phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 02:40:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pre-commit fixes

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-03-14 13:56:05 -07:00
parent 967dd0aa08
commit 7e211f8553
314 changed files with 5574 additions and 11369 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/distribution/routers/__init__.py
View file

@ -45,7 +45,7 @@ async def get_routing_table_impl(
return impl
async def get_auto_router_impl(api: Api, routing_table: RoutingTable, _deps) -> Any:
async def get_auto_router_impl(api: Api, routing_table: RoutingTable, deps: Dict[str, Any]) -> Any:
from .routers import (
DatasetIORouter,
EvalRouter,
@ -65,9 +65,17 @@ async def get_auto_router_impl(api: Api, routing_table: RoutingTable, _deps) ->
"eval": EvalRouter,
"tool_runtime": ToolRuntimeRouter,
}
api_to_deps = {
"inference": {"telemetry": Api.telemetry},
}
if api.value not in api_to_routers:
raise ValueError(f"API {api.value} not found in router map")
impl = api_to_routers[api.value](routing_table)
api_to_dep_impl = {}
for dep_name, dep_api in api_to_deps.get(api.value, {}).items():
if dep_api in deps:
api_to_dep_impl[dep_name] = deps[dep_api]
impl = api_to_routers[api.value](routing_table, **api_to_dep_impl)
await impl.initialize()
return impl

279
llama_stack/distribution/routers/routers.py
View file

@ -4,9 +4,9 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, AsyncGenerator, Dict, List, Optional
import time
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
from llama_stack import logcat
from llama_stack.apis.common.content_types import (
URL,
InterleavedContent,
@ -21,6 +21,10 @@ from llama_stack.apis.eval import (
JobStatus,
)
from llama_stack.apis.inference import (
ChatCompletionResponse,
ChatCompletionResponseEventType,
ChatCompletionResponseStreamChunk,
CompletionMessage,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
@ -28,13 +32,14 @@ from llama_stack.apis.inference import (
Message,
ResponseFormat,
SamplingParams,
StopReason,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import ModelType
from llama_stack.apis.models import Model, ModelType
from llama_stack.apis.safety import RunShieldResponse, Safety
from llama_stack.apis.scoring import (
ScoreBatchResponse,
@ -43,6 +48,7 @@ from llama_stack.apis.scoring import (
ScoringFnParams,
)
from llama_stack.apis.shields import Shield
from llama_stack.apis.telemetry import MetricEvent, MetricInResponse, Telemetry
from llama_stack.apis.tools import (
RAGDocument,
RAGQueryConfig,
@ -52,7 +58,13 @@ from llama_stack.apis.tools import (
ToolRuntime,
)
from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
from llama_stack.log import get_logger
from llama_stack.models.llama.llama3.chat_format import ChatFormat
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.providers.datatypes import RoutingTable
from llama_stack.providers.utils.telemetry.tracing import get_current_span
logger = get_logger(name=__name__, category="core")
class VectorIORouter(VectorIO):
@ -62,15 +74,15 @@ class VectorIORouter(VectorIO):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing VectorIORouter")
logger.debug("Initializing VectorIORouter")
self.routing_table = routing_table
async def initialize(self) -> None:
logcat.debug("core", "VectorIORouter.initialize")
logger.debug("VectorIORouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "VectorIORouter.shutdown")
logger.debug("VectorIORouter.shutdown")
pass
async def register_vector_db(
@ -81,7 +93,7 @@ class VectorIORouter(VectorIO):
provider_id: Optional[str] = None,
provider_vector_db_id: Optional[str] = None,
) -> None:
logcat.debug("core", f"VectorIORouter.register_vector_db: {vector_db_id}, {embedding_model}")
logger.debug(f"VectorIORouter.register_vector_db: {vector_db_id}, {embedding_model}")
await self.routing_table.register_vector_db(
vector_db_id,
embedding_model,
@ -96,8 +108,7 @@ class VectorIORouter(VectorIO):
chunks: List[Chunk],
ttl_seconds: Optional[int] = None,
) -> None:
logcat.debug(
"core",
logger.debug(
f"VectorIORouter.insert_chunks: {vector_db_id}, {len(chunks)} chunks, ttl_seconds={ttl_seconds}, chunk_ids={[chunk.metadata['document_id'] for chunk in chunks[:3]]}{' and more...' if len(chunks) > 3 else ''}",
)
return await self.routing_table.get_provider_impl(vector_db_id).insert_chunks(vector_db_id, chunks, ttl_seconds)
@ -108,7 +119,7 @@ class VectorIORouter(VectorIO):
query: InterleavedContent,
params: Optional[Dict[str, Any]] = None,
) -> QueryChunksResponse:
logcat.debug("core", f"VectorIORouter.query_chunks: {vector_db_id}")
logger.debug(f"VectorIORouter.query_chunks: {vector_db_id}")
return await self.routing_table.get_provider_impl(vector_db_id).query_chunks(vector_db_id, query, params)
@ -118,16 +129,21 @@ class InferenceRouter(Inference):
def __init__(
self,
routing_table: RoutingTable,
telemetry: Optional[Telemetry] = None,
) -> None:
logcat.debug("core", "Initializing InferenceRouter")
logger.debug("Initializing InferenceRouter")
self.routing_table = routing_table
self.telemetry = telemetry
if self.telemetry:
self.tokenizer = Tokenizer.get_instance()
self.formatter = ChatFormat(self.tokenizer)
async def initialize(self) -> None:
logcat.debug("core", "InferenceRouter.initialize")
logger.debug("InferenceRouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "InferenceRouter.shutdown")
logger.debug("InferenceRouter.shutdown")
pass
async def register_model(
@ -138,17 +154,81 @@ class InferenceRouter(Inference):
metadata: Optional[Dict[str, Any]] = None,
model_type: Optional[ModelType] = None,
) -> None:
logcat.debug(
"core",
logger.debug(
f"InferenceRouter.register_model: {model_id=} {provider_model_id=} {provider_id=} {metadata=} {model_type=}",
)
await self.routing_table.register_model(model_id, provider_model_id, provider_id, metadata, model_type)
def _construct_metrics(
self, prompt_tokens: int, completion_tokens: int, total_tokens: int, model: Model
) -> List[MetricEvent]:
"""Constructs a list of MetricEvent objects containing token usage metrics.
Args:
prompt_tokens: Number of tokens in the prompt
completion_tokens: Number of tokens in the completion
total_tokens: Total number of tokens used
model: Model object containing model_id and provider_id
Returns:
List of MetricEvent objects with token usage metrics
"""
span = get_current_span()
if span is None:
logger.warning("No span found for token usage metrics")
return []
metrics = [
("prompt_tokens", prompt_tokens),
("completion_tokens", completion_tokens),
("total_tokens", total_tokens),
]
metric_events = []
for metric_name, value in metrics:
metric_events.append(
MetricEvent(
trace_id=span.trace_id,
span_id=span.span_id,
metric=metric_name,
value=value,
timestamp=time.time(),
unit="tokens",
attributes={
"model_id": model.model_id,
"provider_id": model.provider_id,
},
)
)
return metric_events
async def _compute_and_log_token_usage(
self,
prompt_tokens: int,
completion_tokens: int,
total_tokens: int,
model: Model,
) -> List[MetricInResponse]:
metrics = self._construct_metrics(prompt_tokens, completion_tokens, total_tokens, model)
if self.telemetry:
for metric in metrics:
await self.telemetry.log_event(metric)
return [MetricInResponse(metric=metric.metric, value=metric.value) for metric in metrics]
async def _count_tokens(
self,
messages: List[Message] | InterleavedContent,
tool_prompt_format: Optional[ToolPromptFormat] = None,
) -> Optional[int]:
if isinstance(messages, list):
encoded = self.formatter.encode_dialog_prompt(messages, tool_prompt_format)
else:
encoded = self.formatter.encode_content(messages)
return len(encoded.tokens) if encoded and encoded.tokens else 0
async def chat_completion(
self,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = None,
@ -156,11 +236,12 @@ class InferenceRouter(Inference):
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
tool_config: Optional[ToolConfig] = None,
) -> AsyncGenerator:
logcat.debug(
"core",
) -> Union[ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]]:
logger.debug(
f"InferenceRouter.chat_completion: {model_id=}, {stream=}, {messages=}, {tools=}, {tool_config=}, {response_format=}",
)
if sampling_params is None:
sampling_params = SamplingParams()
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
@ -205,22 +286,60 @@ class InferenceRouter(Inference):
tool_config=tool_config,
)
provider = self.routing_table.get_provider_impl(model_id)
prompt_tokens = await self._count_tokens(messages, tool_config.tool_prompt_format)
if stream:
return (chunk async for chunk in await provider.chat_completion(**params))
async def stream_generator():
completion_text = ""
async for chunk in await provider.chat_completion(**params):
if chunk.event.event_type == ChatCompletionResponseEventType.progress:
if chunk.event.delta.type == "text":
completion_text += chunk.event.delta.text
if chunk.event.event_type == ChatCompletionResponseEventType.complete:
completion_tokens = await self._count_tokens(
[CompletionMessage(content=completion_text, stop_reason=StopReason.end_of_turn)],
tool_config.tool_prompt_format,
)
total_tokens = (prompt_tokens or 0) + (completion_tokens or 0)
metrics = await self._compute_and_log_token_usage(
prompt_tokens or 0,
completion_tokens or 0,
total_tokens,
model,
)
chunk.metrics = metrics if chunk.metrics is None else chunk.metrics + metrics
yield chunk
return stream_generator()
else:
return await provider.chat_completion(**params)
response = await provider.chat_completion(**params)
completion_tokens = await self._count_tokens(
[response.completion_message],
tool_config.tool_prompt_format,
)
total_tokens = (prompt_tokens or 0) + (completion_tokens or 0)
metrics = await self._compute_and_log_token_usage(
prompt_tokens or 0,
completion_tokens or 0,
total_tokens,
model,
)
response.metrics = metrics if response.metrics is None else response.metrics + metrics
return response
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
logcat.debug(
"core",
if sampling_params is None:
sampling_params = SamplingParams()
logger.debug(
f"InferenceRouter.completion: {model_id=}, {stream=}, {content=}, {sampling_params=}, {response_format=}",
)
model = await self.routing_table.get_model(model_id)
@ -237,10 +356,41 @@ class InferenceRouter(Inference):
stream=stream,
logprobs=logprobs,
)
prompt_tokens = await self._count_tokens(content)
if stream:
return (chunk async for chunk in await provider.completion(**params))
async def stream_generator():
completion_text = ""
async for chunk in await provider.completion(**params):
if hasattr(chunk, "delta"):
completion_text += chunk.delta
if hasattr(chunk, "stop_reason") and chunk.stop_reason and self.telemetry:
completion_tokens = await self._count_tokens(completion_text)
total_tokens = (prompt_tokens or 0) + (completion_tokens or 0)
metrics = await self._compute_and_log_token_usage(
prompt_tokens or 0,
completion_tokens or 0,
total_tokens,
model,
)
chunk.metrics = metrics if chunk.metrics is None else chunk.metrics + metrics
yield chunk
return stream_generator()
else:
return await provider.completion(**params)
response = await provider.completion(**params)
completion_tokens = await self._count_tokens(response.content)
total_tokens = (prompt_tokens or 0) + (completion_tokens or 0)
metrics = await self._compute_and_log_token_usage(
prompt_tokens or 0,
completion_tokens or 0,
total_tokens,
model,
)
response.metrics = metrics if response.metrics is None else response.metrics + metrics
return response
async def embeddings(
self,
@ -250,7 +400,7 @@ class InferenceRouter(Inference):
output_dimension: Optional[int] = None,
task_type: Optional[EmbeddingTaskType] = None,
) -> EmbeddingsResponse:
logcat.debug("core", f"InferenceRouter.embeddings: {model_id}")
logger.debug(f"InferenceRouter.embeddings: {model_id}")
model = await self.routing_table.get_model(model_id)
if model is None:
raise ValueError(f"Model '{model_id}' not found")
@ -270,15 +420,15 @@ class SafetyRouter(Safety):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing SafetyRouter")
logger.debug("Initializing SafetyRouter")
self.routing_table = routing_table
async def initialize(self) -> None:
logcat.debug("core", "SafetyRouter.initialize")
logger.debug("SafetyRouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "SafetyRouter.shutdown")
logger.debug("SafetyRouter.shutdown")
pass
async def register_shield(
@ -288,7 +438,7 @@ class SafetyRouter(Safety):
provider_id: Optional[str] = None,
params: Optional[Dict[str, Any]] = None,
) -> Shield:
logcat.debug("core", f"SafetyRouter.register_shield: {shield_id}")
logger.debug(f"SafetyRouter.register_shield: {shield_id}")
return await self.routing_table.register_shield(shield_id, provider_shield_id, provider_id, params)
async def run_shield(
@ -297,7 +447,7 @@ class SafetyRouter(Safety):
messages: List[Message],
params: Dict[str, Any] = None,
) -> RunShieldResponse:
logcat.debug("core", f"SafetyRouter.run_shield: {shield_id}")
logger.debug(f"SafetyRouter.run_shield: {shield_id}")
return await self.routing_table.get_provider_impl(shield_id).run_shield(
shield_id=shield_id,
messages=messages,
@ -310,15 +460,15 @@ class DatasetIORouter(DatasetIO):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing DatasetIORouter")
logger.debug("Initializing DatasetIORouter")
self.routing_table = routing_table
async def initialize(self) -> None:
logcat.debug("core", "DatasetIORouter.initialize")
logger.debug("DatasetIORouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "DatasetIORouter.shutdown")
logger.debug("DatasetIORouter.shutdown")
pass
async def get_rows_paginated(
@ -328,7 +478,9 @@ class DatasetIORouter(DatasetIO):
page_token: Optional[str] = None,
filter_condition: Optional[str] = None,
) -> PaginatedRowsResult:
logcat.debug("core", f"DatasetIORouter.get_rows_paginated: {dataset_id}, rows_in_page={rows_in_page}")
logger.debug(
f"DatasetIORouter.get_rows_paginated: {dataset_id}, rows_in_page={rows_in_page}",
)
return await self.routing_table.get_provider_impl(dataset_id).get_rows_paginated(
dataset_id=dataset_id,
rows_in_page=rows_in_page,
@ -337,7 +489,7 @@ class DatasetIORouter(DatasetIO):
)
async def append_rows(self, dataset_id: str, rows: List[Dict[str, Any]]) -> None:
logcat.debug("core", f"DatasetIORouter.append_rows: {dataset_id}, {len(rows)} rows")
logger.debug(f"DatasetIORouter.append_rows: {dataset_id}, {len(rows)} rows")
return await self.routing_table.get_provider_impl(dataset_id).append_rows(
dataset_id=dataset_id,
rows=rows,
@ -349,15 +501,15 @@ class ScoringRouter(Scoring):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing ScoringRouter")
logger.debug("Initializing ScoringRouter")
self.routing_table = routing_table
async def initialize(self) -> None:
logcat.debug("core", "ScoringRouter.initialize")
logger.debug("ScoringRouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "ScoringRouter.shutdown")
logger.debug("ScoringRouter.shutdown")
pass
async def score_batch(
@ -366,7 +518,7 @@ class ScoringRouter(Scoring):
scoring_functions: Dict[str, Optional[ScoringFnParams]] = None,
save_results_dataset: bool = False,
) -> ScoreBatchResponse:
logcat.debug("core", f"ScoringRouter.score_batch: {dataset_id}")
logger.debug(f"ScoringRouter.score_batch: {dataset_id}")
res = {}
for fn_identifier in scoring_functions.keys():
score_response = await self.routing_table.get_provider_impl(fn_identifier).score_batch(
@ -387,7 +539,7 @@ class ScoringRouter(Scoring):
input_rows: List[Dict[str, Any]],
scoring_functions: Dict[str, Optional[ScoringFnParams]] = None,
) -> ScoreResponse:
logcat.debug("core", f"ScoringRouter.score: {len(input_rows)} rows, {len(scoring_functions)} functions")
logger.debug(f"ScoringRouter.score: {len(input_rows)} rows, {len(scoring_functions)} functions")
res = {}
# look up and map each scoring function to its provider impl
for fn_identifier in scoring_functions.keys():
@ -405,26 +557,26 @@ class EvalRouter(Eval):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing EvalRouter")
logger.debug("Initializing EvalRouter")
self.routing_table = routing_table
async def initialize(self) -> None:
logcat.debug("core", "EvalRouter.initialize")
logger.debug("EvalRouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "EvalRouter.shutdown")
logger.debug("EvalRouter.shutdown")
pass
async def run_eval(
self,
benchmark_id: str,
task_config: BenchmarkConfig,
benchmark_config: BenchmarkConfig,
) -> Job:
logcat.debug("core", f"EvalRouter.run_eval: {benchmark_id}")
logger.debug(f"EvalRouter.run_eval: {benchmark_id}")
return await self.routing_table.get_provider_impl(benchmark_id).run_eval(
benchmark_id=benchmark_id,
task_config=task_config,
benchmark_config=benchmark_config,
)
async def evaluate_rows(
@ -432,14 +584,14 @@ class EvalRouter(Eval):
benchmark_id: str,
input_rows: List[Dict[str, Any]],
scoring_functions: List[str],
task_config: BenchmarkConfig,
benchmark_config: BenchmarkConfig,
) -> EvaluateResponse:
logcat.debug("core", f"EvalRouter.evaluate_rows: {benchmark_id}, {len(input_rows)} rows")
logger.debug(f"EvalRouter.evaluate_rows: {benchmark_id}, {len(input_rows)} rows")
return await self.routing_table.get_provider_impl(benchmark_id).evaluate_rows(
benchmark_id=benchmark_id,
input_rows=input_rows,
scoring_functions=scoring_functions,
task_config=task_config,
benchmark_config=benchmark_config,
)
async def job_status(
@ -447,7 +599,7 @@ class EvalRouter(Eval):
benchmark_id: str,
job_id: str,
) -> Optional[JobStatus]:
logcat.debug("core", f"EvalRouter.job_status: {benchmark_id}, {job_id}")
logger.debug(f"EvalRouter.job_status: {benchmark_id}, {job_id}")
return await self.routing_table.get_provider_impl(benchmark_id).job_status(benchmark_id, job_id)
async def job_cancel(
@ -455,7 +607,7 @@ class EvalRouter(Eval):
benchmark_id: str,
job_id: str,
) -> None:
logcat.debug("core", f"EvalRouter.job_cancel: {benchmark_id}, {job_id}")
logger.debug(f"EvalRouter.job_cancel: {benchmark_id}, {job_id}")
await self.routing_table.get_provider_impl(benchmark_id).job_cancel(
benchmark_id,
job_id,
@ -466,7 +618,7 @@ class EvalRouter(Eval):
benchmark_id: str,
job_id: str,
) -> EvaluateResponse:
logcat.debug("core", f"EvalRouter.job_result: {benchmark_id}, {job_id}")
logger.debug(f"EvalRouter.job_result: {benchmark_id}, {job_id}")
return await self.routing_table.get_provider_impl(benchmark_id).job_result(
benchmark_id,
job_id,
@ -479,7 +631,7 @@ class ToolRuntimeRouter(ToolRuntime):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing ToolRuntimeRouter.RagToolImpl")
logger.debug("Initializing ToolRuntimeRouter.RagToolImpl")
self.routing_table = routing_table
async def query(
@ -488,7 +640,7 @@ class ToolRuntimeRouter(ToolRuntime):
vector_db_ids: List[str],
query_config: Optional[RAGQueryConfig] = None,
) -> RAGQueryResult:
logcat.debug("core", f"ToolRuntimeRouter.RagToolImpl.query: {vector_db_ids}")
logger.debug(f"ToolRuntimeRouter.RagToolImpl.query: {vector_db_ids}")
return await self.routing_table.get_provider_impl("knowledge_search").query(
content, vector_db_ids, query_config
)
@ -499,9 +651,8 @@ class ToolRuntimeRouter(ToolRuntime):
vector_db_id: str,
chunk_size_in_tokens: int = 512,
) -> None:
logcat.debug(
"core",
f"ToolRuntimeRouter.RagToolImpl.insert: {vector_db_id}, {len(documents)} documents, chunk_size={chunk_size_in_tokens}",
logger.debug(
f"ToolRuntimeRouter.RagToolImpl.insert: {vector_db_id}, {len(documents)} documents, chunk_size={chunk_size_in_tokens}"
)
return await self.routing_table.get_provider_impl("insert_into_memory").insert(
documents, vector_db_id, chunk_size_in_tokens
@ -511,7 +662,7 @@ class ToolRuntimeRouter(ToolRuntime):
self,
routing_table: RoutingTable,
) -> None:
logcat.debug("core", "Initializing ToolRuntimeRouter")
logger.debug("Initializing ToolRuntimeRouter")
self.routing_table = routing_table
# HACK ALERT this should be in sync with "get_all_api_endpoints()"
@ -520,15 +671,15 @@ class ToolRuntimeRouter(ToolRuntime):
setattr(self, f"rag_tool.{method}", getattr(self.rag_tool, method))
async def initialize(self) -> None:
logcat.debug("core", "ToolRuntimeRouter.initialize")
logger.debug("ToolRuntimeRouter.initialize")
pass
async def shutdown(self) -> None:
logcat.debug("core", "ToolRuntimeRouter.shutdown")
logger.debug("ToolRuntimeRouter.shutdown")
pass
async def invoke_tool(self, tool_name: str, kwargs: Dict[str, Any]) -> Any:
logcat.debug("core", f"ToolRuntimeRouter.invoke_tool: {tool_name}")
logger.debug(f"ToolRuntimeRouter.invoke_tool: {tool_name}")
return await self.routing_table.get_provider_impl(tool_name).invoke_tool(
tool_name=tool_name,
kwargs=kwargs,
@ -537,5 +688,5 @@ class ToolRuntimeRouter(ToolRuntime):
async def list_runtime_tools(
self, tool_group_id: Optional[str] = None, mcp_endpoint: Optional[URL] = None
) -> List[ToolDef]:
logcat.debug("core", f"ToolRuntimeRouter.list_runtime_tools: {tool_group_id}")
logger.debug(f"ToolRuntimeRouter.list_runtime_tools: {tool_group_id}")
return await self.routing_table.get_provider_impl(tool_group_id).list_tools(tool_group_id, mcp_endpoint)

13
llama_stack/distribution/routers/routing_tables.py
View file

@ -309,13 +309,14 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
if provider_vector_db_id is None:
provider_vector_db_id = vector_db_id
if provider_id is None:
# If provider_id not specified, use the only provider if it supports this shield type
if len(self.impls_by_provider_id) == 1:
if len(self.impls_by_provider_id) > 0:
provider_id = list(self.impls_by_provider_id.keys())[0]
if len(self.impls_by_provider_id) > 1:
logger.warning(
f"No provider specified and multiple providers available. Arbitrarily selected the first provider {provider_id}."
)
else:
raise ValueError(
"No provider specified and multiple providers available. Please specify a provider_id."
)
raise ValueError("No provider available. Please configure a vector_io provider.")
model = await self.get_object_by_identifier("model", embedding_model)
if model is None:
raise ValueError(f"Model {embedding_model} not found")
@ -366,7 +367,7 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
provider_id = list(self.impls_by_provider_id.keys())[0]
else:
raise ValueError(
"No provider specified and multiple providers available. Please specify a provider_id."
f"No provider specified and multiple providers available. Please specify a provider_id. Available providers: {self.impls_by_provider_id.keys()}"
)
if metadata is None:
metadata = {}