portkey integration v2

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",
+            ),
+        },
+    )