From b6500974eca169ed053a7b95408ac756c160c004 Mon Sep 17 00:00:00 2001
From: Kai Wu <kaiwu@meta.com>
Date: Tue, 3 Dec 2024 20:11:19 -0800
Subject: [PATCH] removed assertion in ollama.py and fixed typo in the readme
 (#563)

# What does this PR do?
1. removed [incorrect
assertion](https://github.com/meta-llama/llama-stack/blob/435f34b05e84f1747b28570234f25878cf0b31c4/llama_stack/providers/remote/inference/ollama/ollama.py#L183)
in ollama.py
2. fixed a typo in [this
line](https://github.com/meta-llama/llama-stack/blob/435f34b05e84f1747b28570234f25878cf0b31c4/docs/source/distributions/importing_as_library.md?plain=1#L24),
as `model=` should be `model_id=` .

- [x] Addresses issue
([#issue562](https://github.com/meta-llama/llama-stack/issues/562))


## Test Plan

tested with code:

```python
import asyncio
import os

# pip install aiosqlite ollama faiss
from llama_stack_client.lib.direct.direct import LlamaStackDirectClient
from llama_stack_client.types import SystemMessage, UserMessage


async def main():
    os.environ["INFERENCE_MODEL"] = "meta-llama/Llama-3.2-1B-Instruct"
    client = await LlamaStackDirectClient.from_template("ollama")
    await client.initialize()
    response = await client.models.list()
    print(response)
    model_name = response[0].identifier
    response = await client.inference.chat_completion(
        messages=[
            SystemMessage(content="You are a friendly assistant.", role="system"),
            UserMessage(
                content="hello world, write me a 2 sentence poem about the moon",
                role="user",
            ),
        ],
        model_id=model_name,
        stream=False,
    )
    print("\nChat completion response:")
    print(response, type(response))


asyncio.run(main())

```
OUTPUT:
```
python test.py
Using template ollama with config:
apis:
- agents
- inference
- memory
- safety
- telemetry
conda_env: ollama
datasets: []
docker_image: null
eval_tasks: []
image_name: ollama
memory_banks: []
metadata_store:
  db_path: /Users/kaiwu/.llama/distributions/ollama/registry.db
  namespace: null
  type: sqlite
models:
- metadata: {}
  model_id: meta-llama/Llama-3.2-1B-Instruct
  provider_id: ollama
  provider_model_id: null
providers:
  agents:
  - config:
      persistence_store:
        db_path:
/Users/kaiwu/.llama/distributions/ollama/agents_store.db
        namespace: null
        type: sqlite
    provider_id: meta-reference
    provider_type: inline::meta-reference
  inference:
  - config:
      url: http://localhost:11434
    provider_id: ollama
    provider_type: remote::ollama
  memory:
  - config:
      kvstore:
        db_path:
/Users/kaiwu/.llama/distributions/ollama/faiss_store.db
        namespace: null
        type: sqlite
    provider_id: faiss
    provider_type: inline::faiss
  safety:
  - config: {}
    provider_id: llama-guard
    provider_type: inline::llama-guard
  telemetry:
  - config: {}
    provider_id: meta-reference
    provider_type: inline::meta-reference
scoring_fns: []
shields: []
version: '2'

[Model(identifier='meta-llama/Llama-3.2-1B-Instruct', provider_resource_id='llama3.2:1b-instruct-fp16', provider_id='ollama', type='model', metadata={})]

Chat completion response:
completion_message=CompletionMessage(role='assistant', content='Here is a short poem about the moon:\n\nThe moon glows bright in the midnight sky,\nA silver crescent shining, catching the eye.', stop_reason=<StopReason.end_of_turn: 'end_of_turn'>, tool_calls=[]) logprobs=None <class 'llama_stack.apis.inference.inference.ChatCompletionResponse'>
```

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---
 docs/source/distributions/importing_as_library.md       | 2 +-
 llama_stack/providers/remote/inference/ollama/ollama.py | 1 -
 2 files changed, 1 insertion(+), 2 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..f89629afc 100644
--- a/llama_stack/providers/remote/inference/ollama/ollama.py
+++ b/llama_stack/providers/remote/inference/ollama/ollama.py
@@ -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,