mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-16 14:38:00 +00:00
Some checks failed
Integration Tests (Replay) / discover-tests (push) Successful in 4s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 20s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 21s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 15s
Test Llama Stack Build / build-single-provider (push) Failing after 11s
Test Llama Stack Build / generate-matrix (push) Successful in 14s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 20s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 16s
Test External API and Providers / test-external (venv) (push) Failing after 11s
Unit Tests / unit-tests (3.12) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 20s
Python Package Build Test / build (3.12) (push) Failing after 23s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 25s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 18s
Unit Tests / unit-tests (3.13) (push) Failing after 9s
Update ReadTheDocs / update-readthedocs (push) Failing after 9s
Python Package Build Test / build (3.13) (push) Failing after 21s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 17s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 51s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 58s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 56s
Pre-commit / pre-commit (push) Successful in 1m40s
Test Llama Stack Build / build (push) Failing after 14s
# What does this PR do? Fix the NVIDIA inference docs by updating API methods, model IDs, and embedding example. ## Test Plan N/A
2 KiB
2 KiB
NVIDIA Inference Provider for LlamaStack
This provider enables running inference using NVIDIA NIM.
Features
- Endpoints for completions, chat completions, and embeddings for registered models
Getting Started
Prerequisites
- LlamaStack with NVIDIA configuration
- Access to NVIDIA NIM deployment
- NIM for model to use for inference is deployed
Setup
Build the NVIDIA environment:
llama stack build --distro nvidia --image-type venv
Basic Usage using the LlamaStack Python Client
Initialize the client
import os
os.environ["NVIDIA_API_KEY"] = (
"" # Required if using hosted NIM endpoint. If self-hosted, not required.
)
os.environ["NVIDIA_BASE_URL"] = "http://nim.test" # NIM URL
from llama_stack.core.library_client import LlamaStackAsLibraryClient
client = LlamaStackAsLibraryClient("nvidia")
client.initialize()
Create Completion
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={
"max_tokens": 50,
},
)
print(f"Response: {response.content}")
Create Chat Completion
response = client.inference.chat_completion(
model_id="meta-llama/Llama-3.1-8B-Instruct",
messages=[
{
"role": "system",
"content": "You must respond to each message with only one word",
},
{
"role": "user",
"content": "Complete the sentence using one word: Roses are red, violets are:",
},
],
stream=False,
sampling_params={
"max_tokens": 50,
},
)
print(f"Response: {response.completion_message.content}")
Create Embeddings
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}")