phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-22 16:23:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(cleanup)!: remove tool_runtime.rag_tool (#3871)

Browse source 
Kill the `builtin::rag` tool group completely since it is no longer
targeted. We use the Responses implementation for knowledge_search which
uses the `openai_vector_stores` pathway.

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
Ashwin Bharambe 2025-10-20 22:26:21 -07:00 • committed by GitHub
parent 5aaf1a8bca
commit 0e96279bee
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
55 changed files with 17 additions and 3114 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/providers/utils/memory/vector_store.py
View file

@ -12,17 +12,14 @@ from dataclasses import dataclass
from typing import Any
from urllib.parse import unquote
import httpx
import numpy as np
from numpy.typing import NDArray
from pydantic import BaseModel
from llama_stack.apis.common.content_types import (
URL,
InterleavedContent,
)
from llama_stack.apis.inference import OpenAIEmbeddingsRequestWithExtraBody
from llama_stack.apis.tools import RAGDocument
from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
from llama_stack.apis.vector_stores import VectorStore
from llama_stack.log import get_logger
@ -129,31 +126,6 @@ def content_from_data_and_mime_type(data: bytes | str, mime_type: str | None, en
return ""
async def content_from_doc(doc: RAGDocument) -> str:
if isinstance(doc.content, URL):
if doc.content.uri.startswith("data:"):
return content_from_data(doc.content.uri)
async with httpx.AsyncClient() as client:
r = await client.get(doc.content.uri)
if doc.mime_type == "application/pdf":
return parse_pdf(r.content)
return r.text
elif isinstance(doc.content, str):
pattern = re.compile("^(https?://|file://|data:)")
if pattern.match(doc.content):
if doc.content.startswith("data:"):
return content_from_data(doc.content)
async with httpx.AsyncClient() as client:
r = await client.get(doc.content)
if doc.mime_type == "application/pdf":
return parse_pdf(r.content)
return r.text
return doc.content
else:
# will raise ValueError if the content is not List[InterleavedContent] or InterleavedContent
return interleaved_content_as_str(doc.content)
def make_overlapped_chunks(
document_id: str, text: str, window_len: int, overlap_len: int, metadata: dict[str, Any]
) -> list[Chunk]: