phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 20:27:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Updating files/content response to return additional fields

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-08-06 16:55:14 -04:00
parent e12524af85
commit a19c16428f
143 changed files with 6907 additions and 15104 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/gemini/models.py
View file

@ -13,7 +13,9 @@ LLM_MODEL_IDS = [
"gemini-1.5-flash",
"gemini-1.5-pro",
"gemini-2.0-flash",
"gemini-2.0-flash-lite",
"gemini-2.5-flash",
"gemini-2.5-flash-lite",
"gemini-2.5-pro",
]

16
llama_stack/providers/remote/inference/nvidia/NVIDIA.md
View file

@ -42,8 +42,8 @@ client.initialize()
### Create Completion
```python
response = client.completion(
model_id="meta-llama/Llama-3.1-8b-Instruct",
response = client.inference.completion(
model_id="meta-llama/Llama-3.1-8B-Instruct",
content="Complete the sentence using one word: Roses are red, violets are :",
stream=False,
sampling_params={
@ -56,8 +56,8 @@ print(f"Response: {response.content}")
### Create Chat Completion
```python
response = client.chat_completion(
model_id="meta-llama/Llama-3.1-8b-Instruct",
response = client.inference.chat_completion(
model_id="meta-llama/Llama-3.1-8B-Instruct",
messages=[
{
"role": "system",
@ -78,8 +78,10 @@ print(f"Response: {response.completion_message.content}")
### Create Embeddings
```python
response = client.embeddings(
model_id="meta-llama/Llama-3.1-8b-Instruct", contents=["foo", "bar", "baz"]
response = client.inference.embeddings(
model_id="nvidia/llama-3.2-nv-embedqa-1b-v2",
contents=["What is the capital of France?"],
task_type="query",
)
print(f"Embeddings: {response.embeddings}")
```
```

3
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -112,7 +112,8 @@ class OllamaInferenceAdapter(
@property
def openai_client(self) -> AsyncOpenAI:
if self._openai_client is None:
self._openai_client = AsyncOpenAI(base_url=f"{self.config.url}/v1", api_key="ollama")
url = self.config.url.rstrip("/")
self._openai_client = AsyncOpenAI(base_url=f"{url}/v1", api_key="ollama")
return self._openai_client
async def initialize(self) -> None: