diff --git a/examples/README.md b/examples/README.md index b55fd4e1..50cd2508 100644 --- a/examples/README.md +++ b/examples/README.md @@ -6,6 +6,8 @@ Run the examples in this directory with: python3 examples/.py ``` +See [ollama/docs/api.md](https://github.com/ollama/ollama/blob/main/docs/api.md) for full API documentation + ### Chat - Chat with a model - [chat.py](chat.py) - [async-chat.py](async-chat.py) @@ -50,12 +52,8 @@ Requirement: `pip install tqdm` ### Ollama Create - Create a model from a Modelfile -```python -python create.py -``` - [create.py](create.py) -See [ollama/docs/modelfile.md](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) for more information on the Modelfile format. ### Ollama Embed - Generate embeddings with a model diff --git a/examples/create.py b/examples/create.py old mode 100644 new mode 100755 index d4b5b1f3..5e59976e --- a/examples/create.py +++ b/examples/create.py @@ -1,30 +1,5 @@ -import sys +from ollama import Client -from ollama import create - - -args = sys.argv[1:] -if len(args) == 2: - # create from local file - path = args[1] -else: - print('usage: python create.py ') - sys.exit(1) - -# TODO: update to real Modelfile values -modelfile = f""" -FROM {path} -""" -example_modelfile = """ -FROM llama3.2 -# sets the temperature to 1 [higher is more creative, lower is more coherent] -PARAMETER temperature 1 -# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token -PARAMETER num_ctx 4096 - -# sets a custom system message to specify the behavior of the chat assistant -SYSTEM You are Mario from super mario bros, acting as an assistant. -""" - -for response in create(model=args[0], modelfile=modelfile, stream=True): - print(response['status']) +client = Client() +response = client.create(model='my-assistant', from_='llama3.2', stream=False) +print(response.status)