phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 10:10:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into chroma

Browse source
This commit is contained in:
Bwook (Byoungwook) Kim 2025-08-11 10:06:35 +09:00 • committed by GitHub
commit d460fd64b4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 1419 additions and 88 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}")
```
```