| Example | Description |
|---|---|
| Llama Cpp Basic | Run a local GGUF model with LlamaCpp and print sync and streamed responses. |
| Retry | Review retry settings and why invalid model IDs cannot reliably exercise the retry path. |
| Llama Cpp Structured Output | Generate a MovieScript Pydantic object from a local LlamaCpp model with output_schema. |
| Tool Use | Give a local LlamaCpp model web search tools and stream the tool-assisted answer. |
Llama.cpp
Llama Cpp
Run agents against a local llama.cpp server serving ggml-org/gpt-oss-20b-GGUF at http://127.0.0.1:8080/v1.