mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
209a78b618
# What does this PR do? Adds OCI GenAI PaaS models for openai chat completion endpoints. ## Test Plan In an OCI tenancy with access to GenAI PaaS, perform the following steps: 1. Ensure you have IAM policies in place to use service (check docs included in this PR) 2. For local development, [setup OCI cli](https://docs.oracle.com/en-us/iaas/Content/API/SDKDocs/cliinstall.htm) and configure the CLI with your region, tenancy, and auth [here](https://docs.oracle.com/en-us/iaas/Content/API/SDKDocs/cliconfigure.htm) 3. Once configured, go through llama-stack setup and run llama-stack (uses config based auth) like: ```bash OCI_AUTH_TYPE=config_file \ OCI_CLI_PROFILE=CHICAGO \ OCI_REGION=us-chicago-1 \ OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..aaaaaaaa5...5a \ llama stack run oci ``` 4. Hit the `models` endpoint to list models after server is running: ```bash curl http://localhost:8321/v1/models | jq ... { "identifier": "meta.llama-4-scout-17b-16e-instruct", "provider_resource_id": "ocid1.generativeaimodel.oc1.us-chicago-1.am...q", "provider_id": "oci", "type": "model", "metadata": { "display_name": "meta.llama-4-scout-17b-16e-instruct", "capabilities": [ "CHAT" ], "oci_model_id": "ocid1.generativeaimodel.oc1.us-chicago-1.a...q" }, "model_type": "llm" }, ... ``` 5. Use the "display_name" field to use the model in a `/chat/completions` request: ```bash # Streaming result curl -X POST http://localhost:8321/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "meta.llama-4-scout-17b-16e-instruct", "stream": true, "temperature": 0.9, "messages": [ { "role": "system", "content": "You are a funny comedian. You can be crass." }, { "role": "user", "content": "Tell me a funny joke about programming." } ] }' # Non-streaming result curl -X POST http://localhost:8321/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "meta.llama-4-scout-17b-16e-instruct", "stream": false, "temperature": 0.9, "messages": [ { "role": "system", "content": "You are a funny comedian. You can be crass." }, { "role": "user", "content": "Tell me a funny joke about programming." } ] }' ``` 6. Try out other models from the `/models` endpoint.
108 lines
4.1 KiB
Python
108 lines
4.1 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from pathlib import Path
|
|
|
|
from llama_stack.core.datatypes import BuildProvider, Provider, ToolGroupInput
|
|
from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
|
|
from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
|
|
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
|
from llama_stack.providers.remote.inference.oci.config import OCIConfig
|
|
|
|
|
|
def get_distribution_template(name: str = "oci") -> DistributionTemplate:
|
|
providers = {
|
|
"inference": [BuildProvider(provider_type="remote::oci")],
|
|
"vector_io": [
|
|
BuildProvider(provider_type="inline::faiss"),
|
|
BuildProvider(provider_type="remote::chromadb"),
|
|
BuildProvider(provider_type="remote::pgvector"),
|
|
],
|
|
"safety": [BuildProvider(provider_type="inline::llama-guard")],
|
|
"agents": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"eval": [BuildProvider(provider_type="inline::meta-reference")],
|
|
"datasetio": [
|
|
BuildProvider(provider_type="remote::huggingface"),
|
|
BuildProvider(provider_type="inline::localfs"),
|
|
],
|
|
"scoring": [
|
|
BuildProvider(provider_type="inline::basic"),
|
|
BuildProvider(provider_type="inline::llm-as-judge"),
|
|
BuildProvider(provider_type="inline::braintrust"),
|
|
],
|
|
"tool_runtime": [
|
|
BuildProvider(provider_type="remote::brave-search"),
|
|
BuildProvider(provider_type="remote::tavily-search"),
|
|
BuildProvider(provider_type="inline::rag-runtime"),
|
|
BuildProvider(provider_type="remote::model-context-protocol"),
|
|
],
|
|
"files": [BuildProvider(provider_type="inline::localfs")],
|
|
}
|
|
|
|
inference_provider = Provider(
|
|
provider_id="oci",
|
|
provider_type="remote::oci",
|
|
config=OCIConfig.sample_run_config(),
|
|
)
|
|
|
|
vector_io_provider = Provider(
|
|
provider_id="faiss",
|
|
provider_type="inline::faiss",
|
|
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
|
)
|
|
|
|
files_provider = Provider(
|
|
provider_id="meta-reference-files",
|
|
provider_type="inline::localfs",
|
|
config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
|
)
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
]
|
|
|
|
return DistributionTemplate(
|
|
name=name,
|
|
distro_type="remote_hosted",
|
|
description="Use Oracle Cloud Infrastructure (OCI) Generative AI for running LLM inference with scalable cloud services",
|
|
container_image=None,
|
|
template_path=Path(__file__).parent / "doc_template.md",
|
|
providers=providers,
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [inference_provider],
|
|
"vector_io": [vector_io_provider],
|
|
"files": [files_provider],
|
|
},
|
|
default_tool_groups=default_tool_groups,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"OCI_AUTH_TYPE": (
|
|
"instance_principal",
|
|
"OCI authentication type (instance_principal or config_file)",
|
|
),
|
|
"OCI_REGION": (
|
|
"",
|
|
"OCI region (e.g., us-ashburn-1, us-chicago-1, us-phoenix-1, eu-frankfurt-1)",
|
|
),
|
|
"OCI_COMPARTMENT_OCID": (
|
|
"",
|
|
"OCI compartment ID for the Generative AI service",
|
|
),
|
|
"OCI_CONFIG_FILE_PATH": (
|
|
"~/.oci/config",
|
|
"OCI config file path (required if OCI_AUTH_TYPE is config_file)",
|
|
),
|
|
"OCI_CLI_PROFILE": (
|
|
"DEFAULT",
|
|
"OCI CLI profile name to use from config file",
|
|
),
|
|
},
|
|
)
|