llama-stack/llama_stack/distribution/inspect.py
Sébastien Han 418645696a
fix: improve signal handling and update dependencies (#1044)
# What does this PR do?
This commit enhances the signal handling mechanism in the server by
improving the `handle_signal` (previously handle_sigint) function. It
now properly retrieves the signal name, ensuring clearer logging when a
termination signal is received. Additionally, it cancels all running
tasks and waits for their completion before stopping the event loop,
allowing for a more graceful shutdown. Support for handling
SIGTERM has also been added alongside SIGINT.

Before the changes, handle_sigint used asyncio.run(run_shutdown()).
However, asyncio.run() is meant to start a new event loop, and calling
it inside an existing one (like when running Uvicorn) raises an error.
The fix replaces asyncio.run(run_shutdown()) with an async function
scheduled on the existing loop using loop.create_task(shutdown()). This
ensures that the shutdown coroutine runs within the current event loop
instead of trying to create a new one.

Furthermore, this commit updates the project dependencies. `fastapi` and
`uvicorn` have been added to the development dependencies in
`pyproject.toml` and `uv.lock`, ensuring that the necessary packages are
available for development and execution.

Closes: https://github.com/meta-llama/llama-stack/issues/1043
Signed-off-by: Sébastien Han <seb@redhat.com>

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan

Run a server and send SIGINT:

```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
Using config file: llama_stack/templates/ollama/run.yaml
Run configuration:
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
container_image: null
datasets: []
eval_tasks: []
image_name: ollama
metadata_store:
  db_path: /Users/leseb/.llama/distributions/ollama/registry.db
  namespace: null
  type: sqlite
models:
- metadata: {}
  model_id: meta-llama/Llama-3.2-3B-Instruct
  model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType
  - llm
  provider_id: ollama
  provider_model_id: null
- metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
  model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType
  - embedding
  provider_id: sentence-transformers
  provider_model_id: null
providers:
  agents:
  - config:
      persistence_store:
        db_path: /Users/leseb/.llama/distributions/ollama/agents_store.db
        namespace: null
        type: sqlite
    provider_id: meta-reference
    provider_type: inline::meta-reference
  datasetio:
  - config: {}
    provider_id: huggingface
    provider_type: remote::huggingface
  - config: {}
    provider_id: localfs
    provider_type: inline::localfs
  eval:
  - config: {}
    provider_id: meta-reference
    provider_type: inline::meta-reference
  inference:
  - config:
      url: http://localhost:11434
    provider_id: ollama
    provider_type: remote::ollama
  - config: {}
    provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
  safety:
  - config: {}
    provider_id: llama-guard
    provider_type: inline::llama-guard
  scoring:
  - config: {}
    provider_id: basic
    provider_type: inline::basic
  - config: {}
    provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
  - config:
      openai_api_key: '********'
    provider_id: braintrust
    provider_type: inline::braintrust
  telemetry:
  - config:
      service_name: llama-stack
      sinks: console,sqlite
      sqlite_db_path: /Users/leseb/.llama/distributions/ollama/trace_store.db
    provider_id: meta-reference
    provider_type: inline::meta-reference
  tool_runtime:
  - config:
      api_key: '********'
      max_results: 3
    provider_id: brave-search
    provider_type: remote::brave-search
  - config:
      api_key: '********'
      max_results: 3
    provider_id: tavily-search
    provider_type: remote::tavily-search
  - config: {}
    provider_id: code-interpreter
    provider_type: inline::code-interpreter
  - config: {}
    provider_id: rag-runtime
    provider_type: inline::rag-runtime
  vector_io:
  - config:
      kvstore:
        db_path: /Users/leseb/.llama/distributions/ollama/faiss_store.db
        namespace: null
        type: sqlite
    provider_id: faiss
    provider_type: inline::faiss
scoring_fns: []
server:
  port: 8321
  tls_certfile: null
  tls_keyfile: null
shields: []
tool_groups:
- args: null
  mcp_endpoint: null
  provider_id: tavily-search
  toolgroup_id: builtin::websearch
- args: null
  mcp_endpoint: null
  provider_id: rag-runtime
  toolgroup_id: builtin::rag
- args: null
  mcp_endpoint: null
  provider_id: code-interpreter
  toolgroup_id: builtin::code_interpreter
vector_dbs: []
version: '2'

INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:213: Resolved 31 providers
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-inference => ollama
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-inference => sentence-transformers
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  models => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inference => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-vector_io => faiss
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-safety => llama-guard
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  shields => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  safety => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  vector_dbs => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  vector_io => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-tool_runtime => brave-search
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-tool_runtime => tavily-search
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-tool_runtime => code-interpreter
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-tool_runtime => rag-runtime
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  tool_groups => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  tool_runtime => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  agents => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-datasetio => huggingface
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-datasetio => localfs
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  datasets => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  datasetio => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  telemetry => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-scoring => basic
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-scoring => llm-as-judge
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-scoring => braintrust
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  scoring_functions => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  scoring => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inner-eval => meta-reference
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  eval_tasks => __routing_table__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  eval => __autorouted__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:215:  inspect => __builtin__
INFO 2025-02-12 10:21:03,540 llama_stack.distribution.resolver:216: 
INFO 2025-02-12 10:21:03,723 llama_stack.providers.remote.inference.ollama.ollama:148: checking connectivity to Ollama at `http://localhost:11434`...
INFO 2025-02-12 10:21:03,734 httpx:1740: HTTP Request: GET http://localhost:11434/api/ps "HTTP/1.1 200 OK"
INFO 2025-02-12 10:21:03,843 faiss.loader:148: Loading faiss.
INFO 2025-02-12 10:21:03,865 faiss.loader:150: Successfully loaded faiss.
INFO 2025-02-12 10:21:03,868 faiss:173: Failed to load GPU Faiss: name 'GpuIndexIVFFlat' is not defined. Will not load constructor refs for GPU indexes.
Warning: `bwrap` is not available. Code interpreter tool will not work correctly.
INFO 2025-02-12 10:21:04,315 datasets:54: PyTorch version 2.6.0 available.
INFO 2025-02-12 10:21:04,556 httpx:1740: HTTP Request: GET http://localhost:11434/api/ps "HTTP/1.1 200 OK"
INFO 2025-02-12 10:21:04,557 llama_stack.providers.utils.inference.embedding_mixin:42: Loading sentence transformer for all-MiniLM-L6-v2...
INFO 2025-02-12 10:21:07,202 sentence_transformers.SentenceTransformer:210: Use pytorch device_name: mps
INFO 2025-02-12 10:21:07,202 sentence_transformers.SentenceTransformer:218: Load pretrained SentenceTransformer: all-MiniLM-L6-v2
INFO 2025-02-12 10:21:09,500 llama_stack.distribution.stack:102: Models: all-MiniLM-L6-v2 served by sentence-transformers
INFO 2025-02-12 10:21:09,500 llama_stack.distribution.stack:102: Models: meta-llama/Llama-3.2-3B-Instruct served by ollama
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::equality served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::regex_parser_multiple_choice_answer served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: basic::subset_of served by basic
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-correctness served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-relevancy served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::answer-similarity served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-entity-recall served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-precision served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-recall served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::context-relevancy served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::factuality served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: braintrust::faithfulness served by braintrust
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: llm-as-judge::405b-simpleqa served by llm-as-judge
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Scoring_fns: llm-as-judge::base served by llm-as-judge
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::code_interpreter served by code-interpreter
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::rag served by rag-runtime
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:102: Tool_groups: builtin::websearch served by tavily-search
INFO 2025-02-12 10:21:09,501 llama_stack.distribution.stack:106: 
Serving API eval
 POST /v1/eval/tasks/{task_id}/evaluations
 DELETE /v1/eval/tasks/{task_id}/jobs/{job_id}
 GET /v1/eval/tasks/{task_id}/jobs/{job_id}/result
 GET /v1/eval/tasks/{task_id}/jobs/{job_id}
 POST /v1/eval/tasks/{task_id}/jobs
Serving API agents
 POST /v1/agents
 POST /v1/agents/{agent_id}/session
 POST /v1/agents/{agent_id}/session/{session_id}/turn
 DELETE /v1/agents/{agent_id}
 DELETE /v1/agents/{agent_id}/session/{session_id}
 GET /v1/agents/{agent_id}/session/{session_id}
 GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}
 GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}
Serving API scoring_functions
 GET /v1/scoring-functions/{scoring_fn_id}
 GET /v1/scoring-functions
 POST /v1/scoring-functions
Serving API safety
 POST /v1/safety/run-shield
Serving API inspect
 GET /v1/health
 GET /v1/inspect/providers
 GET /v1/inspect/routes
 GET /v1/version
Serving API tool_runtime
 POST /v1/tool-runtime/invoke
 GET /v1/tool-runtime/list-tools
 POST /v1/tool-runtime/rag-tool/insert
 POST /v1/tool-runtime/rag-tool/query
Serving API datasetio
 POST /v1/datasetio/rows
 GET /v1/datasetio/rows
Serving API shields
 GET /v1/shields/{identifier}
 GET /v1/shields
 POST /v1/shields
Serving API eval_tasks
 GET /v1/eval-tasks/{eval_task_id}
 GET /v1/eval-tasks
 POST /v1/eval-tasks
Serving API models
 GET /v1/models/{model_id}
 GET /v1/models
 POST /v1/models
 DELETE /v1/models/{model_id}
Serving API datasets
 GET /v1/datasets/{dataset_id}
 GET /v1/datasets
 POST /v1/datasets
 DELETE /v1/datasets/{dataset_id}
Serving API vector_io
 POST /v1/vector-io/insert
 POST /v1/vector-io/query
Serving API inference
 POST /v1/inference/chat-completion
 POST /v1/inference/completion
 POST /v1/inference/embeddings
Serving API tool_groups
 GET /v1/tools/{tool_name}
 GET /v1/toolgroups/{toolgroup_id}
 GET /v1/toolgroups
 GET /v1/tools
 POST /v1/toolgroups
 DELETE /v1/toolgroups/{toolgroup_id}
Serving API vector_dbs
 GET /v1/vector-dbs/{vector_db_id}
 GET /v1/vector-dbs
 POST /v1/vector-dbs
 DELETE /v1/vector-dbs/{vector_db_id}
Serving API scoring
 POST /v1/scoring/score
 POST /v1/scoring/score-batch
Serving API telemetry
 GET /v1/telemetry/traces/{trace_id}/spans/{span_id}
 GET /v1/telemetry/spans/{span_id}/tree
 GET /v1/telemetry/traces/{trace_id}
 POST /v1/telemetry/events
 GET /v1/telemetry/spans
 GET /v1/telemetry/traces
 POST /v1/telemetry/spans/export

Listening on ['::', '0.0.0.0']:5001
INFO:     Started server process [65372]
INFO:     Waiting for application startup.
INFO:     ASGI 'lifespan' protocol appears unsupported.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://['::', '0.0.0.0']:5001 (Press CTRL+C to quit)
^CINFO:     Shutting down
INFO:     Finished server process [65372]
Received signal SIGINT (2). Exiting gracefully...
INFO 2025-02-12 10:21:11,215 __main__:151: Shutting down ModelsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down InferenceRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ShieldsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down SafetyRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down VectorDBsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down VectorIORouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ToolGroupsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ToolRuntimeRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down MetaReferenceAgentsImpl
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DatasetsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DatasetIORouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down TelemetryAdapter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ScoringFunctionsRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down ScoringRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down EvalTasksRoutingTable
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down EvalRouter
INFO 2025-02-12 10:21:11,216 __main__:151: Shutting down DistributionInspectImpl
```

[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)

Signed-off-by: Sébastien Han <seb@redhat.com>
2025-02-13 08:07:59 -08:00

87 lines
2.4 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from importlib.metadata import version
from pydantic import BaseModel
from llama_stack.apis.inspect import (
HealthInfo,
Inspect,
ListProvidersResponse,
ListRoutesResponse,
ProviderInfo,
RouteInfo,
VersionInfo,
)
from llama_stack.distribution.datatypes import StackRunConfig
from llama_stack.distribution.server.endpoints import get_all_api_endpoints
class DistributionInspectConfig(BaseModel):
run_config: StackRunConfig
async def get_provider_impl(config, deps):
impl = DistributionInspectImpl(config, deps)
await impl.initialize()
return impl
class DistributionInspectImpl(Inspect):
def __init__(self, config, deps):
self.config = config
self.deps = deps
async def initialize(self) -> None:
pass
async def list_providers(self) -> ListProvidersResponse:
run_config = self.config.run_config
ret = []
for api, providers in run_config.providers.items():
ret.extend(
[
ProviderInfo(
api=api,
provider_id=p.provider_id,
provider_type=p.provider_type,
)
for p in providers
]
)
return ListProvidersResponse(data=ret)
async def list_routes(self) -> ListRoutesResponse:
run_config = self.config.run_config
ret = []
all_endpoints = get_all_api_endpoints()
for api, endpoints in all_endpoints.items():
providers = run_config.providers.get(api.value, [])
ret.extend(
[
RouteInfo(
route=e.route,
method=e.method,
provider_types=[p.provider_type for p in providers],
)
for e in endpoints
]
)
return ListRoutesResponse(data=ret)
async def health(self) -> HealthInfo:
return HealthInfo(status="OK")
async def version(self) -> VersionInfo:
return VersionInfo(version=version("llama-stack"))
async def shutdown(self) -> None:
pass