Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENABLED_TOOLS | No | Comma-separated list of tools to enable. Use "all" to enable all tools | all |
| MODEL_FILL_MASK | No | Default model for fill mask | microsoft/DialoGPT-medium |
| MODEL_EMBEDDINGS | No | Default model for embeddings | sentence-transformers/all-MiniLM-L6-v2 |
| DEEPINFRA_API_KEY | Yes | Your DeepInfra API key | |
| MODEL_GENERATE_IMAGE | No | Default model for image generation | Bria/Bria-3.2 |
| MODEL_TEXT_GENERATION | No | Default model for text generation | meta-llama/Llama-2-7b-chat-hf |
| MODEL_OBJECT_DETECTION | No | Default model for object detection | openai/gpt-4o-mini |
| MODEL_SPEECH_RECOGNITION | No | Default model for speech recognition | openai/whisper-large-v3 |
| MODEL_TEXT_CLASSIFICATION | No | Default model for text classification | microsoft/DialoGPT-medium |
| MODEL_IMAGE_CLASSIFICATION | No | Default model for image classification | openai/gpt-4o-mini |
| MODEL_TOKEN_CLASSIFICATION | No | Default model for token classification | microsoft/DialoGPT-medium |
| MODEL_ZERO_SHOT_IMAGE_CLASSIFICATION | No | Default model for zero-shot image classification | openai/gpt-4o-mini |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_image | Generate an image from a text prompt using DeepInfra OpenAI-compatible API. |
| text_generation | Generate text completion using DeepInfra OpenAI-compatible API. |
| embeddings | Generate embeddings for a list of texts using DeepInfra OpenAI-compatible API. |
| speech_recognition | Transcribe audio to text using DeepInfra OpenAI-compatible API (Whisper). |
| zero_shot_image_classification | Classify an image with zero-shot labels using DeepInfra OpenAI-compatible API (CLIP). |
| object_detection | Detect objects in an image using DeepInfra OpenAI-compatible API with multimodal model. |
| image_classification | Classify an image using DeepInfra OpenAI-compatible API with multimodal model. |
| text_classification | Classify text sentiment/category using DeepInfra OpenAI-compatible API. |
| token_classification | Perform named entity recognition (NER) on text using DeepInfra OpenAI-compatible API. |
| fill_mask | Fill masked tokens in text using DeepInfra OpenAI-compatible API. |