phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-25 01:01:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877)

Browse source 
Reverts llamastack/llama-stack#3871

This PR broke RAG (even from Responses -- there _is_ a dependency)
This commit is contained in:
Ashwin Bharambe 2025-10-21 11:22:06 -07:00 • committed by GitHub
parent eb3e9b85f9
commit bd3c473208
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
55 changed files with 3114 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/providers/registry/tool_runtime.py
View file

@ -7,13 +7,33 @@
from llama_stack.providers.datatypes import (
Api,
InlineProviderSpec,
ProviderSpec,
RemoteProviderSpec,
)
from llama_stack.providers.registry.vector_io import DEFAULT_VECTOR_IO_DEPS
def available_providers() -> list[ProviderSpec]:
return [
InlineProviderSpec(
api=Api.tool_runtime,
provider_type="inline::rag-runtime",
pip_packages=DEFAULT_VECTOR_IO_DEPS
+ [
"tqdm",
"numpy",
"scikit-learn",
"scipy",
"nltk",
"sentencepiece",
"transformers",
],
module="llama_stack.providers.inline.tool_runtime.rag",
config_class="llama_stack.providers.inline.tool_runtime.rag.config.RagToolRuntimeConfig",
api_dependencies=[Api.vector_io, Api.inference, Api.files],
description="RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.",
),
RemoteProviderSpec(
api=Api.tool_runtime,
adapter_type="brave-search",