mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-20 13:48:40 +00:00
Nutanix AI distribution
This commit is contained in:
parent
f2ac4e2a94
commit
cb82b1ee9e
10 changed files with 237 additions and 14 deletions
|
|
@ -1,40 +0,0 @@
|
|||
# Nutanix Distribution
|
||||
|
||||
The `llamastack/distribution-nutanix` distribution consists of the following provider configurations.
|
||||
|
||||
|
||||
| **API** | **Inference** | **Agents** | **Memory** | **Safety** | **Telemetry** |
|
||||
|----------------- |--------------- |---------------- |-------------------------------------------------- |---------------- |---------------- |
|
||||
| **Provider(s)** | remote::nutanix | meta-reference | meta-reference | meta-reference | meta-reference |
|
||||
|
||||
|
||||
### Start the Distribution (Hosted remote)
|
||||
|
||||
> [!NOTE]
|
||||
> This assumes you have an hosted Nutanix AI endpoint and an API Key.
|
||||
|
||||
1. Clone the repo
|
||||
```
|
||||
git clone git@github.com:meta-llama/llama-stack.git
|
||||
cd llama-stack
|
||||
```
|
||||
|
||||
2. Config the model name
|
||||
|
||||
Please adjust the `NUTANIX_SUPPORTED_MODELS` variable at line 29 in `llama_stack/providers/adapters/inference/nutanix/nutanix.py` according to your deployment.
|
||||
|
||||
3. Build the distrbution
|
||||
```
|
||||
pip install -e .
|
||||
llama stack build --template nutanix --name ntnx --image-type conda
|
||||
```
|
||||
|
||||
4. Set the endpoint URL and API Key
|
||||
```
|
||||
llama stack configure ntnx
|
||||
```
|
||||
|
||||
5. Serve and enjoy!
|
||||
```
|
||||
llama stack run ntnx --port 174
|
||||
```
|
||||
15
distributions/nutanix/compose.yaml
Normal file
15
distributions/nutanix/compose.yaml
Normal file
|
|
@ -0,0 +1,15 @@
|
|||
services:
|
||||
llamastack:
|
||||
image: distribution-nutanix
|
||||
volumes:
|
||||
- ~/.llama:/root/.llama
|
||||
- ./run.yaml:/root/llamastack-run-nutanix.yaml
|
||||
ports:
|
||||
- "5000:5000"
|
||||
entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-nutanix.yaml"
|
||||
deploy:
|
||||
restart_policy:
|
||||
condition: on-failure
|
||||
delay: 3s
|
||||
max_attempts: 5
|
||||
window: 60s
|
||||
51
distributions/nutanix/run.yaml
Normal file
51
distributions/nutanix/run.yaml
Normal file
|
|
@ -0,0 +1,51 @@
|
|||
version: '2'
|
||||
image_name: nutanix
|
||||
docker_image: null
|
||||
conda_env: nutanix
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: nutanix
|
||||
provider_type: remote::nutanix
|
||||
config:
|
||||
url: https://ai.nutanix.com/api/v1
|
||||
api_key: ${env.NUTANIX_API_KEY}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nutanix}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: nutanix
|
||||
provider_type: remote::nutanix
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nutanix}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nutanix}/registry.db
|
||||
models: []
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
Loading…
Add table
Add a link
Reference in a new issue