Next.js, and Tailwind CSS, with seamless integration with LangchainJs and Ollama for efficient model switching and context storage.

github

: 246

h2o-llmstudio

H2O LLM Studio is a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). With H2O LLM Studio, you can easily and effectively fine-tune LLMs without the need for any coding experience. The GUI is specially designed for large language models, and you can finetune any LLM using a large variety of hyperparameters. You can also use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint. Additionally, you can use Reinforcement Learning (RL) to finetune your model (experimental), use advanced evaluation metrics to judge generated answers by the model, track and compare your model performance visually, and easily export your model to the Hugging Face Hub and share it with the community.

github

: 4.1k

genai-toolbox

Gen AI Toolbox for Databases is an open source server that simplifies building Gen AI tools for interacting with databases. It handles complexities like connection pooling, authentication, and more, enabling easier, faster, and more secure tool development. The toolbox sits between the application's orchestration framework and the database, providing a control plane to modify, distribute, or invoke tools. It offers simplified development, better performance, enhanced security, and end-to-end observability. Users can install the toolbox as a binary, container image, or compile from source. Configuration is done through a 'tools.yaml' file, defining sources, tools, and toolsets. The project follows semantic versioning and welcomes contributions.

github

: 495

torchchat

torchchat is a codebase showcasing the ability to run large language models (LLMs) seamlessly. It allows running LLMs using Python in various environments such as desktop, server, iOS, and Android. The tool supports running models via PyTorch, chatting, generating text, running chat in the browser, and running models on desktop/server without Python. It also provides features like AOT Inductor for faster execution, running in C++ using the runner, and deploying and running on iOS and Android. The tool supports popular hardware and OS including Linux, Mac OS, Android, and iOS, with various data types and execution modes available.

github

: 3.5k

open-deep-research

Open Deep Research is an open-source project that serves as a clone of Open AI's Deep Research experiment. It utilizes Firecrawl's extract and search method along with a reasoning model to conduct in-depth research on the web. The project features Firecrawl Search + Extract, real-time data feeding to AI via search, structured data extraction from multiple websites, Next.js App Router for advanced routing, React Server Components and Server Actions for server-side rendering, AI SDK for generating text and structured objects, support for various model providers, styling with Tailwind CSS, data persistence with Vercel Postgres and Blob, and simple and secure authentication with NextAuth.js.

github

: 4.4k

blockoli

Blockoli is a high-performance tool for code indexing, embedding generation, and semantic search tool for use with LLMs. It is built in Rust and uses the ASTerisk crate for semantic code parsing. Blockoli allows you to efficiently index, store, and search code blocks and their embeddings using vector similarity. Key features include indexing code blocks from a codebase, generating vector embeddings for code blocks using a pre-trained model, storing code blocks and their embeddings in a SQLite database, performing efficient similarity search on code blocks using vector embeddings, providing a REST API for easy integration with other tools and platforms, and being fast and memory-efficient due to its implementation in Rust.

github

: 53

CoML

CoML (formerly MLCopilot) is an interactive coding assistant for data scientists and machine learning developers, empowered on large language models. It offers an out-of-the-box interactive natural language programming interface for data mining and machine learning tasks, integration with Jupyter lab and Jupyter notebook, and a built-in large knowledge base of machine learning to enhance the ability to solve complex tasks. The tool is designed to assist users in coding tasks related to data analysis and machine learning using natural language commands within Jupyter environments.

github

: 57

labs-ai-tools-for-devs

This repository provides AI tools for developers through Docker containers, enabling agentic workflows. It allows users to create complex workflows using Dockerized tools and Markdown, leveraging various LLM models. The core features include Dockerized tools, conversation loops, multi-model agents, project-first design, and trackable prompts stored in a git repo.

github

: 126

lmql

LMQL is a programming language designed for large language models (LLMs) that offers a unique way of integrating traditional programming with LLM interaction. It allows users to write programs that combine algorithmic logic with LLM calls, enabling model reasoning capabilities within the context of the program. LMQL provides features such as Python syntax integration, rich control-flow options, advanced decoding techniques, powerful constraints via logit masking, runtime optimization, sync and async API support, multi-model compatibility, and extensive applications like JSON decoding and interactive chat interfaces. The tool also offers library integration, flexible tooling, and output streaming options for easy model output handling.

github

: 3.4k

python-sc2

python-sc2 is an easy-to-use library for writing AI Bots for StarCraft II in Python 3. It aims for simplicity and ease of use while providing both high and low level abstractions. The library covers only the raw scripted interface and intends to help new bot authors with added functions. Users can install the library using pip and need a StarCraft II executable to run bots. The API configuration options allow users to customize bot behavior and performance. The community provides support through Discord servers, and users can contribute to the project by creating new issues or pull requests following style guidelines.

github

: 480

metavoice-src

MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities: * Emotional speech rhythm and tone in English. * Zero-shot cloning for American & British voices, with 30s reference audio. * Support for (cross-lingual) voice cloning with finetuning. * We have had success with as little as 1 minute training data for Indian speakers. * Synthesis of arbitrary length text

github

: 3.1k

neo4j-genai-python

This repository contains the official Neo4j GenAI features for Python. The purpose of this package is to provide a first-party package to developers, where Neo4j can guarantee long-term commitment and maintenance as well as being fast to ship new features and high-performing patterns and methods.

github

: 88

open-source-slack-ai

This repository provides a ready-to-run basic Slack AI solution that allows users to summarize threads and channels using OpenAI. Users can generate thread summaries, channel overviews, channel summaries since a specific time, and full channel summaries. The tool is powered by GPT-3.5-Turbo and an ensemble of NLP models. It requires Python 3.8 or higher, an OpenAI API key, Slack App with associated API tokens, Poetry package manager, and ngrok for local development. Users can customize channel and thread summaries, run tests with coverage using pytest, and contribute to the project for future enhancements.

github

: 142

For similar tasks

elia

Elia is a powerful terminal user interface designed for interacting with large language models. It allows users to chat with models like Claude 3, ChatGPT, Llama 3, Phi 3, Mistral, and Gemma. Conversations are stored locally in a SQLite database, ensuring privacy. Users can run local models through 'ollama' without data leaving their machine. Elia offers easy installation with pipx and supports various environment variables for different models. It provides a quick start to launch chats and manage local models. Configuration options are available to customize default models, system prompts, and add new models. Users can import conversations from ChatGPT and wipe the database when needed. Elia aims to enhance user experience in interacting with language models through a user-friendly interface.

github

: 1.8k

mistral-inference

Mistral Inference repository contains minimal code to run 7B, 8x7B, and 8x22B models. It provides model download links, installation instructions, and usage guidelines for running models via CLI or Python. The repository also includes information on guardrailing, model platforms, deployment, and references. Users can interact with models through commands like mistral-demo, mistral-chat, and mistral-common. Mistral AI models support function calling and chat interactions for tasks like testing models, chatting with models, and using Codestral as a coding assistant. The repository offers detailed documentation and links to blogs for further information.

github

: 10.1k

LLMFlex

github

: 94

minimal-chat

MinimalChat is a minimal and lightweight open-source chat application with full mobile PWA support that allows users to interact with various language models, including GPT-4 Omni, Claude Opus, and various Local/Custom Model Endpoints. It focuses on simplicity in setup and usage while being fully featured and highly responsive. The application supports features like fully voiced conversational interactions, multiple language models, markdown support, code syntax highlighting, DALL-E 3 integration, conversation importing/exporting, and responsive layout for mobile use.

github

: 171

chat-with-mlx

Chat with MLX is an all-in-one Chat Playground using Apple MLX on Apple Silicon Macs. It provides privacy-enhanced AI for secure conversations with various models, easy integration of HuggingFace and MLX Compatible Open-Source Models, and comes with default models like Llama-3, Phi-3, Yi, Qwen, Mistral, Codestral, Mixtral, StableLM. The tool is designed for developers and researchers working with machine learning models on Apple Silicon.

github

: 1.5k

transformerlab-app

Transformer Lab is an app that allows users to experiment with Large Language Models by providing features such as one-click download of popular models, finetuning across different hardware, RLHF and Preference Optimization, working with LLMs across different operating systems, chatting with models, using different inference engines, evaluating models, building datasets for training, calculating embeddings, providing a full REST API, running in the cloud, converting models across platforms, supporting plugins, embedded Monaco code editor, prompt editing, inference logs, all through a simple cross-platform GUI.

github

: 1.5k

ell

ell is a command-line interface for Language Model Models (LLMs) written in Bash. It allows users to interact with LLMs from the terminal, supports piping, context bringing, and chatting with LLMs. Users can also call functions and use templates. The tool requires bash, jq for JSON parsing, curl for HTTPS requests, and perl for PCRE. Configuration involves setting variables for different LLM models and APIs. Usage examples include asking questions, specifying models, recording input/output, running in interactive mode, and using templates. The tool is lightweight, easy to install, and pipe-friendly, making it suitable for interacting with LLMs in a terminal environment.

github

: 428

Ollama-SwiftUI

Ollama-SwiftUI is a user-friendly interface for Ollama.ai created in Swift. It allows seamless chatting with local Large Language Models on Mac. Users can change models mid-conversation, restart conversations, send system prompts, and use multimodal models with image + text. The app supports managing models, including downloading, deleting, and duplicating them. It offers light and dark mode, multiple conversation tabs, and a localized interface in English and Arabic.

github

: 217

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 620

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k