ehhuang bb2690f176 feat: remove special handling of builtin::rag tool (#1015) ... Summary: Lets the model decide which tool it needs to call to respond to a query. Test Plan: ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/ --safety-shield meta-llama/Llama-Guard-3-8B ``` Also evaluated on a small benchmark with 20 questions from HotpotQA. With this PR and some prompting, the performance is 77% recall compared to 50% currently. --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1015). * #1268 * #1239 * __->__ #1015		2025-02-26 13:04:52 -08:00
..
__init__.py	fix: Get distro_codegen.py working with default deps and enabled in pre-commit hooks (#1123)	2025-02-19 18:39:20 -08:00
config.py	Move tool_runtime.memory -> tool_runtime.rag	2025-01-22 20:25:02 -08:00
context_retriever.py	build: format codebase imports using ruff linter (#1028)	2025-02-13 10:06:21 -08:00
memory.py	feat: remove special handling of builtin::rag tool (#1015)	2025-02-26 13:04:52 -08:00