ollama

Ollama supports the OpenAI client, allowing you to use the openai-generic provider with an overridden base_url.

Note that to call Ollama, you must use its OpenAI-compatible /v1 endpoint. See Ollama’s OpenAI compatibility documentation.

You can try out BAML with Ollama at promptfiddle.com, by running OLLAMA_ORIGINS='*' ollama serve. Learn more in here
BAML
1client<llm> MyClient {
2  provider "openai-generic"
3  options {
4    base_url "http://localhost:11434/v1"
5    model llama3
6  }
7}

The options are passed through directly to the API, barring a few. Here’s a shorthand of the options:

Non-forwarded options

base_url
string

The base URL for the API. Default: http://localhost:11434/v1

Note the /v1 at the end of the URL. See Ollama’s OpenAI compatability

default_role
string

The default role for any prompts that don’t specify a role. Default: system

We don’t have any checks for this field, you can pass any string you wish.

headers
object

Additional headers to send with the request.

Example:

BAML
1client<llm> MyClient {
2  provider ollama
3  options {
4    model "llama3"
5    headers {
6      "X-My-Header" "my-value"
7    }
8  }
9}
allowed_role_metadata
string[]

Which role metadata should we forward to the API? Default: []

For example you can set this to ["foo", "bar"] to forward the cache policy to the API.

If you do not set allowed_role_metadata, we will not forward any role metadata to the API even if it is set in the prompt.

Then in your prompt you can use something like:

1client<llm> Foo {
2  provider openai
3  options {
4    allowed_role_metadata: ["foo", "bar"]
5  }
6}
7
8client<llm> FooWithout {
9  provider openai
10  options {
11  }
12}
13template_string Foo() #"
14  {{ _.role('user', foo={"type": "ephemeral"}, bar="1", cat=True) }}
15  This will be have foo and bar, but not cat metadata. But only for Foo, not FooWithout.
16  {{ _.role('user') }}
17  This will have none of the role metadata for Foo or FooWithout.
18"#

You can use the playground to see the raw curl request to see what is being sent to the API.

supports_streaming
boolean

Whether the internal LLM client should use the streaming API. Default: true

Then in your prompt you can use something like:

1client<llm> MyClientWithoutStreaming {
2  provider anthropic
3  options {
4    model claude-3-haiku-20240307
5    api_key env.ANTHROPIC_API_KEY
6    max_tokens 1000
7    supports_streaming false
8  }
9}
10
11function MyFunction() -> string {
12  client MyClientWithoutStreaming
13  prompt #"Write a short story"#
14}
1# This will be streamed from your python code perspective, 
2# but under the hood it will call the non-streaming HTTP API
3# and then return a streamable response with a single event
4b.stream.MyFunction()
5
6# This will work exactly the same as before
7b.MyFunction()

Forwarded options

messages
DO NOT USE

BAML will auto construct this field for you from the prompt

stream
DO NOT USE

BAML will auto construct this field for you based on how you call the client in your code

model
string

The model to use.

ModelDescription
llama3Meta Llama 3: The most capable openly available LLM to date
qwen2Qwen2 is a new series of large language models from Alibaba group
phi3Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft
ayaAya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
mistralThe 7B model released by Mistral AI, updated to version 0.3.
gemmaGemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
mixtralA set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

For the most up-to-date list of models supported by Ollama, see their Model Library.

To use a specific version you would do: "mixtral:8x22b"