mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-27 19:12:00 +00:00
chore: Updating Milvus to use OpenAIVectorStoreMixin
docs: Add recent releases to CHANGELOG.md (#2533) <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Update changelog. --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> build: update temp. created Containerfile (#2492) <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> - conditionally created folder /.llama/providers.d if external_providers_dir is set - do not create /.cache folder, not in use anywhere - combine chmod and copy to one command <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> updated test: ``` export CONTAINER_BINARY=podman LLAMA_STACK_DIR=. uv run llama stack build --template remote-vllm --image-type container --image-name <name> ``` log: ``` Containerfile created successfully in /tmp/tmp.rPMunE39Aw/Containerfile FROM python:3.11-slim WORKDIR /app RUN apt-get update && apt-get install -y iputils-ping net-tools iproute2 dnsutils telnet curl wget telnet git procps psmisc lsof traceroute bubblewrap gcc && rm -rf /var/lib/apt/lists/* ENV UV_SYSTEM_PYTHON=1 RUN pip install uv RUN uv pip install --no-cache sentencepiece pillow pypdf transformers pythainlp faiss-cpu opentelemetry-sdk requests datasets chardet scipy nltk numpy matplotlib psycopg2-binary aiosqlite langdetect autoevals tree_sitter tqdm pandas chromadb-client opentelemetry-exporter-otlp-proto-http redis scikit-learn openai pymongo emoji sqlalchemy[asyncio] mcp aiosqlite fastapi fire httpx uvicorn opentelemetry-sdk opentelemetry-exporter-otlp-proto-http RUN uv pip install --no-cache sentence-transformers --no-deps RUN uv pip install --no-cache torch torchvision --index-url https://download.pytorch.org/whl/cpu RUN mkdir -p /.llama/providers.d /.cache RUN uv pip install --no-cache llama-stack RUN pip uninstall -y uv ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "remote-vllm"] RUN chmod -R g+rw /app /.llama /.cache PWD: /tmp/llama-stack Containerfile: /tmp/tmp.rPMunE39Aw/Containerfile + podman build --progress=plain --security-opt label=disable --platform linux/amd64 -t distribution-remote-vllm:0.2.12 -f /tmp/tmp.rPMunE39Aw/Containerfile /tmp/llama-stack .... Success! Build Successful! You can find the newly-built template here: /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml You can run the new Llama Stack distro via: llama stack run /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml --image-type container ``` ``` podman tag localhost/distribution-remote-vllm:dev quay.io/wenzhou/distribution-remote-vllm:2492_2 podman push quay.io/wenzhou/distribution-remote-vllm:2492_2 docker run --rm -p 8321:8321 -e INFERENCE_MODEL="meta-llama/Llama-2-7b-chat-hf" -e VLLM_URL="http://localhost:8000/v1" quay.io/wenzhou/distribution-remote-vllm:2492_2 --port 8321 INFO 2025-06-26 13:47:31,813 __main__:436 server: Using template remote-vllm config file: /app/llama-stack-source/llama_stack/templates/remote-vllm/run.yaml INFO 2025-06-26 13:47:31,818 __main__:438 server: Run configuration: INFO 2025-06-26 13:47:31,826 __main__:440 server: apis: - agents - datasetio - eval - inference - safety - scoring - telemetry - tool_runtime - vector_io benchmarks: [] container_image: null .... ``` ----- previous test: local run` >llama stack build --template remote-vllm --image-type container` image stored in `quay.io/wenzhou/distribution-remote-vllm:2492` --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> fix(security): Upgrade urllib3 to v2.5.0. Fixes CVE-2025-50181 and CVE-2025-50182 (#2534) This fixes CVE-2025-50181 and CVE-2025-50182. Changes via: ``` uv sync --upgrade-package urllib3 uv export --frozen --no-hashes --no-emit-project --no-default-groups --output-file=requirements.txt ``` Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> fix: dataset metadata without provider_id (#2527) Fixes an error when inferring dataset provider_id with metadata Closes #[2506](https://github.com/meta-llama/llama-stack/issues/2506) Signed-off-by: Juanma Barea <juanmabareamartinez@gmail.com> fix(security): Upgrade protobuf and aiohttp. Fixes CVE-2025-4565 (#2541) Fixes CVE-2025-4565 and the following warning: ``` warning: `aiohttp==3.11.13` is yanked (reason: "Regression: https://github.com/aio-libs/aiohttp/issues/10617") ``` Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> adding milvus prefix Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating CI Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> removing CI tests for now Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> think I got the config correct for CI Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated build and run files Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> adding marshmallow constraint Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> removing CI changes Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Update starter.py updated starter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo
parent
0883944bc3
commit
7273a125cd
14 changed files with 233 additions and 244 deletions
|
|
@ -5,34 +5,27 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import uuid
|
||||
from typing import Any
|
||||
|
||||
from numpy.typing import NDArray
|
||||
from pymilvus import MilvusClient
|
||||
|
||||
from llama_stack.apis.inference import InterleavedContent
|
||||
from llama_stack.apis.files.files import Files
|
||||
from llama_stack.apis.inference import Inference, InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import (
|
||||
Chunk,
|
||||
QueryChunksResponse,
|
||||
SearchRankingOptions,
|
||||
VectorIO,
|
||||
VectorStoreChunkingStrategy,
|
||||
VectorStoreDeleteResponse,
|
||||
VectorStoreFileContentsResponse,
|
||||
VectorStoreFileObject,
|
||||
VectorStoreFileStatus,
|
||||
VectorStoreListFilesResponse,
|
||||
VectorStoreListResponse,
|
||||
VectorStoreObject,
|
||||
VectorStoreSearchResponsePage,
|
||||
)
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.datatypes import VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.inline.vector_io.milvus import MilvusVectorIOConfig as InlineMilvusVectorIOConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.api import KVStore
|
||||
from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
|
||||
from llama_stack.providers.utils.memory.vector_store import (
|
||||
EmbeddingIndex,
|
||||
VectorDBWithIndex,
|
||||
|
|
@ -42,12 +35,22 @@ from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig
|
|||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
VERSION = "v3"
|
||||
VECTOR_DBS_PREFIX = f"vector_dbs:milvus:{VERSION}::"
|
||||
VECTOR_INDEX_PREFIX = f"vector_index:milvus:{VERSION}::"
|
||||
OPENAI_VECTOR_STORES_PREFIX = f"openai_vector_stores:milvus:{VERSION}::"
|
||||
OPENAI_VECTOR_STORES_FILES_PREFIX = f"openai_vector_stores_files:milvus:{VERSION}::"
|
||||
OPENAI_VECTOR_STORES_FILES_CONTENTS_PREFIX = f"openai_vector_stores_files_contents:milvus:{VERSION}::"
|
||||
|
||||
|
||||
class MilvusIndex(EmbeddingIndex):
|
||||
def __init__(self, client: MilvusClient, collection_name: str, consistency_level="Strong"):
|
||||
def __init__(
|
||||
self, client: MilvusClient, collection_name: str, consistency_level="Strong", kvstore: KVStore | None = None
|
||||
):
|
||||
self.client = client
|
||||
self.collection_name = collection_name.replace("-", "_")
|
||||
self.consistency_level = consistency_level
|
||||
self.kvstore = kvstore
|
||||
|
||||
async def delete(self):
|
||||
if await asyncio.to_thread(self.client.has_collection, self.collection_name):
|
||||
|
|
@ -68,11 +71,9 @@ class MilvusIndex(EmbeddingIndex):
|
|||
|
||||
data = []
|
||||
for chunk, embedding in zip(chunks, embeddings, strict=False):
|
||||
chunk_id = generate_chunk_id(chunk.metadata["document_id"], chunk.content)
|
||||
|
||||
data.append(
|
||||
{
|
||||
"chunk_id": chunk_id,
|
||||
"chunk_id": chunk.chunk_id,
|
||||
"vector": embedding,
|
||||
"chunk_content": chunk.model_dump(),
|
||||
}
|
||||
|
|
@ -120,16 +121,42 @@ class MilvusIndex(EmbeddingIndex):
|
|||
raise NotImplementedError("Hybrid search is not supported in Milvus")
|
||||
|
||||
|
||||
class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
||||
class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
|
||||
def __init__(
|
||||
self, config: RemoteMilvusVectorIOConfig | InlineMilvusVectorIOConfig, inference_api: Api.inference
|
||||
self,
|
||||
config: RemoteMilvusVectorIOConfig | InlineMilvusVectorIOConfig,
|
||||
inference_api: Inference,
|
||||
files_api: Files | None,
|
||||
) -> None:
|
||||
self.config = config
|
||||
self.cache = {}
|
||||
self.client = None
|
||||
self.inference_api = inference_api
|
||||
self.files_api = files_api
|
||||
self.kvstore: KVStore | None = None
|
||||
self.vector_db_store = None
|
||||
self.openai_vector_stores: dict[str, dict[str, Any]] = {}
|
||||
self.metadata_collection_name = "openai_vector_stores_metadata"
|
||||
|
||||
async def initialize(self) -> None:
|
||||
self.kvstore = await kvstore_impl(self.config.kvstore)
|
||||
start_key = VECTOR_DBS_PREFIX
|
||||
end_key = f"{VECTOR_DBS_PREFIX}\xff"
|
||||
stored_vector_dbs = await self.kvstore.values_in_range(start_key, end_key)
|
||||
|
||||
for vector_db_data in stored_vector_dbs:
|
||||
vector_db = VectorDB.mdel_validate_json(vector_db_data)
|
||||
index = VectorDBWithIndex(
|
||||
vector_db,
|
||||
index=await MilvusIndex(
|
||||
client=self.client,
|
||||
collection_name=vector_db.identifier,
|
||||
consistency_level=self.config.consistency_level,
|
||||
kvstore=self.kvstore,
|
||||
),
|
||||
inference_api=self.inference_api,
|
||||
)
|
||||
self.cache[vector_db.identifier] = index
|
||||
if isinstance(self.config, RemoteMilvusVectorIOConfig):
|
||||
logger.info(f"Connecting to Milvus server at {self.config.uri}")
|
||||
self.client = MilvusClient(**self.config.model_dump(exclude_none=True))
|
||||
|
|
@ -138,6 +165,8 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
|||
uri = os.path.expanduser(self.config.db_path)
|
||||
self.client = MilvusClient(uri=uri)
|
||||
|
||||
self.openai_vector_stores = await self._load_openai_vector_stores()
|
||||
|
||||
async def shutdown(self) -> None:
|
||||
self.client.close()
|
||||
|
||||
|
|
@ -202,116 +231,62 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
|
|||
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
async def openai_create_vector_store(
|
||||
self,
|
||||
name: str,
|
||||
file_ids: list[str] | None = None,
|
||||
expires_after: dict[str, Any] | None = None,
|
||||
chunking_strategy: dict[str, Any] | None = None,
|
||||
metadata: dict[str, Any] | None = None,
|
||||
embedding_model: str | None = None,
|
||||
embedding_dimension: int | None = 384,
|
||||
provider_id: str | None = None,
|
||||
provider_vector_db_id: str | None = None,
|
||||
) -> VectorStoreObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
|
||||
async def _save_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
|
||||
"""Save vector store metadata to persistent storage."""
|
||||
assert self.kvstore is not None
|
||||
key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
|
||||
await self.kvstore.set(key=key, value=json.dumps(store_info))
|
||||
self.openai_vector_stores[store_id] = store_info
|
||||
|
||||
async def openai_list_vector_stores(
|
||||
self,
|
||||
limit: int | None = 20,
|
||||
order: str | None = "desc",
|
||||
after: str | None = None,
|
||||
before: str | None = None,
|
||||
) -> VectorStoreListResponse:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
|
||||
async def _update_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
|
||||
"""Update vector store metadata in persistent storage."""
|
||||
assert self.kvstore is not None
|
||||
key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
|
||||
await self.kvstore.set(key=key, value=json.dumps(store_info))
|
||||
self.openai_vector_stores[store_id] = store_info
|
||||
|
||||
async def openai_retrieve_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
) -> VectorStoreObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
|
||||
async def _delete_openai_vector_store_from_storage(self, store_id: str) -> None:
|
||||
"""Delete vector store metadata from persistent storage."""
|
||||
assert self.kvstore is not None
|
||||
key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
|
||||
await self.kvstore.delete(key)
|
||||
|
||||
async def openai_update_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
name: str | None = None,
|
||||
expires_after: dict[str, Any] | None = None,
|
||||
metadata: dict[str, Any] | None = None,
|
||||
) -> VectorStoreObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
|
||||
async def _save_openai_vector_store_file(
|
||||
self, store_id: str, file_id: str, file_info: dict[str, Any], file_contents: list[dict[str, Any]]
|
||||
) -> None:
|
||||
"""Save vector store file metadata to Milvus database."""
|
||||
assert self.kvstore is not None
|
||||
key = f"{OPENAI_VECTOR_STORES_FILES_PREFIX}{store_id}:{file_id}"
|
||||
await self.kvstore.set(key=key, value=json.dumps(file_info))
|
||||
content_key = f"{OPENAI_VECTOR_STORES_FILES_CONTENTS_PREFIX}{store_id}:{file_id}"
|
||||
await self.kvstore.set(key=content_key, value=json.dumps(file_contents))
|
||||
|
||||
async def openai_delete_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
) -> VectorStoreDeleteResponse:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
|
||||
async def _load_openai_vector_stores(self) -> dict[str, dict[str, Any]]:
|
||||
"""Load all vector store metadata from persistent storage."""
|
||||
assert self.kvstore is not None
|
||||
start_key = OPENAI_VECTOR_STORES_PREFIX
|
||||
end_key = f"{OPENAI_VECTOR_STORES_PREFIX}\xff"
|
||||
stored = await self.kvstore.values_in_range(start_key, end_key)
|
||||
return {json.loads(s)["id"]: json.loads(s) for s in stored}
|
||||
|
||||
async def openai_search_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
query: str | list[str],
|
||||
filters: dict[str, Any] | None = None,
|
||||
max_num_results: int | None = 10,
|
||||
ranking_options: SearchRankingOptions | None = None,
|
||||
rewrite_query: bool | None = False,
|
||||
search_mode: str | None = "vector",
|
||||
) -> VectorStoreSearchResponsePage:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
async def _save_openai_vector_store_file(
|
||||
self, store_id: str, file_id: str, file_info: dict[str, Any], file_contents: list[dict[str, Any]]
|
||||
) -> None:
|
||||
"""Save vector store file metadata to Milvus database."""
|
||||
raise NotImplementedError("Files API not yet implemented for Milvus")
|
||||
|
||||
async def openai_attach_file_to_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
attributes: dict[str, Any] | None = None,
|
||||
chunking_strategy: VectorStoreChunkingStrategy | None = None,
|
||||
) -> VectorStoreFileObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
async def _load_openai_vector_store_file(self, store_id: str, file_id: str) -> dict[str, Any]:
|
||||
"""Load vector store file metadata from Milvus database."""
|
||||
raise NotImplementedError("Files API not yet implemented for Milvus")
|
||||
|
||||
async def openai_list_files_in_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
limit: int | None = 20,
|
||||
order: str | None = "desc",
|
||||
after: str | None = None,
|
||||
before: str | None = None,
|
||||
filter: VectorStoreFileStatus | None = None,
|
||||
) -> VectorStoreListFilesResponse:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
async def _load_openai_vector_store_file_contents(self, store_id: str, file_id: str) -> list[dict[str, Any]]:
|
||||
"""Load vector store file contents from Milvus database."""
|
||||
raise NotImplementedError("Files API not yet implemented for Milvus")
|
||||
|
||||
async def openai_retrieve_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
async def _update_openai_vector_store_file(self, store_id: str, file_id: str, file_info: dict[str, Any]) -> None:
|
||||
"""Update vector store file metadata in Milvus database."""
|
||||
raise NotImplementedError("Files API not yet implemented for Milvus")
|
||||
|
||||
async def openai_retrieve_vector_store_file_contents(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileContentsResponse:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
|
||||
async def openai_update_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
attributes: dict[str, Any] | None = None,
|
||||
) -> VectorStoreFileObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
|
||||
async def openai_delete_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileObject:
|
||||
raise NotImplementedError("OpenAI Vector Stores API is not supported in Milvus")
|
||||
|
||||
|
||||
def generate_chunk_id(document_id: str, chunk_text: str) -> str:
|
||||
"""Generate a unique chunk ID using a hash of document ID and chunk text."""
|
||||
hash_input = f"{document_id}:{chunk_text}".encode()
|
||||
return str(uuid.UUID(hashlib.md5(hash_input).hexdigest()))
|
||||
|
||||
|
||||
# TODO: refactor this generate_chunk_id along with the `sqlite-vec` implementation into a separate utils file
|
||||
async def _delete_openai_vector_store_file_from_storage(self, store_id: str, file_id: str) -> None:
|
||||
"""Delete vector store file metadata from Milvus database."""
|
||||
raise NotImplementedError("Files API not yet implemented for Milvus")
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue