llama-stack 0.3.5__py3-none-any.whl → 0.4.0__py3-none-any.whl

llama_stack/distributions/postgres-demo/postgres_demo.py

@@ -1,125 +0,0 @@
-# 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 llama_stack.apis.models import ModelType
-from llama_stack.core.datatypes import (
-    BuildProvider,
-    ModelInput,
-    Provider,
-    ShieldInput,
-    ToolGroupInput,
-)
-from llama_stack.distributions.template import (
-    DistributionTemplate,
-    RunConfigSettings,
-)
-from llama_stack.providers.inline.inference.sentence_transformers import SentenceTransformersInferenceConfig
-from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
-from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
-from llama_stack.providers.utils.kvstore.config import PostgresKVStoreConfig
-from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
-
-
-def get_distribution_template() -> DistributionTemplate:
-    inference_providers = [
-        Provider(
-            provider_id="vllm-inference",
-            provider_type="remote::vllm",
-            config=VLLMInferenceAdapterConfig.sample_run_config(
-                url="${env.VLLM_URL:=http://localhost:8000/v1}",
-            ),
-        ),
-    ]
-    providers = {
-        "inference": [
-            BuildProvider(provider_type="remote::vllm"),
-            BuildProvider(provider_type="inline::sentence-transformers"),
-        ],
-        "vector_io": [BuildProvider(provider_type="remote::chromadb")],
-        "safety": [BuildProvider(provider_type="inline::llama-guard")],
-        "agents": [BuildProvider(provider_type="inline::meta-reference")],
-        "tool_runtime": [
-            BuildProvider(provider_type="remote::brave-search"),
-            BuildProvider(provider_type="remote::tavily-search"),
-            BuildProvider(provider_type="inline::rag-runtime"),
-            BuildProvider(provider_type="remote::model-context-protocol"),
-        ],
-    }
-    name = "postgres-demo"
-
-    vector_io_providers = [
-        Provider(
-            provider_id="${env.ENABLE_CHROMADB:+chromadb}",
-            provider_type="remote::chromadb",
-            config=ChromaVectorIOConfig.sample_run_config(
-                f"~/.llama/distributions/{name}",
-                url="${env.CHROMADB_URL:=}",
-            ),
-        ),
-    ]
-    default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::websearch",
-            provider_id="tavily-search",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::rag",
-            provider_id="rag-runtime",
-        ),
-    ]
-
-    default_models = [
-        ModelInput(
-            model_id="${env.INFERENCE_MODEL}",
-            provider_id="vllm-inference",
-        )
-    ]
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-    embedding_model = ModelInput(
-        model_id="nomic-embed-text-v1.5",
-        provider_id=embedding_provider.provider_id,
-        model_type=ModelType.embedding,
-        metadata={
-            "embedding_dimension": 768,
-        },
-    )
-    return DistributionTemplate(
-        name=name,
-        distro_type="self_hosted",
-        description="Quick start template for running Llama Stack with several popular providers",
-        container_image=None,
-        template_path=None,
-        providers=providers,
-        available_models_by_provider={},
-        run_configs={
-            "run.yaml": RunConfigSettings(
-                provider_overrides={
-                    "inference": inference_providers + [embedding_provider],
-                    "vector_io": vector_io_providers,
-                },
-                default_models=default_models + [embedding_model],
-                default_tool_groups=default_tool_groups,
-                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
-                storage_backends={
-                    "kv_default": PostgresKVStoreConfig.sample_run_config(
-                        table_name="llamastack_kvstore",
-                    ),
-                    "sql_default": PostgresSqlStoreConfig.sample_run_config(),
-                },
-            ),
-        },
-        run_config_env_vars={
-            "LLAMA_STACK_PORT": (
-                "8321",
-                "Port for the Llama Stack distribution server",
-            ),
-        },
-    )

llama_stack/distributions/starter/build.yaml

@@ -1,61 +0,0 @@
-version: 2
-distribution_spec:
-  description: Quick start template for running Llama Stack with several popular providers.
-    This distribution is intended for CPU-only environments.
-  providers:
-    inference:
-    - provider_type: remote::cerebras
-    - provider_type: remote::ollama
-    - provider_type: remote::vllm
-    - provider_type: remote::tgi
-    - provider_type: remote::fireworks
-    - provider_type: remote::together
-    - provider_type: remote::bedrock
-    - provider_type: remote::nvidia
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::vertexai
-    - provider_type: remote::groq
-    - provider_type: remote::sambanova
-    - provider_type: remote::azure
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: inline::sqlite-vec
-    - provider_type: inline::milvus
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    - provider_type: remote::qdrant
-    - provider_type: remote::weaviate
-    files:
-    - provider_type: inline::localfs
-    safety:
-    - provider_type: inline::llama-guard
-    - provider_type: inline::code-scanner
-    agents:
-    - provider_type: inline::meta-reference
-    post_training:
-    - provider_type: inline::torchtune-cpu
-    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
-    batches:
-    - provider_type: inline::reference
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- asyncpg
-- psycopg2-binary
-- sqlalchemy[asyncio]

llama_stack/distributions/starter-gpu/build.yaml

@@ -1,61 +0,0 @@
-version: 2
-distribution_spec:
-  description: Quick start template for running Llama Stack with several popular providers.
-    This distribution is intended for GPU-enabled environments.
-  providers:
-    inference:
-    - provider_type: remote::cerebras
-    - provider_type: remote::ollama
-    - provider_type: remote::vllm
-    - provider_type: remote::tgi
-    - provider_type: remote::fireworks
-    - provider_type: remote::together
-    - provider_type: remote::bedrock
-    - provider_type: remote::nvidia
-    - provider_type: remote::openai
-    - provider_type: remote::anthropic
-    - provider_type: remote::gemini
-    - provider_type: remote::vertexai
-    - provider_type: remote::groq
-    - provider_type: remote::sambanova
-    - provider_type: remote::azure
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    - provider_type: inline::sqlite-vec
-    - provider_type: inline::milvus
-    - provider_type: remote::chromadb
-    - provider_type: remote::pgvector
-    - provider_type: remote::qdrant
-    - provider_type: remote::weaviate
-    files:
-    - provider_type: inline::localfs
-    safety:
-    - provider_type: inline::llama-guard
-    - provider_type: inline::code-scanner
-    agents:
-    - provider_type: inline::meta-reference
-    post_training:
-    - provider_type: inline::huggingface-gpu
-    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
-    batches:
-    - provider_type: inline::reference
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- asyncpg
-- psycopg2-binary
-- sqlalchemy[asyncio]

llama_stack/distributions/watsonx/build.yaml

@@ -1,33 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use watsonx for running LLM inference
-  providers:
-    inference:
-    - provider_type: remote::watsonx
-    - provider_type: inline::sentence-transformers
-    vector_io:
-    - provider_type: inline::faiss
-    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
-    files:
-    - provider_type: inline::localfs
-image_type: venv
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]