llama-stack-mirror/llama_stack
Ilya Kolchinsky 40f41af2f7
feat: Add a direct (non-agentic) RAG option to the Playground RAG page (#1940)
# What does this PR do?
This PR makes it possible to switch between agentic and non-agentic RAG
when running the respective Playground page.
When non-agentic RAG is selected, user queries are answered by directly
querying the vector DB, augmenting the prompt, and sending the extended
prompt to the model via Inference API.

## Test Plan
- Launch the Playground and go to the RAG page;
- Select the vector DB ID;
- Adjust other configuration parameters if necessary;
- Set the radio button to Agent-based RAG;
- Send a message to the chat;
- The query will be answered by an agent using the knowledge search tool
as indicated by the output;
- Click the 'Clear Chat' button to make it possible to switch modes;
- Send a message to the chat again;
- This time, the query will be answered by the model directly as can be
deduced from the reply.
2025-04-11 10:16:10 -07:00
..
apis refactor: move all llama code to models/llama out of meta reference (#1887) 2025-04-07 15:03:58 -07:00
cli refactor: move all llama code to models/llama out of meta reference (#1887) 2025-04-07 15:03:58 -07:00
distribution feat: Add a direct (non-agentic) RAG option to the Playground RAG page (#1940) 2025-04-11 10:16:10 -07:00
models fix: on-the-fly int4 quantize parameter (#1920) 2025-04-09 15:00:12 -07:00
providers fix: use torchao 0.8.0 for inference (#1925) 2025-04-10 13:39:20 -07:00
strong_typing chore: more mypy checks (ollama, vllm, ...) (#1777) 2025-04-01 17:12:39 +02:00
templates fix: use torchao 0.8.0 for inference (#1925) 2025-04-10 13:39:20 -07:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore: Remove style tags from log formatter (#1808) 2025-03-27 10:18:21 -04:00
schema_utils.py chore: make mypy happy with webmethod (#1758) 2025-03-22 08:17:23 -07:00