Explore and interact with HuggingFace LLM APIs using Swagger UI
Display and explore model leaderboards and chat history
Identify named entities in text
Humanize AI-generated text to sound like it was written by a human
Parse and highlight entities in an email thread
Analyze content to detect triggers
Predict NCM codes from product descriptions
A benchmark for open-source multi-dialect Arabic ASR models
Track, rank and evaluate open Arabic LLMs and chatbots
Analyze Ancient Greek text for syntax and named entities
Retrieve news articles based on a query
Compare LLMs by role stability
Detect if text was generated by GPT-2
The HF LLM API is an interface designed to interact with HuggingFace's diverse range of Large Language Models (LLMs). This API allows developers to explore and integrate the powerful capabilities of HuggingFace models directly into their applications. With its user-friendly Swagger UI interface, users can easily test endpoints, review documentation, and understand how to interact with the models effectively. The HF LLM API serves as a bridge between developers and state-of-the-art NLP models, enabling seamless integration for text analysis, generation, and processing tasks.
What programming languages does HF LLM API support?
The HF LLM API is language-agnostic and can be accessed using any language capable of making HTTP requests. However, official client libraries are available for Python and other popular languages.
How do I authenticate with the HF LLM API?
Authentication depends on the specific model or endpoint you are using. Some endpoints may require an API token, which can be obtained from the HuggingFace authentication portal.
Are there usage limits for the HF LLM API?
Usage limits vary depending on the model and your access level. Free-tier models typically have rate limits, while paid tiers offer higher quotas. Check the model's documentation for specific details.
Can I use custom models with the HF LLM API?
Yes, the HF LLM API supports integration with custom models hosted on the HuggingFace Model Hub. You can deploy your own model and generate API endpoints to interact with it.
How do I report issues or provide feedback?
You can report issues or provide feedback through the HuggingFace community forums or by opening an issue on the appropriate GitHub repository.