The Aleph Alpha Intelligence Layer ☯️ offers a comprehensive suite of development tools for crafting solutions that harness the capabilities of large language models (LLMs). With a unified framework for LLM-based workflows, it facilitates seamless AI product development, from prototyping and prompt experimentation to result evaluation and deployment.
The key features of the Intelligence Layer are:
- Best practices We provide you with state-of-the-art methods tailored for prevalent LLM use cases. Utilize our off-the-shelf techniques to swiftly prototype based on your primary data. Our approach integrates the best industry practices, allowing for optimal performance.
- Composability: The Intelligence Layer streamlines your journey from prototyping to scalable deployment. It offers seamless integration with diverse evaluation methods, manages concurrency, and orchestrates smaller tasks into complex workflows.
- Auditability At the core of the Intelligence Layer is the belief that all AI processes must be auditable and traceable. To ensure this, we provide full coprehensibility, by seamlessly logging each step of every workflow. This enhances your debugging capabilities and offers greater control post-deployment when examining model responses.
Not sure where to start? Familiarize yourself with the Intelligence Layer using the below notebooks.
Order | Task | Description | Notebook 📓 |
---|---|---|---|
1 | Summarization | Summarize a document | summarize.ipynb |
2 | Question Answering | Various approaches for QA | qa.ipynb |
3 | Quickstart task | Build a custom task for your use case | quickstart_task.ipynb |
4 | Single label Classification | Conduct zero-shot text classification | single_label_classify.ipynb |
5 | Embedding based Classification | Classify texts on the basis of examples | embedding_based_classify.ipynb |
6 | Document Index | Connect your proprietary knowledge base | document_index.ipynb |
You will need an Aleph Alpha access token to run the examples. First, set your access token:
export AA_TOKEN=<YOUR TOKEN HERE>
Then, install all the dependencies:
poetry install
Run jupytyer lab
, and go to the examples directory.
cd src/examples && poetry run jupyter lab
To install this as a dependency in your project, you will need to get a Github access token.
Set your access token:
GITHUB_TOKEN=<YOUR_GITHUB_TOKEN>
We recommend setting up a dedicated virtual environment. You can do so by using conda or venv.
Let's install the package:
pip install git+https://$GITHUB_TOKEN@github.com/aleph-alpha-intelligence-layer/intelligence-layer.git
Now, the intelligence layer should be available and ready to use as a Python package.
from intelligence_layer.core.task import Task