PromptTools
:wrench: Test and experiment with prompts, LLMs, and vector databases. :hammer:
Welcome to prompttools created by Hegel AI! This repo offers a set of open-source, self-hostable tools for experimenting with, testing, and evaluating LLMs, vector databases, and prompts. The core idea is to enable developers to evaluate using familiar interfaces like code, notebooks, and a local playground.
In just a few lines of code, you can test your prompts and parameters across different models (whether you are using OpenAI, Anthropic, or LLaMA models). You can even evaluate the retrieval accuracy of vector databases.
from prompttools.experiment import OpenAIChatExperiment
messages = [
[{"role": "user", "content": "Tell me a joke."},],
[{"role": "user", "content": "Is 17077 a prime number?"},],
]
models = ["gpt-3.5-turbo", "gpt-4"]
temperatures = [0.0]
openai_experiment = OpenAIChatExperiment(models, messages, temperature=temperatures)
openai_experiment.run()
openai_experiment.visualize()
To stay in touch with us about issues and future updates, join the Discord.
Quickstart
To install prompttools, you can use pip:
pip install prompttools
You can run a simple example of a prompttools locally with the following
git clone https://github.com/hegelai/prompttools.git
cd prompttools && jupyter notebook examples/notebooks/OpenAIChatExperiment.ipynb
You can also run the notebook in Google Colab
Playground
If you want to interact with prompttools using our playground interface, you can launch it with the following commands.
First, install prompttools:
pip install prompttools
Then, clone the git repo and launch the streamlit app:
git clone https://github.com/hegelai/prompttools.git
cd prompttools && streamlit run prompttools/playground/playground.py
You can also access a hosted version of the playground on the Streamlit Community Cloud.
Note: The hosted version does not support LlamaCpp
Documentation
Our documentation website contains the full API reference and more description of individual components. Check it out!
Supported Integrations
Here is a list of APIs that we support with our experiments:
LLMs
- OpenAI (Completion, ChatCompletion, Fine-tuned models) - Supported
- LLaMA.Cpp (LLaMA 1, LLaMA 2) - Supported
- HuggingFace (Hub API, Inference Endpoints) - Supported
- Anthropic - Supported
- Mistral AI - Supported
- Google Gemini - Supported
- Google PaLM (legacy) - Supported
- Google Vertex AI - Supported
- Azure OpenAI Service - Supported
- Replicate - Supported
- Ollama - In Progress
Vector Databases and Data Utility
- Chroma - Supported
- Weaviate - Supported
- Qdrant - Supported
- LanceDB - Supported
- Milvus - Exploratory
- Pinecone - Supported
- Epsilla - In Progress
Frameworks
- LangChain - Supported
- MindsDB - Supported
- LlamaIndex - Exploratory
Computer Vision
- Stable Diffusion - Supported
- Replicate's hosted Stable Diffusion - Supported
If you have any API that you'd like to see being supported soon, please open an issue or a PR to add it. Feel free to discuss in our Discord channel as well.
Frequently Asked Questions (FAQs)
-
Will this library forward my LLM calls to a server before sending it to OpenAI, Anthropic, and etc.?
- No, the source code will be executed on your machine. Any call to LLM APIs will be directly executed from your machine without any forwarding.
-
Does
prompttoolsstore my API keys or LLM inputs and outputs to a server?- No, all of those data stay on your local machine. We do not collect any PII (personally identifiable information).
-
How do I persist my results?
- To persist the results of your tests and experiments, you can export your
Experimentwith the methodsto_csv,to_json,to_lora_json, orto_mongo_db. We are building more persistence features and we will be happy to further discuss your use cases, pain points, and what export options may be useful for you.
- To persist the results of your tests and experiments, you can export your
Sentry
Usage Tracking
Since we are changing our API rapidly, there are some errors caused by our negligence or out of date documentation. To improve user experience, we collect data from normal package usage that helps us understand the errors that are raised. This data is collected and sent to Sentry, a third-party error tracking service, commonly used in open-source softwares. It only logs this library's own actions.
You can easily opt-out by defining an environment variable called SENTRY_OPT_OUT.
Contributing
We welcome PRs and suggestions! Don't hesitate to open a PR/issue or to reach out to us via email. Please have a look at our contribution guide and "Help Wanted" issues to get started!
Usage and Feedback
We will be delighted to work with early adopters to shape our designs. Please reach out to us via email if you're interested in using this tooling for your project or have any feedback.
License
We will be gradually releasing more components to the open-source community. The current license can be found in the LICENSE file. If there is any concern, please contact us and we will be happy to work with you.
1 maintainer
Metadata
1 maintainer
Release files for prompttools 0.0.46
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| prompttools-0.0.46.tar.gz | 80.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| prompttools-0.0.46-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 201.0 kB
Release files / prompttools-0.0.46.tar.gz
| Download URL | prompttools-0.0.46.tar.gz |
|---|---|
| Size | 80.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
78673db78c46b3ebaf60a92cec605b4370611d441a64c93d8fda98abd22f5d08
|
|
BLAKE2b-256 checksum How to use checksums |
42323f38d4ace2a5f9c87d6af5e296a791cc5c7240ced5f6e5bc61c589ea1311
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.4
|
Release files / prompttools-0.0.46-py3-none-any.whl
| Download URL | prompttools-0.0.46-py3-none-any.whl |
|---|---|
| Size | 120.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5d1a4538fe6d52b9408edf2a9266379e1176125b65256c6dd5be4d5b1544483f
|
|
BLAKE2b-256 checksum How to use checksums |
3608539485cd42bb79d72c7ca90940916b75eec8619c597b117b14c2d3a86600
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.4
|
