DeepSparse Server
DeepSparse is an inference runtime taking advantage of sparsity with neural networks offering GPU-class performance on CPUs.
LlamaIndex gives you the tools you need to build production-ready LLM applications from your organization's data.
LlamaIndex is a data framework that makes it simple to build production-ready applications from your data using LLMs. Providing an entire suite of packages and classes for loading, indexing, querying, and evaluating data, LlamaIndex specializes in context augmentation so that you can safely and reliably optimize your queries with custom data.
This demo application deploys a basic application that allows visitors to ask questions about the story "Gift of the Magi" by O. Henry. The web interface is built using Streamlit, a Python framework for building and sharing data apps.
To deploy this application, you'll need to sign up for an OpenAI account and create an API key.
When you deploy the application, fill in the OPENAI_API_KEY
environment variable with your API key value. This application requires a Koyeb Instance of "micro" or larger.
Once the LlamaIndex application is deployed, you can view the prompt page by visiting the Koyeb App URL in your browser:
https://<YOUR_APP_NAME>-<YOUR_KOYEB_ORG>.koyeb.app
DeepSparse is an inference runtime taking advantage of sparsity with neural networks offering GPU-class performance on CPUs.
Deploy Fooocus, a powerful AI image generation tool, on Koyeb
LangServe makes it easy to deploy LangChain applications as RESTful APIs.