Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| kobold_max_context_length | Get current max context length setting |
| kobold_max_length | Get current max length setting |
| kobold_generate | Generate text with KoboldAI |
| kobold_model_info | Get current model information |
| kobold_version | Get KoboldAI version information |
| kobold_perf_info | Get performance information |
| kobold_token_count | Count tokens in text |
| kobold_detokenize | Convert token IDs to text |
| kobold_transcribe | Transcribe audio using Whisper |
| kobold_web_search | Search the web via DuckDuckGo |
| kobold_tts | Generate text-to-speech audio |
| kobold_abort | Abort the currently ongoing generation |
| kobold_last_logprobs | Get token logprobs from the last request |
| kobold_sd_models | List available Stable Diffusion models |
| kobold_sd_samplers | List available Stable Diffusion samplers |
| kobold_txt2img | Generate image from text prompt |
| kobold_img2img | Transform existing image using prompt |
| kobold_interrogate | Generate caption for image |
| kobold_chat | Chat completion (OpenAI-compatible) |
| kobold_complete | Text completion (OpenAI-compatible) |