mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-19 03:29:39 +00:00
adding logo and favicon
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chore: Enable keyword search for Milvus inline (#3073) With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite supports keyword search using BM25. While introducing keyword search we had explicitly disabled it for inline milvus. This PR removes the need for the check, and enables `inline::milvus` for tests. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Run llama stack with `inline::milvus` enabled: ``` pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v ``` ``` INFO 2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS =========================================================================================== test session starts ============================================================================================ platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 3 items tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED [ 33%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED [ 66%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED [100%] ============================================================================================ 3 passed in 4.75s ============================================================================================= ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> chore: Fixup main pre commit (#3204) build: Bump version to 0.2.18 chore: Faster npm pre-commit (#3206) Adds npm to pre-commit.yml installation and caches ui Removes node installation during pre-commit. <!-- 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.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chiecking in for tonight, wip moving to agents api Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> remove log Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix: disable ui-prettier & ui-eslint (#3207) chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> fix: fix ```openai_embeddings``` for asymmetric embedding NIMs (#3205) NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ``` cleaning up Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating session manager to cache messages locally Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix linter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> more cleanup Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo
parent
e7be568d7e
commit
6620b625f1
76 changed files with 2343 additions and 1187 deletions
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
from typing import Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
|
|
@ -20,6 +19,7 @@ from llama_stack.apis.vector_io import (
|
|||
QueryChunksResponse,
|
||||
VectorIO,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
|
|
@ -33,7 +33,7 @@ from llama_stack.providers.utils.memory.vector_store import (
|
|||
|
||||
from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="vector_io")
|
||||
|
||||
ChromaClientType = chromadb.api.AsyncClientAPI | chromadb.api.ClientAPI
|
||||
|
||||
|
|
|
|||
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
|
|
@ -21,6 +20,7 @@ from llama_stack.apis.vector_io import (
|
|||
QueryChunksResponse,
|
||||
VectorIO,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
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
|
||||
|
|
@ -36,7 +36,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
|
|||
|
||||
from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
logger = get_logger(name=__name__, category="vector_io")
|
||||
|
||||
VERSION = "v3"
|
||||
VECTOR_DBS_PREFIX = f"vector_dbs:milvus:{VERSION}::"
|
||||
|
|
@ -413,15 +413,6 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
|
|||
index = await self._get_and_cache_vector_db_index(vector_db_id)
|
||||
if not index:
|
||||
raise VectorStoreNotFoundError(vector_db_id)
|
||||
|
||||
if params and params.get("mode") == "keyword":
|
||||
# Check if this is inline Milvus (Milvus-Lite)
|
||||
if hasattr(self.config, "db_path"):
|
||||
raise NotImplementedError(
|
||||
"Keyword search is not supported in Milvus-Lite. "
|
||||
"Please use a remote Milvus server for keyword search functionality."
|
||||
)
|
||||
|
||||
return await index.query_chunks(query, params)
|
||||
|
||||
async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
import psycopg2
|
||||
|
|
@ -22,6 +21,7 @@ from llama_stack.apis.vector_io import (
|
|||
QueryChunksResponse,
|
||||
VectorIO,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.api import KVStore
|
||||
|
|
@ -34,7 +34,7 @@ from llama_stack.providers.utils.memory.vector_store import (
|
|||
|
||||
from .config import PGVectorVectorIOConfig
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="vector_io")
|
||||
|
||||
VERSION = "v3"
|
||||
VECTOR_DBS_PREFIX = f"vector_dbs:pgvector:{VERSION}::"
|
||||
|
|
|
|||
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import uuid
|
||||
from typing import Any
|
||||
|
||||
|
|
@ -24,6 +23,7 @@ from llama_stack.apis.vector_io import (
|
|||
VectorStoreChunkingStrategy,
|
||||
VectorStoreFileObject,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
|
||||
from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
|
||||
|
|
@ -36,7 +36,7 @@ from llama_stack.providers.utils.memory.vector_store import (
|
|||
|
||||
from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="vector_io")
|
||||
CHUNK_ID_KEY = "_chunk_id"
|
||||
|
||||
# KV store prefixes for vector databases
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
import json
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
import weaviate
|
||||
|
|
@ -19,6 +18,7 @@ from llama_stack.apis.files.files import Files
|
|||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
|
||||
from llama_stack.core.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.api import KVStore
|
||||
|
|
@ -34,7 +34,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
|
|||
|
||||
from .config import WeaviateVectorIOConfig
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="vector_io")
|
||||
|
||||
VERSION = "v3"
|
||||
VECTOR_DBS_PREFIX = f"vector_dbs:weaviate:{VERSION}::"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue