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 17:07:59 +01:00 · 2025-02-13 17:07:59 +01:00 · 418645696a
commit 418645696a
parent dd1a366347
6 changed files with 94 additions and 12 deletions
--- a/llama_stack/distribution/inspect.py
+++ b/llama_stack/distribution/inspect.py
@ -82,3 +82,6 @@ class DistributionInspectImpl(Inspect):

    async def version(self) -> VersionInfo:
        return VersionInfo(version=version("llama-stack"))
+
+    async def shutdown(self) -> None:
+        pass
--- a/llama_stack/distribution/routers/routing_tables.py
+++ b/llama_stack/distribution/routers/routing_tables.py
@ -537,3 +537,6 @@ class ToolGroupsRoutingTable(CommonRoutingTableImpl, ToolGroups):
        for tool in tools:
            await self.unregister_object(tool)
        await self.unregister_object(tool_group)
+
+    async def shutdown(self) -> None:
+        pass
--- a/llama_stack/distribution/server/server.py
+++ b/llama_stack/distribution/server/server.py
@ -7,6 +7,7 @@
 import argparse
 import asyncio
 import functools
+import logging
 import inspect
 import json
 import os
@ -52,6 +53,9 @@ from .endpoints import get_all_api_endpoints

 REPO_ROOT = Path(__file__).parent.parent.parent.parent

+logging.basicConfig(level=logging.INFO, format="%(levelname)s %(asctime)s %(name)s:%(lineno)d: %(message)s")
+logger = logging.getLogger(__name__)
+

 def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
    log = file if hasattr(file, "write") else sys.stderr
@ -112,21 +116,69 @@ def translate_exception(exc: Exception) -> Union[HTTPException, RequestValidatio
        )


-def handle_sigint(app, *args, **kwargs):
-    print("SIGINT or CTRL-C detected. Exiting gracefully...")
+def handle_signal(app, signum, _) -> None:
+    """
+    Handle incoming signals and initiate a graceful shutdown of the application.

-    async def run_shutdown():
-        for impl in app.__llama_stack_impls__.values():
-            print(f"Shutting down {impl}")
-            await impl.shutdown()
+    This function is intended to be used as a signal handler for various signals
+    (e.g., SIGINT, SIGTERM). Upon receiving a signal, it will print a message
+    indicating the received signal and initiate a shutdown process.

-    asyncio.run(run_shutdown())
+    Args:
+        app: The application instance containing implementations to be shut down.
+        signum (int): The signal number received.
+        frame: The current stack frame (not used in this function).

-    loop = asyncio.get_event_loop()
-    for task in asyncio.all_tasks(loop):
-        task.cancel()
+    The shutdown process involves:
+        - Shutting down all implementations registered in the application.
+        - Gathering all running asyncio tasks.
+        - Cancelling all gathered tasks.
+        - Waiting for all tasks to finish.
+        - Stopping the event loop.

-    loop.stop()
+    Note:
+        This function schedules the shutdown process as an asyncio task and does
+        not block the current execution.
+    """
+    signame = signal.Signals(signum).name
+    print(f"Received signal {signame} ({signum}). Exiting gracefully...")
+
+    async def shutdown():
+        try:
+            # Gracefully shut down implementations
+            for impl in app.__llama_stack_impls__.values():
+                impl_name = impl.__class__.__name__
+                logger.info("Shutting down %s", impl_name)
+                try:
+                    if hasattr(impl, "shutdown"):
+                        await asyncio.wait_for(impl.shutdown(), timeout=5)
+                    else:
+                        logger.warning("No shutdown method for %s", impl_name)
+                except asyncio.TimeoutError:
+                    logger.exception("Shutdown timeout for %s ", impl_name, exc_info=True)
+                except Exception as e:
+                    logger.exception("Failed to shutdown %s: %s", impl_name, {e})
+
+            # Gather all running tasks
+            loop = asyncio.get_running_loop()
+            tasks = [task for task in asyncio.all_tasks(loop) if task is not asyncio.current_task()]
+
+            # Cancel all tasks
+            for task in tasks:
+                task.cancel()
+
+            # Wait for all tasks to finish
+            try:
+                await asyncio.wait_for(asyncio.gather(*tasks, return_exceptions=True), timeout=10)
+            except asyncio.TimeoutError:
+                logger.exception("Timeout while waiting for tasks to finish")
+        except asyncio.CancelledError:
+            pass
+        finally:
+            loop.stop()
+
+    loop = asyncio.get_running_loop()
+    loop.create_task(shutdown())


@asynccontextmanager
@ -386,7 +438,8 @@ def main():
    print("")
    app.exception_handler(RequestValidationError)(global_exception_handler)
    app.exception_handler(Exception)(global_exception_handler)
-    signal.signal(signal.SIGINT, functools.partial(handle_sigint, app))
+    signal.signal(signal.SIGINT, functools.partial(handle_signal, app))
+    signal.signal(signal.SIGTERM, functools.partial(handle_signal, app))

    app.__llama_stack_impls__ = impls

--- a/llama_stack/providers/inline/agents/meta_reference/agents.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agents.py
@ -212,3 +212,6 @@ class MetaReferenceAgentsImpl(Agents):

    async def delete_agent(self, agent_id: str) -> None:
        await self.persistence_store.delete(f"agent:{agent_id}")
+
+    async def shutdown(self) -> None:
+        pass
--- a/pyproject.toml
+++ b/pyproject.toml
@ -46,6 +46,8 @@ dev = [
    "types-requests",
    "types-setuptools",
    "pre-commit",
+    "uvicorn",
+    "fastapi",
 ]
 docs = [
    "sphinx-autobuild",
--- a/uv.lock
+++ b/uv.lock
@ -431,6 +431,20 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/7b/8f/c4d9bafc34ad7ad5d8dc16dd1347ee0e507a52c3adb6bfa8887e1c6a26ba/executing-2.2.0-py2.py3-none-any.whl", hash = "sha256:11387150cad388d62750327a53d3339fad4888b39a6fe233c3afbb54ecffd3aa", size = 26702 },
 ]

+[[package]]
+name = "fastapi"
+version = "0.115.8"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pydantic" },
+    { name = "starlette" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a2/b2/5a5dc4affdb6661dea100324e19a7721d5dc524b464fe8e366c093fd7d87/fastapi-0.115.8.tar.gz", hash = "sha256:0ce9111231720190473e222cdf0f07f7206ad7e53ea02beb1d2dc36e2f0741e9", size = 295403 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8f/7d/2d6ce181d7a5f51dedb8c06206cbf0ec026a99bf145edd309f9e17c3282f/fastapi-0.115.8-py3-none-any.whl", hash = "sha256:753a96dd7e036b34eeef8babdfcfe3f28ff79648f86551eb36bfc1b0bf4a8cbf", size = 94814 },
+]
+
 [[package]]
 name = "fastjsonschema"
 version = "2.21.1"
@ -724,6 +738,7 @@ dependencies = [
 [package.optional-dependencies]
 dev = [
    { name = "black" },
+    { name = "fastapi" },
    { name = "nbval" },
    { name = "pre-commit" },
    { name = "pytest" },
@ -731,6 +746,7 @@ dev = [
    { name = "ruff" },
    { name = "types-requests" },
    { name = "types-setuptools" },
+    { name = "uvicorn" },
 ]
 docs = [
    { name = "myst-parser" },
@ -748,6 +764,7 @@ docs = [
 requires-dist = [
    { name = "black", marker = "extra == 'dev'" },
    { name = "blobfile" },
+    { name = "fastapi", marker = "extra == 'dev'" },
    { name = "fire" },
    { name = "httpx" },
    { name = "huggingface-hub" },
@ -776,6 +793,7 @@ requires-dist = [
    { name = "termcolor" },
    { name = "types-requests", marker = "extra == 'dev'" },
    { name = "types-setuptools", marker = "extra == 'dev'" },
+    { name = "uvicorn", marker = "extra == 'dev'" },
 ]

 [[package]]