llama-stack 0.4.3__py3-none-any.whl → 0.5.0__py3-none-any.whl

llama_stack/core/store/registry.py

@@ -190,7 +190,7 @@ class CachedDiskDistributionRegistry(DiskDistributionRegistry):
 
 
 async def create_dist_registry(
-    metadata_store: KVStoreReference, image_name: str
+    metadata_store: KVStoreReference, distro_name: str
 ) -> tuple[CachedDiskDistributionRegistry, KVStore]:
     # instantiate kvstore for storing and retrieving distribution metadata
     dist_kvstore = await kvstore_impl(metadata_store)

llama_stack/core/utils/exec.py

@@ -17,10 +17,10 @@ from llama_stack.log import get_logger
 log = get_logger(name=__name__, category="core")
 
 
-def formulate_run_args(image_type: str, image_name: str) -> list:
+def formulate_run_args(image_type: str, distro_name: str) -> list:
     # Only venv is supported now
     current_venv = os.environ.get("VIRTUAL_ENV")
-    env_name = image_name or current_venv
+    env_name = distro_name or current_venv
     if not env_name:
         cprint(
             "No current virtual environment detected, please specify a virtual environment name with --image-name",

llama_stack/core/utils/type_inspection.py

@@ -36,10 +36,24 @@ def is_unwrapped_body_param(param_type: Any) -> bool:
         base_type = args[0]
         metadata = args[1:]
 
-        # Look for Body annotation with embed=False
+        # Look for Body annotation; treat embed=None (default) as unwrapped
         # Body() returns a FieldInfo object, so we check for that type and the embed attribute
         for item in metadata:
-            if isinstance(item, FieldInfo) and hasattr(item, "embed") and not item.embed:
+            if isinstance(item, FieldInfo) and hasattr(item, "embed") and item.embed is not True:
                 return inspect.isclass(base_type) and issubclass(base_type, BaseModel)
 
     return False
+
+
+def is_body_param(param_type: Any) -> bool:
+    """
+    Check if a parameter type represents a body parameter (Annotated with Body()).
+    """
+    if get_origin(param_type) is typing.Annotated:
+        args = get_args(param_type)
+        base_type = args[0]
+        metadata = args[1:]
+        for item in metadata:
+            if isinstance(item, FieldInfo):
+                return inspect.isclass(base_type) and issubclass(base_type, BaseModel)
+    return False

llama_stack/distributions/dell/config.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: dell
+distro_name: dell
 apis:
 - agents
 - datasetio
@@ -108,6 +108,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}

llama_stack/distributions/dell/doc_template.md

@@ -0,0 +1,209 @@
+---
+orphan: true
+---
+
+# Dell Distribution of Llama Stack
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+
+self
+```
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+You can use this distribution if you have GPUs and want to run an independent TGI or Dell Enterprise Hub container for running inference.
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+
+## Setting up Inference server using Dell Enterprise Hub's custom TGI container.
+
+NOTE: This is a placeholder to run inference with TGI. This will be updated to use [Dell Enterprise Hub's containers](https://dell.huggingface.co/authenticated/models) once verified.
+
+```bash
+export INFERENCE_PORT=8181
+export DEH_URL=http://0.0.0.0:$INFERENCE_PORT
+export INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
+export CHROMADB_HOST=localhost
+export CHROMADB_PORT=6601
+export CHROMA_URL=http://$CHROMADB_HOST:$CHROMADB_PORT
+export CUDA_VISIBLE_DEVICES=0
+export LLAMA_STACK_PORT=8321
+
+docker run --rm -it \
+  --pull always \
+  --network host \
+  -v $HOME/.cache/huggingface:/data \
+  -e HF_TOKEN=$HF_TOKEN \
+  -p $INFERENCE_PORT:$INFERENCE_PORT \
+  --gpus $CUDA_VISIBLE_DEVICES \
+  ghcr.io/huggingface/text-generation-inference \
+  --dtype bfloat16 \
+  --usage-stats off \
+  --sharded false \
+  --cuda-memory-fraction 0.7 \
+  --model-id $INFERENCE_MODEL \
+  --port $INFERENCE_PORT --hostname 0.0.0.0
+```
+
+If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a TGI with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
+
+```bash
+export SAFETY_INFERENCE_PORT=8282
+export DEH_SAFETY_URL=http://0.0.0.0:$SAFETY_INFERENCE_PORT
+export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+export CUDA_VISIBLE_DEVICES=1
+
+docker run --rm -it \
+  --pull always \
+  --network host \
+  -v $HOME/.cache/huggingface:/data \
+  -e HF_TOKEN=$HF_TOKEN \
+  -p $SAFETY_INFERENCE_PORT:$SAFETY_INFERENCE_PORT \
+  --gpus $CUDA_VISIBLE_DEVICES \
+  ghcr.io/huggingface/text-generation-inference \
+  --dtype bfloat16 \
+  --usage-stats off \
+  --sharded false \
+  --cuda-memory-fraction 0.7 \
+  --model-id $SAFETY_MODEL \
+  --hostname 0.0.0.0 \
+  --port $SAFETY_INFERENCE_PORT
+```
+
+## Dell distribution relies on ChromaDB for vector database usage
+
+You can start a chroma-db easily using docker.
+```bash
+# This is where the indices are persisted
+mkdir -p $HOME/chromadb
+
+podman run --rm -it \
+  --network host \
+  --name chromadb \
+  -v $HOME/chromadb:/chroma/chroma \
+  -e IS_PERSISTENT=TRUE \
+  chromadb/chroma:latest \
+  --port $CHROMADB_PORT \
+  --host $CHROMADB_HOST
+```
+
+## Running Llama Stack
+
+Now you are ready to run Llama Stack with TGI as the inference provider. You can do this via Conda (build code) or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+docker run -it \
+  --pull always \
+  --network host \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v $HOME/.llama:/root/.llama \
+  # NOTE: mount the llama-stack directory if testing local changes else not needed
+  -v $HOME/git/llama-stack:/app/llama-stack-source \
+  # localhost/distribution-dell:dev if building / testing locally
+  -e INFERENCE_MODEL=$INFERENCE_MODEL \
+  -e DEH_URL=$DEH_URL \
+  -e CHROMA_URL=$CHROMA_URL \
+  llamastack/distribution-{{ name }}\
+  --port $LLAMA_STACK_PORT
+
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+# You need a local checkout of llama-stack to run this, get it using
+# git clone https://github.com/meta-llama/llama-stack.git
+cd /path/to/llama-stack
+
+export SAFETY_INFERENCE_PORT=8282
+export DEH_SAFETY_URL=http://0.0.0.0:$SAFETY_INFERENCE_PORT
+export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+
+docker run \
+  -it \
+  --pull always \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v $HOME/.llama:/root/.llama \
+  -v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-config.yaml \
+  -e INFERENCE_MODEL=$INFERENCE_MODEL \
+  -e DEH_URL=$DEH_URL \
+  -e SAFETY_MODEL=$SAFETY_MODEL \
+  -e DEH_SAFETY_URL=$DEH_SAFETY_URL \
+  -e CHROMA_URL=$CHROMA_URL \
+  llamastack/distribution-{{ name }} \
+  --config /root/my-config.yaml \
+  --port $LLAMA_STACK_PORT
+```
+
+### Via Docker with Custom Run Configuration
+
+You can also run the Docker container with a custom run configuration file by mounting it into the container:
+
+```bash
+# Set the path to your custom config.yaml file
+CUSTOM_RUN_CONFIG=/path/to/your/custom-config.yaml
+
+docker run -it \
+  --pull always \
+  --network host \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v $HOME/.llama:/root/.llama \
+  -v $CUSTOM_RUN_CONFIG:/app/custom-config.yaml \
+  -e RUN_CONFIG_PATH=/app/custom-config.yaml \
+  -e INFERENCE_MODEL=$INFERENCE_MODEL \
+  -e DEH_URL=$DEH_URL \
+  -e CHROMA_URL=$CHROMA_URL \
+  llamastack/distribution-{{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+**Note**: The run configuration must be mounted into the container before it can be used. The `-v` flag mounts your local file into the container, and the `RUN_CONFIG_PATH` environment variable tells the entrypoint script which configuration to use.
+
+{% if run_configs %}
+Available run configurations for this distribution:
+{% for config in run_configs %}
+- `{{ config }}`
+{% endfor %}
+{% endif %}
+
+### Via Conda
+
+Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
+
+```bash
+llama stack list-deps {{ name }} | xargs -L1 pip install
+INFERENCE_MODEL=$INFERENCE_MODEL \
+DEH_URL=$DEH_URL \
+CHROMA_URL=$CHROMA_URL \
+llama stack run {{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+INFERENCE_MODEL=$INFERENCE_MODEL \
+DEH_URL=$DEH_URL \
+SAFETY_MODEL=$SAFETY_MODEL \
+DEH_SAFETY_URL=$DEH_SAFETY_URL \
+CHROMA_URL=$CHROMA_URL \
+llama stack run ./run-with-safety.yaml \
+  --port $LLAMA_STACK_PORT
+```

llama_stack/distributions/dell/run-with-safety.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: dell
+distro_name: dell
 apis:
 - agents
 - datasetio
@@ -112,6 +112,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}

llama_stack/distributions/nvidia/config.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: nvidia
+distro_name: nvidia
 apis:
 - agents
 - datasetio
@@ -102,6 +102,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models: []
   shields: []

llama_stack/distributions/nvidia/doc_template.md

@@ -0,0 +1,170 @@
+---
+orphan: true
+---
+# NVIDIA Distribution
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+{% if default_models %}
+### Models
+
+The following models are available by default:
+
+{% for model in default_models %}
+- `{{ model.model_id }} {{ model.doc_string }}`
+{% endfor %}
+{% endif %}
+
+
+## Prerequisites
+### NVIDIA API Keys
+
+Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/). Use this key for the `NVIDIA_API_KEY` environment variable.
+
+### Deploy NeMo Microservices Platform
+The NVIDIA NeMo microservices platform supports end-to-end microservice deployment of a complete AI flywheel on your Kubernetes cluster through the NeMo Microservices Helm Chart. Please reference the [NVIDIA NeMo Microservices documentation](https://docs.nvidia.com/nemo/microservices/latest/about/index.html) for platform prerequisites and instructions to install and deploy the platform.
+
+## Supported Services
+Each Llama Stack API corresponds to a specific NeMo microservice. The core microservices (Customizer, Evaluator, Guardrails) are exposed by the same endpoint. The platform components (Data Store) are each exposed by separate endpoints.
+
+### Inference: NVIDIA NIM
+NVIDIA NIM is used for running inference with registered models. There are two ways to access NVIDIA NIMs:
+  1. Hosted (default): Preview APIs hosted at https://integrate.api.nvidia.com (Requires an API key)
+  2. Self-hosted: NVIDIA NIMs that run on your own infrastructure.
+
+The deployed platform includes the NIM Proxy microservice, which is the service that provides to access your NIMs (for example, to run inference on a model). Set the `NVIDIA_BASE_URL` environment variable to use your NVIDIA NIM Proxy deployment.
+
+### Datasetio API: NeMo Data Store
+The NeMo Data Store microservice serves as the default file storage solution for the NeMo microservices platform. It exposts APIs compatible with the Hugging Face Hub client (`HfApi`), so you can use the client to interact with Data Store. The `NVIDIA_DATASETS_URL` environment variable should point to your NeMo Data Store endpoint.
+
+See the [NVIDIA Datasetio docs](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/datasetio/nvidia/README.md) for supported features and example usage.
+
+### Eval API: NeMo Evaluator
+The NeMo Evaluator microservice supports evaluation of LLMs. Launching an Evaluation job with NeMo Evaluator requires an Evaluation Config (an object that contains metadata needed by the job). A Llama Stack Benchmark maps to an Evaluation Config, so registering a Benchmark creates an Evaluation Config in NeMo Evaluator. The `NVIDIA_EVALUATOR_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the [NVIDIA Eval docs](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/eval/nvidia/README.md) for supported features and example usage.
+
+### Post-Training API: NeMo Customizer
+The NeMo Customizer microservice supports fine-tuning models. You can reference [this list of supported models](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/post_training/nvidia/models.py) that can be fine-tuned using Llama Stack. The `NVIDIA_CUSTOMIZER_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the [NVIDIA Post-Training docs](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/post_training/nvidia/README.md) for supported features and example usage.
+
+### Safety API: NeMo Guardrails
+The NeMo Guardrails microservice sits between your application and the LLM, and adds checks and content moderation to a model. The `GUARDRAILS_SERVICE_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the [NVIDIA Safety docs](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/safety/nvidia/README.md) for supported features and example usage.
+
+## Deploying models
+In order to use a registered model with the Llama Stack APIs, ensure the corresponding NIM is deployed to your environment. For example, you can use the NIM Proxy microservice to deploy `meta/llama-3.2-1b-instruct`.
+
+Note: For improved inference speeds, we need to use NIM with `fast_outlines` guided decoding system (specified in the request body). This is the default if you deployed the platform with the NeMo Microservices Helm Chart.
+```sh
+# URL to NeMo NIM Proxy service
+export NEMO_URL="http://nemo.test"
+
+curl --location "$NEMO_URL/v1/deployment/model-deployments" \
+   -H 'accept: application/json' \
+   -H 'Content-Type: application/json' \
+   -d '{
+      "name": "llama-3.2-1b-instruct",
+      "namespace": "meta",
+      "config": {
+         "model": "meta/llama-3.2-1b-instruct",
+         "nim_deployment": {
+            "image_name": "nvcr.io/nim/meta/llama-3.2-1b-instruct",
+            "image_tag": "1.8.3",
+            "pvc_size": "25Gi",
+            "gpu": 1,
+            "additional_envs": {
+               "NIM_GUIDED_DECODING_BACKEND": "fast_outlines"
+            }
+         }
+      }
+   }'
+```
+This NIM deployment should take approximately 10 minutes to go live. [See the docs](https://docs.nvidia.com/nemo/microservices/latest/get-started/tutorials/deploy-nims.html) for more information on how to deploy a NIM and verify it's available for inference.
+
+You can also remove a deployed NIM to free up GPU resources, if needed.
+```sh
+export NEMO_URL="http://nemo.test"
+
+curl -X DELETE "$NEMO_URL/v1/deployment/model-deployments/meta/llama-3.1-8b-instruct"
+```
+
+## Running Llama Stack with NVIDIA
+
+You can do this via venv (build code), or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=8321
+docker run \
+  -it \
+  --pull always \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  -e NVIDIA_API_KEY=$NVIDIA_API_KEY \
+  llamastack/distribution-{{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+### Via Docker with Custom Run Configuration
+
+You can also run the Docker container with a custom run configuration file by mounting it into the container:
+
+```bash
+# Set the path to your custom config.yaml file
+CUSTOM_RUN_CONFIG=/path/to/your/custom-config.yaml
+LLAMA_STACK_PORT=8321
+
+docker run \
+  -it \
+  --pull always \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  -v $CUSTOM_RUN_CONFIG:/app/custom-config.yaml \
+  -e RUN_CONFIG_PATH=/app/custom-config.yaml \
+  -e NVIDIA_API_KEY=$NVIDIA_API_KEY \
+  llamastack/distribution-{{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+**Note**: The run configuration must be mounted into the container before it can be used. The `-v` flag mounts your local file into the container, and the `RUN_CONFIG_PATH` environment variable tells the entrypoint script which configuration to use.
+
+{% if run_configs %}
+Available run configurations for this distribution:
+{% for config in run_configs %}
+- `{{ config }}`
+{% endfor %}
+{% endif %}
+
+### Via venv
+
+If you've set up your local development environment, you can also install the distribution dependencies using your local virtual environment.
+
+```bash
+INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
+llama stack list-deps nvidia | xargs -L1 uv pip install
+NVIDIA_API_KEY=$NVIDIA_API_KEY \
+INFERENCE_MODEL=$INFERENCE_MODEL \
+llama stack run ./config.yaml \
+  --port 8321
+```
+
+## Example Notebooks
+For examples of how to use the NVIDIA Distribution to run inference, fine-tune, evaluate, and run safety checks on your LLMs, you can reference the example notebooks in [docs/notebooks/nvidia](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks/nvidia).

llama_stack/distributions/nvidia/run-with-safety.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: nvidia
+distro_name: nvidia
 apis:
 - agents
 - datasetio
@@ -113,6 +113,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}

llama_stack/distributions/oci/config.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: oci
+distro_name: oci
 apis:
 - agents
 - datasetio
@@ -120,6 +120,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models: []
   shields: []

llama_stack/distributions/oci/doc_template.md

@@ -0,0 +1,140 @@
+---
+orphan: true
+---
+# OCI Distribution
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+{% if default_models %}
+### Models
+
+The following models are available by default:
+
+{% for model in default_models %}
+- `{{ model.model_id }} {{ model.doc_string }}`
+{% endfor %}
+{% endif %}
+
+## Prerequisites
+### Oracle Cloud Infrastructure Setup
+
+Before using the OCI Generative AI distribution, ensure you have:
+
+1. **Oracle Cloud Infrastructure Account**: Sign up at [Oracle Cloud Infrastructure](https://cloud.oracle.com/)
+2. **Generative AI Service Access**: Enable the Generative AI service in your OCI tenancy
+3. **Compartment**: Create or identify a compartment where you'll deploy Generative AI models
+4. **Authentication**: Configure authentication using either:
+   - **Instance Principal** (recommended for cloud-hosted deployments)
+   - **API Key** (for on-premises or development environments)
+
+### Authentication Methods
+
+#### Instance Principal Authentication (Recommended)
+Instance Principal authentication allows OCI resources to authenticate using the identity of the compute instance they're running on. This is the most secure method for production deployments.
+
+Requirements:
+- Instance must be running in an Oracle Cloud Infrastructure compartment
+- Instance must have appropriate IAM policies to access Generative AI services
+
+#### API Key Authentication
+For development or on-premises deployments, follow [this doc](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/apisigningkey.htm) to learn how to create your API signing key for your config file.
+
+### Required IAM Policies
+
+Ensure your OCI user or instance has the following policy statements:
+
+```
+Allow group <group_name> to use generative-ai-inference-endpoints in compartment <compartment_name>
+Allow group <group_name> to manage generative-ai-inference-endpoints in compartment <compartment_name>
+```
+
+## Supported Services
+
+### Inference: OCI Generative AI
+Oracle Cloud Infrastructure Generative AI provides access to high-performance AI models through OCI's Platform-as-a-Service offering. The service supports:
+
+- **Chat Completions**: Conversational AI with context awareness
+- **Text Generation**: Complete prompts and generate text content
+
+#### Available Models
+Common OCI Generative AI models include access to Meta, Cohere, OpenAI, Grok, and more models.
+
+### Safety: Llama Guard
+For content safety and moderation, this distribution uses Meta's LlamaGuard model through the OCI Generative AI service to provide:
+- Content filtering and moderation
+- Policy compliance checking
+- Harmful content detection
+
+### Vector Storage: Multiple Options
+The distribution supports several vector storage providers:
+- **FAISS**: Local in-memory vector search
+- **ChromaDB**: Distributed vector database
+- **PGVector**: PostgreSQL with vector extensions
+
+### Additional Services
+- **Dataset I/O**: Local filesystem and Hugging Face integration
+- **Tool Runtime**: Web search (Brave, Tavily) and RAG capabilities
+- **Evaluation**: Meta reference evaluation framework
+
+## Running Llama Stack with OCI
+
+You can run the OCI distribution via Docker or local virtual environment.
+
+### Via venv
+
+If you've set up your local development environment, you can also build the image using your local virtual environment.
+
+```bash
+OCI_AUTH=$OCI_AUTH_TYPE OCI_REGION=$OCI_REGION OCI_COMPARTMENT_OCID=$OCI_COMPARTMENT_OCID llama stack run --port 8321 oci
+```
+
+### Configuration Examples
+
+#### Using Instance Principal (Recommended for Production)
+```bash
+export OCI_AUTH_TYPE=instance_principal
+export OCI_REGION=us-chicago-1
+export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..<your-compartment-id>
+```
+
+#### Using API Key Authentication (Development)
+```bash
+export OCI_AUTH_TYPE=config_file
+export OCI_CONFIG_FILE_PATH=~/.oci/config
+export OCI_CLI_PROFILE=DEFAULT
+export OCI_REGION=us-chicago-1
+export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..your-compartment-id
+```
+
+## Regional Endpoints
+
+OCI Generative AI is available in multiple regions. The service automatically routes to the appropriate regional endpoint based on your configuration. For a full list of regional model availability, visit:
+
+https://docs.oracle.com/en-us/iaas/Content/generative-ai/overview.htm#regions
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Authentication Errors**: Verify your OCI credentials and IAM policies
+2. **Model Not Found**: Ensure the model OCID is correct and the model is available in your region
+3. **Permission Denied**: Check compartment permissions and Generative AI service access
+4. **Region Unavailable**: Verify the specified region supports Generative AI services
+
+### Getting Help
+
+For additional support:
+- [OCI Generative AI Documentation](https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm)
+- [Llama Stack Issues](https://github.com/meta-llama/llama-stack/issues)

llama_stack/distributions/open-benchmark/config.yaml

@@ -1,5 +1,5 @@
 version: 2
-image_name: open-benchmark
+distro_name: open-benchmark
 apis:
 - agents
 - datasetio
@@ -57,6 +57,11 @@ providers:
       db: ${env.PGVECTOR_DB:=}
       user: ${env.PGVECTOR_USER:=}
       password: ${env.PGVECTOR_PASSWORD:=}
+      distance_metric: COSINE
+      vector_index:
+        type: HNSW
+        m: 16
+        ef_construction: 64
       persistence:
         namespace: vector_io::pgvector
         backend: kv_default
@@ -145,6 +150,9 @@ storage:
     prompts:
       namespace: prompts
       backend: kv_default
+    connectors:
+      namespace: connectors
+      backend: kv_default
 registered_resources:
   models:
   - metadata: {}