phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 21:34:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into remove-deprecated-chat-completion

Browse source
This commit is contained in:
Matthew Farrellee 2025-10-02 18:19:06 -04:00
commit ee6a502289
209 changed files with 109297 additions and 8828 deletions
Download patch file Download diff file Expand all files Collapse all files

26
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -82,8 +82,7 @@ def _convert_to_vllm_tool_calls_in_response(
ToolCall(
call_id=call.id,
tool_name=call.function.name,
arguments=json.loads(call.function.arguments),
arguments_json=call.function.arguments,
arguments=call.function.arguments,
)
for call in tool_calls
]
@ -93,18 +92,6 @@ def _convert_to_vllm_tools_in_request(tools: list[ToolDefinition]) -> list[dict]
compat_tools = []
for tool in tools:
properties = {}
compat_required = []
if tool.parameters:
for tool_key, tool_param in tool.parameters.items():
properties[tool_key] = {"type": tool_param.param_type}
if tool_param.description:
properties[tool_key]["description"] = tool_param.description
if tool_param.default:
properties[tool_key]["default"] = tool_param.default
if tool_param.required:
compat_required.append(tool_key)
# The tool.tool_name can be a str or a BuiltinTool enum. If
# it's the latter, convert to a string.
tool_name = tool.tool_name
@ -116,10 +103,11 @@ def _convert_to_vllm_tools_in_request(tools: list[ToolDefinition]) -> list[dict]
"function": {
"name": tool_name,
"description": tool.description,
"parameters": {
"parameters": tool.input_schema
or {
"type": "object",
"properties": properties,
"required": compat_required,
"properties": {},
"required": [],
},
},
}
@ -154,7 +142,6 @@ def _process_vllm_chat_completion_end_of_stream(
for _index, tool_call_buf in sorted(tool_call_bufs.items()):
args_str = tool_call_buf.arguments or "{}"
try:
args = json.loads(args_str)
chunks.append(
ChatCompletionResponseStreamChunk(
event=ChatCompletionResponseEvent(
@ -163,8 +150,7 @@ def _process_vllm_chat_completion_end_of_stream(
tool_call=ToolCall(
call_id=tool_call_buf.call_id,
tool_name=tool_call_buf.tool_name,
arguments=args,
arguments_json=args_str,
arguments=args_str,
),
parse_status=ToolCallParseStatus.succeeded,
),

18
llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py
View file

@ -15,7 +15,6 @@ from llama_stack.apis.tools import (
ToolDef,
ToolGroup,
ToolInvocationResult,
ToolParameter,
ToolRuntime,
)
from llama_stack.core.request_headers import NeedsRequestProviderData
@ -57,13 +56,16 @@ class BingSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsReq
ToolDef(
name="web_search",
description="Search the web using Bing Search API",
parameters=[
ToolParameter(
name="query",
description="The query to search for",
parameter_type="string",
)
],
input_schema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to search for",
}
},
"required": ["query"],
},
)
]
)

18
llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py
View file

@ -14,7 +14,6 @@ from llama_stack.apis.tools import (
ToolDef,
ToolGroup,
ToolInvocationResult,
ToolParameter,
ToolRuntime,
)
from llama_stack.core.request_headers import NeedsRequestProviderData
@ -56,13 +55,16 @@ class BraveSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsRe
ToolDef(
name="web_search",
description="Search the web for information",
parameters=[
ToolParameter(
name="query",
description="The query to search for",
parameter_type="string",
)
],
input_schema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to search for",
}
},
"required": ["query"],
},
built_in_type=BuiltinTool.brave_search,
)
]

18
llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py
View file

@ -15,7 +15,6 @@ from llama_stack.apis.tools import (
ToolDef,
ToolGroup,
ToolInvocationResult,
ToolParameter,
ToolRuntime,
)
from llama_stack.core.request_headers import NeedsRequestProviderData
@ -56,13 +55,16 @@ class TavilySearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR
ToolDef(
name="web_search",
description="Search the web for information",
parameters=[
ToolParameter(
name="query",
description="The query to search for",
parameter_type="string",
)
],
input_schema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to search for",
}
},
"required": ["query"],
},
)
]
)

18
llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py
View file

@ -15,7 +15,6 @@ from llama_stack.apis.tools import (
ToolDef,
ToolGroup,
ToolInvocationResult,
ToolParameter,
ToolRuntime,
)
from llama_stack.core.request_headers import NeedsRequestProviderData
@ -57,13 +56,16 @@ class WolframAlphaToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR
ToolDef(
name="wolfram_alpha",
description="Query WolframAlpha for computational knowledge",
parameters=[
ToolParameter(
name="query",
description="The query to compute",
parameter_type="string",
)
],
input_schema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query to compute",
}
},
"required": ["query"],
},
)
]
)