llama-stack 0.0.42__py3-none-any.whl → 0.3.4__py3-none-any.whl

llama_stack/distributions/nvidia/nvidia.py

@@ -0,0 +1,154 @@
+# 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, ModelInput, Provider, ShieldInput, ToolGroupInput
+from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
+from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
+from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
+from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
+from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
+from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
+
+
+def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
+    providers = {
+        "inference": [BuildProvider(provider_type="remote::nvidia")],
+        "vector_io": [BuildProvider(provider_type="inline::faiss")],
+        "safety": [BuildProvider(provider_type="remote::nvidia")],
+        "agents": [BuildProvider(provider_type="inline::meta-reference")],
+        "eval": [BuildProvider(provider_type="remote::nvidia")],
+        "post_training": [BuildProvider(provider_type="remote::nvidia")],
+        "datasetio": [
+            BuildProvider(provider_type="inline::localfs"),
+            BuildProvider(provider_type="remote::nvidia"),
+        ],
+        "scoring": [BuildProvider(provider_type="inline::basic")],
+        "tool_runtime": [BuildProvider(provider_type="inline::rag-runtime")],
+        "files": [BuildProvider(provider_type="inline::localfs")],
+    }
+
+    inference_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NVIDIAConfig.sample_run_config(),
+    )
+    safety_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NVIDIASafetyConfig.sample_run_config(),
+    )
+    datasetio_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NvidiaDatasetIOConfig.sample_run_config(),
+    )
+    eval_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NVIDIAEvalConfig.sample_run_config(),
+    )
+    files_provider = Provider(
+        provider_id="meta-reference-files",
+        provider_type="inline::localfs",
+        config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )
+    inference_model = ModelInput(
+        model_id="${env.INFERENCE_MODEL}",
+        provider_id="nvidia",
+    )
+    safety_model = ModelInput(
+        model_id="${env.SAFETY_MODEL}",
+        provider_id="nvidia",
+    )
+
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+    ]
+
+    return DistributionTemplate(
+        name=name,
+        distro_type="self_hosted",
+        description="Use NVIDIA NIM for running LLM inference, evaluation and safety",
+        container_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider],
+                    "datasetio": [datasetio_provider],
+                    "eval": [eval_provider],
+                    "files": [files_provider],
+                },
+                default_tool_groups=default_tool_groups,
+            ),
+            "run-with-safety.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [
+                        inference_provider,
+                        safety_provider,
+                    ],
+                    "eval": [eval_provider],
+                    "files": [files_provider],
+                },
+                default_models=[inference_model, safety_model],
+                default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
+                default_tool_groups=default_tool_groups,
+            ),
+        },
+        run_config_env_vars={
+            "NVIDIA_API_KEY": (
+                "",
+                "NVIDIA API Key",
+            ),
+            "NVIDIA_APPEND_API_VERSION": (
+                "True",
+                "Whether to append the API version to the base_url",
+            ),
+            ## Nemo Customizer related variables
+            "NVIDIA_DATASET_NAMESPACE": (
+                "default",
+                "NVIDIA Dataset Namespace",
+            ),
+            "NVIDIA_PROJECT_ID": (
+                "test-project",
+                "NVIDIA Project ID",
+            ),
+            "NVIDIA_CUSTOMIZER_URL": (
+                "https://customizer.api.nvidia.com",
+                "NVIDIA Customizer URL",
+            ),
+            "NVIDIA_OUTPUT_MODEL_DIR": (
+                "test-example-model@v1",
+                "NVIDIA Output Model Directory",
+            ),
+            "GUARDRAILS_SERVICE_URL": (
+                "http://0.0.0.0:7331",
+                "URL for the NeMo Guardrails Service",
+            ),
+            "NVIDIA_GUARDRAILS_CONFIG_ID": (
+                "self-check",
+                "NVIDIA Guardrail Configuration ID",
+            ),
+            "NVIDIA_EVALUATOR_URL": (
+                "http://0.0.0.0:7331",
+                "URL for the NeMo Evaluator Service",
+            ),
+            "INFERENCE_MODEL": (
+                "Llama3.1-8B-Instruct",
+                "Inference model",
+            ),
+            "SAFETY_MODEL": (
+                "meta/llama-3.1-8b-instruct",
+                "Name of the model to use for safety",
+            ),
+        },
+    )

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

@@ -0,0 +1,137 @@
+version: 2
+image_name: nvidia
+apis:
+- agents
+- datasetio
+- eval
+- files
+- inference
+- post_training
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
+      api_key: ${env.NVIDIA_API_KEY:=}
+      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
+      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  safety:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
+      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  eval:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
+  datasetio:
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        namespace: datasetio::localfs
+        backend: kv_default
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  tool_runtime:
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
+      metadata_store:
+        table_name: files_metadata
+        backend: sql_default
+storage:
+  backends:
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+registered_resources:
+  models:
+  - metadata: {}
+    model_id: ${env.INFERENCE_MODEL}
+    provider_id: nvidia
+    model_type: llm
+  - metadata: {}
+    model_id: ${env.SAFETY_MODEL}
+    provider_id: nvidia
+    model_type: llm
+  shields:
+  - shield_id: ${env.SAFETY_MODEL}
+    provider_id: nvidia
+  vector_dbs: []
+  datasets: []
+  scoring_fns: []
+  benchmarks: []
+  tool_groups:
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
+server:
+  port: 8321
+telemetry:
+  enabled: true

llama_stack/distributions/nvidia/run.yaml

@@ -0,0 +1,116 @@
+version: 2
+image_name: nvidia
+apis:
+- agents
+- datasetio
+- eval
+- files
+- inference
+- post_training
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
+      api_key: ${env.NVIDIA_API_KEY:=}
+      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  safety:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
+      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  eval:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
+  datasetio:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  tool_runtime:
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
+      metadata_store:
+        table_name: files_metadata
+        backend: sql_default
+storage:
+  backends:
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+registered_resources:
+  models: []
+  shields: []
+  vector_dbs: []
+  datasets: []
+  scoring_fns: []
+  benchmarks: []
+  tool_groups:
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
+server:
+  port: 8321
+telemetry:
+  enabled: true

llama_stack/distributions/open-benchmark/__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 .open_benchmark import get_distribution_template  # noqa: F401

llama_stack/distributions/open-benchmark/build.yaml

@@ -0,0 +1,36 @@
+version: 2
+distribution_spec:
+  description: Distribution for running open benchmarks
+  providers:
+    inference:
+    - provider_type: remote::openai
+    - provider_type: remote::anthropic
+    - provider_type: remote::gemini
+    - provider_type: remote::groq
+    - provider_type: remote::together
+    vector_io:
+    - provider_type: inline::sqlite-vec
+    - provider_type: remote::chromadb
+    - provider_type: remote::pgvector
+    safety:
+    - provider_type: inline::llama-guard
+    agents:
+    - provider_type: inline::meta-reference
+    eval:
+    - provider_type: inline::meta-reference
+    datasetio:
+    - provider_type: remote::huggingface
+    - provider_type: inline::localfs
+    scoring:
+    - provider_type: inline::basic
+    - provider_type: inline::llm-as-judge
+    - provider_type: inline::braintrust
+    tool_runtime:
+    - provider_type: remote::brave-search
+    - provider_type: remote::tavily-search
+    - provider_type: inline::rag-runtime
+    - provider_type: remote::model-context-protocol
+image_type: venv
+additional_pip_packages:
+- aiosqlite
+- sqlalchemy[asyncio]