phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-30 19:53:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama_models.llama3_1 -> llama_models.llama3

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-19 10:55:37 -07:00
parent f502716cf7
commit 38244c3161
27 changed files with 44 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_toolchain/inference/ollama/ollama.py
View file

@ -9,15 +9,17 @@ from typing import AsyncGenerator, Dict
import httpx
from llama_models.llama3_1.api.datatypes import (
from llama_models.llama3.api.datatypes import (
BuiltinTool,
CompletionMessage,
Message,
StopReason,
ToolCall,
)
from llama_models.llama3_1.api.tool_utils import ToolUtils
from llama_models.llama3.api.tool_utils import ToolUtils
from llama_models.sku_list import resolve_model
from ollama import AsyncClient
from llama_toolchain.distribution.datatypes import Api, ProviderSpec
from llama_toolchain.inference.api import (
ChatCompletionRequest,
@ -30,7 +32,6 @@ from llama_toolchain.inference.api import (
ToolCallDelta,
ToolCallParseStatus,
)
from ollama import AsyncClient
from .config import OllamaImplConfig
@ -64,10 +65,10 @@ class OllamaInference(Inference):
async def initialize(self) -> None:
try:
await self.client.ps()
except httpx.ConnectError:
except httpx.ConnectError as e:
raise RuntimeError(
"Ollama Server is not running, start it using `ollama serve` in a separate terminal"
)
) from e
async def shutdown(self) -> None:
pass