flow-prompt
Open source library for production prompt engineering and load balancing of AI Models
Stars: 68
Flow Prompt is a dynamic library for managing and optimizing prompts for large language models. It facilitates budget-aware operations, dynamic data integration, and efficient load distribution. Features include CI/CD testing, dynamic prompt development, multi-model support, real-time insights, and prompt testing and evolution.
README:
Flow Prompt is a dynamic, all-in-one library designed for managing and optimizing prompts and making tests based on the ideal answer for large language models (LLMs) in production and R&D. It facilitates budget-aware operations, dynamic data integration, latency and cost metrics visibility, and efficient load distribution across multiple AI models.
- CI/CD testing: Generates tests based on the context and ideal answer (usually written by the human).
- Dynamic Prompt Development: Avoid budget exceptions with dynamic data.
- Multi-Model Support: Seamlessly integrate with various LLMs like OpenAI, Anthropic, and more.
- Real-Time Insights: Monitor interactions, request/response metrics in production.
- Prompt Testing and Evolution: Quickly test and iterate on prompts using historical data.
Install Flow Prompt using pip:
pip install flow-prompt# setting as os.env
os.setenv('OPENAI_API_KEY', 'your_key_here')
# or creating flow_prompt obj
FlowPrompt(openai_key="your_key", openai_org="your_org")Add Azure keys to accommodate multiple realms:
# setting as os.env
os.setenv('AZURE_KEYS', '{"name_realm":{"url": "https://baseurl.azure.com/","key": "secret"}}')
# or creating flow_prompt obj
FlowPrompt(azure_keys={"realm_name":{"url": "https://baseurl.azure.com/", "key": "your_secret"}})Mix models easily, and districute the load across models. The system will automatically distribute your load based on the weights. We support:
- Claude
- Gemini
- OpenAI (Azure OpenAI models)
def_behaviour = behaviour.AIModelsBehaviour(attempts=[
AttemptToCall(
ai_model=OpenAIModel(
model='gpt-4o',
max_tokens=128_000,
),
weight=100
),
AttemptToCall(
ai_model=AzureAIModel(
realm='useast,
deployment_id='gpt-4o',
max_tokens=128_000,
),
weight=100
),
AttemptToCall(
ai_model=ClaudeAIModel(
model = 'claude-3-5-sonnet-20240620',
max_tokens=200_000,
),
weight=100
),
AttemptToCall(
ai_model=GeminiAIModel(
model = 'gemini-1.5-pro',
max_tokens=1_000_000,
),
weight=100
)
])
response_llm = fp.call(agent.id, context, def_behaviour)
Obtain an API token from Flow Prompt and add it:
# As an environment variable:
os.setenv('FLOW_PROMPT_API_TOKEN', 'your_token_here')
# Via code:
FlowPrompt(api_token='your_api_token')- use OPENAI_BEHAVIOR
- or add your own Behaviour, you can set max count of attempts, if you have different AI Models, if the first attempt will fail because of retryable error, the second will be called, based on the weights.
from flow_prompt import OPENAI_GPT4_0125_PREVIEW_BEHAVIOUR
flow_behaviour = OPENAI_GPT4_0125_PREVIEW_BEHAVIOUR
or:
from flow_prompt import behaviour
flow_behaviour = behaviour.AIModelsBehaviour(
attempts=[
AttemptToCall(
ai_model=AzureAIModel(
realm='us-east-1',
deployment_name="gpt-4-1106-preview",
max_tokens=C_128K,
support_functions=True,
),
weight=100,
),
AttemptToCall(
ai_model=OpenAIModel(
model="gpt-4-1106-preview",
max_tokens=C_128K,
support_functions=True,
),
weight=100,
),
]
)
from flow_prompt import FlowPrompt, PipePrompt
# Initialize and configure FlowPrompt
flow = FlowPrompt(openai_key='your_api_key', openai_org='your_org')
# Create a prompt
prompt = PipePrompt('greet_user')
prompt.add("You're {name}. Say Hello and ask what's their name.", role="system")
# Call AI model with FlowPrompt
context = {"name": "John Doe"}
# test_data - optional parameter used for generating tests
response = flow.call(prompt.id, context, flow_behaviour, test_data={
'ideal_answer': "Hello, I'm John Doe. What's your name?",
'behavior_name': "gemini"
}
)
print(response.content)-
To review your created tests and score please go to https://cloud.flow-prompt.com/tests. You can update there Prompt and rerun tests for a published version, or saved version. If you will update and publish version online - library will automatically use the new updated version of the prompt. It's made for updating prompt without redeployment of the code, which is costly operation to do if it's required to update just prompt.
-
To review logs please proceed to https://cloud.flow-prompt.com/logs, there you can see metrics like latency, cost, tokens;
For production environments, it is recommended to store secrets securely and not directly in your codebase. Consider using a secret management service or encrypted environment variables.
We welcome contributions! Please see our Contribution Guidelines for more information on how to get involved.
This project is licensed under the Apache2.0 License - see the LICENSE file for details.
For support or contributions, please contact us via GitHub Issues.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for flow-prompt
Similar Open Source Tools
flow-prompt
Flow Prompt is a dynamic library for managing and optimizing prompts for large language models. It facilitates budget-aware operations, dynamic data integration, and efficient load distribution. Features include CI/CD testing, dynamic prompt development, multi-model support, real-time insights, and prompt testing and evolution.
langrila
Langrila is a library that provides an easy way to use API-based LLM (Large Language Models) with an emphasis on simple architecture for readability. It supports various AI models for chat and embedding tasks, as well as retrieval functionalities using Qdrant, Chroma, and Usearch. Langrila also includes modules for function calling, conversation memory management, and prompt templates. It enforces coding policies for simplicity, responsibility independence, and minimum module implementation. The library requires Python version 3.10 to 3.13 and additional dependencies like OpenAI, Gemini, Qdrant, Chroma, and Usearch for specific functionalities.
embodied-agents
Embodied Agents is a toolkit for integrating large multi-modal models into existing robot stacks with just a few lines of code. It provides consistency, reliability, scalability, and is configurable to any observation and action space. The toolkit is designed to reduce complexities involved in setting up inference endpoints, converting between different model formats, and collecting/storing datasets. It aims to facilitate data collection and sharing among roboticists by providing Python-first abstractions that are modular, extensible, and applicable to a wide range of tasks. The toolkit supports asynchronous and remote thread-safe agent execution for maximal responsiveness and scalability, and is compatible with various APIs like HuggingFace Spaces, Datasets, Gymnasium Spaces, Ollama, and OpenAI. It also offers automatic dataset recording and optional uploads to the HuggingFace hub.
gollm
gollm is a Go package designed to simplify interactions with Large Language Models (LLMs) for AI engineers and developers. It offers a unified API for multiple LLM providers, easy provider and model switching, flexible configuration options, advanced prompt engineering, prompt optimization, memory retention, structured output and validation, provider comparison tools, high-level AI functions, robust error handling and retries, and extensible architecture. The package enables users to create AI-powered golems for tasks like content creation workflows, complex reasoning tasks, structured data generation, model performance analysis, prompt optimization, and creating a mixture of agents.
redisvl
Redis Vector Library (RedisVL) is a Python client library for building AI applications on top of Redis. It provides a high-level interface for managing vector indexes, performing vector search, and integrating with popular embedding models and providers. RedisVL is designed to make it easy for developers to build and deploy AI applications that leverage the speed, flexibility, and reliability of Redis.
mlx-llm
mlx-llm is a library that allows you to run Large Language Models (LLMs) on Apple Silicon devices in real-time using Apple's MLX framework. It provides a simple and easy-to-use API for creating, loading, and using LLM models, as well as a variety of applications such as chatbots, fine-tuning, and retrieval-augmented generation.
IntelliNode
IntelliNode is a javascript module that integrates cutting-edge AI models like ChatGPT, LLaMA, WaveNet, Gemini, and Stable diffusion into projects. It offers functions for generating text, speech, and images, as well as semantic search, multi-model evaluation, and chatbot capabilities. The module provides a wrapper layer for low-level model access, a controller layer for unified input handling, and a function layer for abstract functionality tailored to various use cases.
LLMDebugger
This repository contains the code and dataset for LDB, a novel debugging framework that enables Large Language Models (LLMs) to refine their generated programs by tracking the values of intermediate variables throughout the runtime execution. LDB segments programs into basic blocks, allowing LLMs to concentrate on simpler code units, verify correctness block by block, and pinpoint errors efficiently. The tool provides APIs for debugging and generating code with debugging messages, mimicking how human developers debug programs.
HippoRAG
HippoRAG is a novel retrieval augmented generation (RAG) framework inspired by the neurobiology of human long-term memory that enables Large Language Models (LLMs) to continuously integrate knowledge across external documents. It provides RAG systems with capabilities that usually require a costly and high-latency iterative LLM pipeline for only a fraction of the computational cost. The tool facilitates setting up retrieval corpus, indexing, and retrieval processes for LLMs, offering flexibility in choosing different online LLM APIs or offline LLM deployments through LangChain integration. Users can run retrieval on pre-defined queries or integrate directly with the HippoRAG API. The tool also supports reproducibility of experiments and provides data, baselines, and hyperparameter tuning scripts for research purposes.
SimplerLLM
SimplerLLM is an open-source Python library that simplifies interactions with Large Language Models (LLMs) for researchers and beginners. It provides a unified interface for different LLM providers, tools for enhancing language model capabilities, and easy development of AI-powered tools and apps. The library offers features like unified LLM interface, generic text loader, RapidAPI connector, SERP integration, prompt template builder, and more. Users can easily set up environment variables, create LLM instances, use tools like SERP, generic text loader, calling RapidAPI APIs, and prompt template builder. Additionally, the library includes chunking functions to split texts into manageable chunks based on different criteria. Future updates will bring more tools, interactions with local LLMs, prompt optimization, response evaluation, GPT Trainer, document chunker, advanced document loader, integration with more providers, Simple RAG with SimplerVectors, integration with vector databases, agent builder, and LLM server.
raptor
RAPTOR introduces a novel approach to retrieval-augmented language models by constructing a recursive tree structure from documents. This allows for more efficient and context-aware information retrieval across large texts, addressing common limitations in traditional language models. Users can add documents to the tree, answer questions based on indexed documents, save and load the tree, and extend RAPTOR with custom summarization, question-answering, and embedding models. The tool is designed to be flexible and customizable for various NLP tasks.
videokit
VideoKit is a full-featured user-generated content solution for Unity Engine, enabling video recording, camera streaming, microphone streaming, social sharing, and conversational interfaces. It is cross-platform, with C# source code available for inspection. Users can share media, save to camera roll, pick from camera roll, stream camera preview, record videos, remove background, caption audio, and convert text commands. VideoKit requires Unity 2022.3+ and supports Android, iOS, macOS, Windows, and WebGL platforms.
ecologits
EcoLogits tracks energy consumption and environmental impacts of generative AI models through APIs. It provides estimated environmental impacts of the inference, such as energy consumption and GHG emissions. The tool supports integration with various providers like Anthropic, Cohere, Google GenerativeAI, Huggingface Hub, MistralAI, and OpenAI. Users can easily install EcoLogits using pip and access detailed documentation on ecologits.ai. The project welcomes contributions and is licensed under MPL-2.0.
unify
The Unify Python Package provides access to the Unify REST API, allowing users to query Large Language Models (LLMs) from any Python 3.7.1+ application. It includes Synchronous and Asynchronous clients with Streaming responses support. Users can easily use any endpoint with a single key, route to the best endpoint for optimal throughput, cost, or latency, and customize prompts to interact with the models. The package also supports dynamic routing to automatically direct requests to the top-performing provider. Additionally, users can enable streaming responses and interact with the models asynchronously for handling multiple user requests simultaneously.
SUPIR
SUPIR is an AI-based image processing and upscaling tool that leverages cutting-edge technology to enhance image quality and resolution. The tool provides users with the ability to upscale images with high generalization and quality, as well as specific settings for light degradation scenarios. It offers a range of models and checkpoints for different use cases, along with detailed instructions for installation and usage. SUPIR also includes features for color fixing, linear CFG adjustments, and various prompts for image enhancement. The tool is designed for non-commercial use only and comes with a contact email for inquiries and permission requests for commercial use.
parea-sdk-py
Parea AI provides a SDK to evaluate & monitor AI applications. It allows users to test, evaluate, and monitor their AI models by defining and running experiments. The SDK also enables logging and observability for AI applications, as well as deploying prompts to facilitate collaboration between engineers and subject-matter experts. Users can automatically log calls to OpenAI and Anthropic, create hierarchical traces of their applications, and deploy prompts for integration into their applications.
For similar tasks
flow-prompt
Flow Prompt is a dynamic library for managing and optimizing prompts for large language models. It facilitates budget-aware operations, dynamic data integration, and efficient load distribution. Features include CI/CD testing, dynamic prompt development, multi-model support, real-time insights, and prompt testing and evolution.
twinny
Twinny is a free and open-source AI code completion plugin for Visual Studio Code and compatible editors. It integrates with various tools and frameworks, including Ollama, llama.cpp, oobabooga/text-generation-webui, LM Studio, LiteLLM, and Open WebUI. Twinny offers features such as fill-in-the-middle code completion, chat with AI about your code, customizable API endpoints, and support for single or multiline fill-in-middle completions. It is easy to install via the Visual Studio Code extensions marketplace and provides a range of customization options. Twinny supports both online and offline operation and conforms to the OpenAI API standard.
commanddash
Dash AI is an open-source coding assistant for Flutter developers. It is designed to not only write code but also run and debug it, allowing it to assist beyond code completion and automate routine tasks. Dash AI is powered by Gemini, integrated with the Dart Analyzer, and specifically tailored for Flutter engineers. The vision for Dash AI is to create a single-command assistant that can automate tedious development tasks, enabling developers to focus on creativity and innovation. It aims to assist with the entire process of engineering a feature for an app, from breaking down the task into steps to generating exploratory tests and iterating on the code until the feature is complete. To achieve this vision, Dash AI is working on providing LLMs with the same access and information that human developers have, including full contextual knowledge, the latest syntax and dependencies data, and the ability to write, run, and debug code. Dash AI welcomes contributions from the community, including feature requests, issue fixes, and participation in discussions. The project is committed to building a coding assistant that empowers all Flutter developers.
kaizen
Kaizen is an open-source project that helps teams ensure quality in their software delivery by providing a suite of tools for code review, test generation, and end-to-end testing. It integrates with your existing code repositories and workflows, allowing you to streamline your software development process. Kaizen generates comprehensive end-to-end tests, provides UI testing and review, and automates code review with insightful feedback. The file structure includes components for API server, logic, actors, generators, LLM integrations, documentation, and sample code. Getting started involves installing the Kaizen package, generating tests for websites, and executing tests. The tool also runs an API server for GitHub App actions. Contributions are welcome under the AGPL License.
eval-dev-quality
DevQualityEval is an evaluation benchmark and framework designed to compare and improve the quality of code generation of Language Model Models (LLMs). It provides developers with a standardized benchmark to enhance real-world usage in software development and offers users metrics and comparisons to assess the usefulness of LLMs for their tasks. The tool evaluates LLMs' performance in solving software development tasks and measures the quality of their results through a point-based system. Users can run specific tasks, such as test generation, across different programming languages to evaluate LLMs' language understanding and code generation capabilities.
twinny
Twinny is a free and private AI extension for Visual Studio Code that offers AI-based code completion and code discussion features. It provides real-time code suggestions, function explanations, test generation, refactoring requests, and more. Twinny operates both online and offline, supports customizable API endpoints, conforms to OpenAI API standards, and offers various customization options for prompt templates, API providers, model names, and more. It is compatible with multiple APIs and allows users to accept code solutions directly in the editor, create new documents from code blocks, and copy generated code solution blocks. Twinny is open-source under the MIT license and welcomes contributions from the community.
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.
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.
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.
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.
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.
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
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.
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.