Prompt Perfection at Your Fingertips
Project description
LLMstudio by TensorOps
Prompt Engineering at your fingertips
[!IMPORTANT] LLMstudio is now supporting OpenAI v1.0 + just added support to Anthropic
🌟 Features
- Python Client Gateway:
- Access models from known providers such as OpenAI, VertexAI and Bedrock. All in one platform.
- Speed up development with tracking and robustness features from LLMstudio.
- Continue using popular libraries like LangChain through their LLMstudio-wrapped versions.
- Prompt Editing UI:
- An intuitive interface designed for prompt engineering.
- Quickly iterate between prompts until you reach your desired results.
- Access the history of your previous prompts and their results.
- History Management:
- Track past runs, available for both on the UI and the Client.
- Log the cost, latency and output of each prompt.
- Export the history to a CSV.
- Context Limit Adaptability:
- Automatic switch to a larger-context fallback model if the current model's context limit is exceeded.
- Always use the lowest context model and only use the higher context ones when necessary to save costs.
- For instance, exceeding 4k tokens in gpt-3.5-turbo triggers a switch to gpt-3.5-turbo-16k.
👀 Coming soon:
- Side-by-side comparison of multiple LLMs using the same prompt.
- Automated testing and validation for your LLMs. (Create Unit-tests for your LLMs which are evaluated automatically)
- API key administration. (Define quota limits)
- Projects and sessions. (Organize your History and API keys by project)
- Resilience against service provider rate limits.
- Organized tracking of groups of related prompts (Chains, Agents)
🚀 Quickstart
Don't forget to check out https://docs.llmstudio.ai page.
Installation
Install the latest version of LLMstudio using pip
. We suggest that you create and activate a new environment using conda
pip install llmstudio
Install bun
if you want to use the UI
curl -fsSL https://bun.sh/install | bash
Create a .env
file at the same path you'll run LLMstudio
OPENAI_API_KEY="sk-api_key"
ANTHROPIC_API_KEY="sk-api_key"
Now you should be able to run LLMstudio using the following command.
llmstudio server --ui
When the --ui
flag is set, you'll be able to access the UI at http://localhost:3000
🤔 About LLMstudio
Powered by TensorOps, LLMstudio redefines your experience with OpenAI, Vertex Ai and more language model providers. More than just a tool, it’s an evolving environment where teams can experiment, modify, and optimize their interactions with advanced language models.
Benefits include:
- Streamlined Prompt Engineering: Simplify and enhance your prompt design process.
- Execution History: Keep a detailed log of past executions, track progress, and make iterative improvements effortlessly.
- Effortless Data Export: Share your team's endeavors by exporting data to shareable CSV files.
Step into the future of AI with LLMstudio, by watching our introduction video
📖 Documentation
- Visit our docs to learn how the SDK works (coming soon)
- Checkout our notebook examples to follow along with interactive tutorials
- Checkout out LLMstudio Architecture Roadmap
👨💻 Contributing
- Head on to our Contribution Guide to see how you can help LLMstudio.
- Join our Discord to talk with other LLMstudio enthusiasts.
Training
Thank you for choosing LLMstudio. Your journey to perfecting AI interactions starts here.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for llmstudio-0.3.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 83a0fe68822960456b7b9f007af2ddb6cf8f368011b0e7e86e3ae802b0a84446 |
|
MD5 | ce91a5bab2e99366bfc6328429b4374a |
|
BLAKE2b-256 | 96a32b972b6aca21b6272f4017d1e3ff9994fdfd763a627ba3c25523fee42d65 |