llama-stack-mirror/llama_stack/providers/inline
Xi Yan 6520baebed
fix: replace eval with json decoding (#1327)
# What does this PR do?

- Using `eval` on server is a security risk
- Replace `eval` with `json.loads`

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
pytest -v -s --nbval-lax ./llama-stack/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb 
```
<img width="747" alt="image"
src="https://github.com/user-attachments/assets/7aff3d95-0b12-4394-b9d0-aeff791eee38"
/>


[//]: # (## Documentation)
2025-02-28 11:10:45 -08:00
..
agents chore(lint): update Ruff ignores for project conventions and maintainability (#1184) 2025-02-28 09:36:49 -08:00
datasetio build: format codebase imports using ruff linter (#1028) 2025-02-13 10:06:21 -08:00
eval fix: replace eval with json decoding (#1327) 2025-02-28 11:10:45 -08:00
inference chore(lint): update Ruff ignores for project conventions and maintainability (#1184) 2025-02-28 09:36:49 -08:00
ios/inference chore: removed executorch submodule (#1265) 2025-02-25 21:57:21 -08:00
post_training chore(lint): update Ruff ignores for project conventions and maintainability (#1184) 2025-02-28 09:36:49 -08:00
safety chore: move all Llama Stack types from llama-models to llama-stack (#1098) 2025-02-14 09:10:59 -08:00
scoring chore(lint): update Ruff ignores for project conventions and maintainability (#1184) 2025-02-28 09:36:49 -08:00
telemetry fix: sqlite conn (#1282) 2025-02-26 14:44:31 -08:00
tool_runtime feat: remove special handling of builtin::rag tool (#1015) 2025-02-26 13:04:52 -08:00
vector_io Fix sqlite_vec config defaults 2025-02-20 17:50:33 -08:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00