portkey integration v2

llama_stack/providers/tests/inference/fixtures.py

@@ -22,6 +22,7 @@ from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
 from llama_stack.providers.remote.inference.tgi import TGIImplConfig
+from llama_stack.providers.remote.inference.portkey import PortkeyImplConfig
 from llama_stack.providers.remote.inference.together import TogetherImplConfig
 from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
 from llama_stack.providers.tests.resolver import construct_stack_for_test
@@ -82,6 +83,21 @@ def inference_cerebras() -> ProviderFixture:
         ],
     )
 
+@pytest.fixture(scope="session")
+def inference_cerebras() -> ProviderFixture:
+    return ProviderFixture(
+        providers=[
+            Provider(
+                provider_id="portkey",
+                provider_type="remote::portkey",
+                config=CerebrasImplConfig(
+                    api_key=get_env_or_fail("PORTKEY_API_KEY"),
+                ).model_dump(),
+            )
+        ],
+    )
+
+
 
 @pytest.fixture(scope="session")
 def inference_ollama(inference_model) -> ProviderFixture:

llama_stack/templates/portkey/__init__.py

@@ -0,0 +1,7 @@
+# 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 .cerebras import get_distribution_template  # noqa: F401

llama_stack/templates/portkey/build.yaml

@@ -0,0 +1,17 @@
+version: '2'
+name: cerebras
+distribution_spec:
+  description: Use Cerebras for running LLM inference
+  docker_image: null
+  providers:
+    inference:
+    - remote::cerebras
+    safety:
+    - inline::llama-guard
+    memory:
+    - inline::meta-reference
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+image_type: conda

llama_stack/templates/portkey/doc_template.md

@@ -0,0 +1,60 @@
+# Cerebras 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.provider_model_id }})`
+{% endfor %}
+{% endif %}
+
+
+### Prerequisite: API Keys
+
+Make sure you have access to a Cerebras API Key. You can get one by visiting [cloud.cerebras.ai](https://cloud.cerebras.ai/).
+
+
+## Running Llama Stack with Cerebras
+
+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
+LLAMA_STACK_PORT=5001
+docker run \
+  -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-{{ name }} \
+  --yaml-config /root/my-run.yaml \
+  --port $LLAMA_STACK_PORT \
+  --env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
+```
+
+### Via Conda
+
+```bash
+llama stack build --template cerebras --image-type conda
+llama stack run ./run.yaml \
+  --port 5001 \
+  --env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
+```

llama_stack/templates/portkey/portkey.py

@@ -0,0 +1,89 @@
+# 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_models.sku_list import all_registered_models
+
+from llama_stack.apis.models.models import ModelType
+
+from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
+from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
+from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["remote::cerebras"],
+        "safety": ["inline::llama-guard"],
+        "memory": ["inline::meta-reference"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+    }
+
+    inference_provider = Provider(
+        provider_id="cerebras",
+        provider_type="remote::cerebras",
+        config=CerebrasImplConfig.sample_run_config(),
+    )
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
+
+    core_model_to_hf_repo = {
+        m.descriptor(): m.huggingface_repo for m in all_registered_models()
+    }
+    default_models = [
+        ModelInput(
+            model_id=core_model_to_hf_repo[m.llama_model],
+            provider_model_id=m.provider_model_id,
+            provider_id="cerebras",
+        )
+        for m in model_aliases
+    ]
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
+
+    return DistributionTemplate(
+        name="cerebras",
+        distro_type="self_hosted",
+        description="Use Cerebras for running LLM inference",
+        docker_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        default_models=default_models,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider, embedding_provider],
+                },
+                default_models=default_models + [embedding_model],
+                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
+            ),
+        },
+        run_config_env_vars={
+            "LLAMASTACK_PORT": (
+                "5001",
+                "Port for the Llama Stack distribution server",
+            ),
+            "CEREBRAS_API_KEY": (
+                "",
+                "Cerebras API Key",
+            ),
+        },
+    )

llama_stack/templates/portkey/run.yaml

@@ -0,0 +1,77 @@
+version: '2'
+image_name: portkey
+docker_image: null
+conda_env: portkey
+apis:
+- agents
+- inference
+- memory
+- safety
+- telemetry
+providers:
+  inference:
+  - provider_id: portkey
+    provider_type: remote::portkey
+    config:
+      base_url: https://api.portkey.ai/v1
+      api_key: ${env.PORTKEY_API_KEY}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config: {}
+  memory:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/portkey}/faiss_store.db
+  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/portkey}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/portkey/trace_store.db}
+metadata_store:
+  namespace: null
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/portkey}/registry.db
+models:
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: portkey
+  provider_model_id: llama3.1-8b
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: portkey
+  provider_model_id: llama-3.3-70b
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  provider_model_id: null
+  model_type: embedding
+shields:
+- params: null
+  shield_id: meta-llama/Llama-Guard-3-8B
+  provider_id: null
+  provider_shield_id: null
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []