phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 05:08:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: update pyproject.toml dependencies for vector processing (#3555)

Browse source 
What does this PR do?

Updates pyproject.toml dependencies to fix vector processing
compatibility issues.

closes: #3495 

  Test Plan

  Tested llama stack server with faiss vector database:

1. Built and ran server: llama stack build --distro starter --image-type
venv --image-name llamastack-faiss
3. Tested file upload: Successfully uploaded PDF via /v1/openai/v1/files
  4. Tested vector operations:
    - Created vector store with faiss backend
    - Added PDF to vector store
    - Performed semantic search queries
This commit is contained in:
Sumanth Kamenani 2025-10-07 09:01:36 -04:00 • committed by GitHub
parent 509ac4a659
commit 1fcde5fc2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 18 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/registry/tool_runtime.py
View file

@ -11,6 +11,7 @@ from llama_stack.providers.datatypes import (
ProviderSpec,
RemoteProviderSpec,
)
from llama_stack.providers.registry.vector_io import DEFAULT_VECTOR_IO_DEPS
def available_providers() -> list[ProviderSpec]:
@ -18,9 +19,8 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec(
api=Api.tool_runtime,
provider_type="inline::rag-runtime",
pip_packages=[
"chardet",
"pypdf",
pip_packages=DEFAULT_VECTOR_IO_DEPS
+ [
"tqdm",
"numpy",
"scikit-learn",