Skip to content

models - ollama - init async client per request #433

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pgrayy merged 1 commit into from
Jul 12, 2025
Merged

models - ollama - init async client per request #433

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions src/strands/models/ollama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,14 +68,12 @@ def __init__(
ollama_client_args: Additional arguments for the Ollama client.
**model_config: Configuration options for the Ollama model.
"""
self.host = host
self.client_args = ollama_client_args or {}
self.config = OllamaModel.OllamaConfig(**model_config)

logger.debug("config=<%s> | initializing", self.config)

ollama_client_args = ollama_client_args if ollama_client_args is not None else {}

self.client = ollama.AsyncClient(host, **ollama_client_args)

@override
def update_config(self, **model_config: Unpack[OllamaConfig]) -> None: # type: ignore
"""Update the Ollama Model configuration with the provided arguments.
Expand Down Expand Up @@ -306,7 +304,8 @@ async def stream(
logger.debug("invoking model")
tool_requested = False

response = await self.client.chat(**request)
client = ollama.AsyncClient(self.host, **self.client_args)
response = await client.chat(**request)

logger.debug("got response from model")
yield self.format_chunk({"chunk_type": "message_start"})
Expand Down Expand Up @@ -346,7 +345,9 @@ async def structured_output(
formatted_request = self.format_request(messages=prompt)
formatted_request["format"] = output_model.model_json_schema()
formatted_request["stream"] = False
response = await self.client.chat(**formatted_request)

client = ollama.AsyncClient(self.host, **self.client_args)
response = await client.chat(**formatted_request)

try:
content = response.message.content.strip()
Expand Down
Loading