From 98c97d310468f5d8a9442b51ceab7b6d89c5eec5 Mon Sep 17 00:00:00 2001 From: Kai Wu Date: Tue, 3 Dec 2024 16:15:47 -0800 Subject: [PATCH] removed assertion in ollama.py and fixed typo in the readme --- docs/source/distributions/importing_as_library.md | 2 +- llama_stack/providers/remote/inference/ollama/ollama.py | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/docs/source/distributions/importing_as_library.md b/docs/source/distributions/importing_as_library.md index 815660fd4..7e15062df 100644 --- a/docs/source/distributions/importing_as_library.md +++ b/docs/source/distributions/importing_as_library.md @@ -21,7 +21,7 @@ print(response) ```python response = await client.inference.chat_completion( messages=[UserMessage(content="What is the capital of France?", role="user")], - model="Llama3.1-8B-Instruct", + model_id="Llama3.1-8B-Instruct", stream=False, ) print("\nChat completion response:") diff --git a/llama_stack/providers/remote/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py index 74c0b8601..c2d7a0660 100644 --- a/llama_stack/providers/remote/inference/ollama/ollama.py +++ b/llama_stack/providers/remote/inference/ollama/ollama.py @@ -13,13 +13,13 @@ from llama_models.datatypes import CoreModelId from llama_models.llama3.api.chat_format import ChatFormat from llama_models.llama3.api.datatypes import Message from llama_models.llama3.api.tokenizer import Tokenizer -from ollama import AsyncClient from llama_stack.providers.utils.inference.model_registry import ( build_model_alias, build_model_alias_with_just_provider_model_id, ModelRegistryHelper, ) +from ollama import AsyncClient from llama_stack.apis.inference import * # noqa: F403 from llama_stack.providers.datatypes import ModelsProtocolPrivate @@ -180,7 +180,6 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate): async def _nonstream_completion(self, request: CompletionRequest) -> AsyncGenerator: params = await self._get_params(request) r = await self.client.generate(**params) - assert isinstance(r, dict) choice = OpenAICompatCompletionChoice( finish_reason=r["done_reason"] if r["done"] else None,