From 89e449c2cbb9ac8117d6ede27b5fd0c7f5e8ca35 Mon Sep 17 00:00:00 2001 From: Botao Chen Date: Fri, 7 Mar 2025 14:49:10 -0800 Subject: [PATCH] fix: Fix open benchmark template (#1496) ## What does this PR do? Delete the open_benchmark template which was generated by the auto codegen by accident --- distributions/dependencies.json | 36 -- .../templates/open-benchmark/__init__.py | 7 - .../open-benchmark/open_benchmark.py | 178 --------- .../templates/open_benchmark/build.yaml | 37 -- llama_stack/templates/open_benchmark/run.yaml | 364 ------------------ 5 files changed, 622 deletions(-) delete mode 100644 llama_stack/templates/open-benchmark/__init__.py delete mode 100644 llama_stack/templates/open-benchmark/open_benchmark.py delete mode 100644 llama_stack/templates/open_benchmark/build.yaml delete mode 100644 llama_stack/templates/open_benchmark/run.yaml diff --git a/distributions/dependencies.json b/distributions/dependencies.json index 5623e251a..59b0c9e62 100644 --- a/distributions/dependencies.json +++ b/distributions/dependencies.json @@ -453,42 +453,6 @@ "transformers", "uvicorn" ], - "open_benchmark": [ - "aiosqlite", - "autoevals", - "blobfile", - "chardet", - "chromadb-client", - "datasets", - "fastapi", - "fire", - "httpx", - "litellm", - "matplotlib", - "mcp", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pymongo", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "sqlite-vec", - "together", - "tqdm", - "transformers", - "uvicorn", - "sentence-transformers --no-deps", - "torch torchvision --index-url https://download.pytorch.org/whl/cpu" - ], "remote-vllm": [ "aiosqlite", "autoevals", diff --git a/llama_stack/templates/open-benchmark/__init__.py b/llama_stack/templates/open-benchmark/__init__.py deleted file mode 100644 index 14d0a28f5..000000000 --- a/llama_stack/templates/open-benchmark/__init__.py +++ /dev/null @@ -1,7 +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 .open_benchmark import get_distribution_template # noqa: F401 diff --git a/llama_stack/templates/open-benchmark/open_benchmark.py b/llama_stack/templates/open-benchmark/open_benchmark.py deleted file mode 100644 index 9ef84456e..000000000 --- a/llama_stack/templates/open-benchmark/open_benchmark.py +++ /dev/null @@ -1,178 +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 typing import List, Tuple - -from llama_stack.distribution.datatypes import ( - ModelInput, - Provider, - ShieldInput, - ToolGroupInput, -) -from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig -from llama_stack.providers.remote.inference.anthropic.config import AnthropicConfig -from llama_stack.providers.remote.inference.anthropic.models import MODEL_ENTRIES as ANTHROPIC_MODEL_ENTRIES -from llama_stack.providers.remote.inference.gemini.config import GeminiConfig -from llama_stack.providers.remote.inference.gemini.models import MODEL_ENTRIES as GEMINI_MODEL_ENTRIES -from llama_stack.providers.remote.inference.groq.config import GroqConfig -from llama_stack.providers.remote.inference.groq.models import MODEL_ENTRIES as GROQ_MODEL_ENTRIES -from llama_stack.providers.remote.inference.openai.config import OpenAIConfig -from llama_stack.providers.remote.inference.openai.models import MODEL_ENTRIES as OPENAI_MODEL_ENTRIES -from llama_stack.providers.remote.inference.together.config import TogetherImplConfig -from llama_stack.providers.remote.inference.together.models import MODEL_ENTRIES as TOGETHER_MODEL_ENTRIES -from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig -from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig -from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry - - -def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]: - # in this template, we allow each API key to be optional - providers = [ - ( - "openai", - OPENAI_MODEL_ENTRIES, - OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:}"), - ), - ( - "anthropic", - ANTHROPIC_MODEL_ENTRIES, - AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:}"), - ), - ( - "gemini", - GEMINI_MODEL_ENTRIES, - GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:}"), - ), - ( - "groq", - GROQ_MODEL_ENTRIES, - GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"), - ), - ( - "together", - TOGETHER_MODEL_ENTRIES, - TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"), - ), - ] - inference_providers = [] - available_models = {} - for provider_id, model_entries, config in providers: - inference_providers.append( - Provider( - provider_id=provider_id, - provider_type=f"remote::{provider_id}", - config=config, - ) - ) - available_models[provider_id] = model_entries - return inference_providers, available_models - - -def get_distribution_template() -> DistributionTemplate: - inference_providers, available_models = get_inference_providers() - providers = { - "inference": ([p.provider_type for p in inference_providers] + ["inline::sentence-transformers"]), - "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"], - "safety": ["inline::llama-guard"], - "agents": ["inline::meta-reference"], - "telemetry": ["inline::meta-reference"], - "eval": ["inline::meta-reference"], - "datasetio": ["remote::huggingface", "inline::localfs"], - "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"], - "tool_runtime": [ - "remote::brave-search", - "remote::tavily-search", - "inline::code-interpreter", - "inline::rag-runtime", - "remote::model-context-protocol", - ], - } - name = "open_benchmark" - - vector_io_providers = [ - Provider( - provider_id="sqlite-vec", - provider_type="inline::sqlite-vec", - config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"), - ), - Provider( - provider_id="${env.ENABLE_CHROMADB+chromadb}", - provider_type="remote::chromadb", - config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"), - ), - Provider( - provider_id="${env.ENABLE_PGVECTOR+pgvector}", - provider_type="remote::pgvector", - config=PGVectorVectorIOConfig.sample_run_config( - db="${env.PGVECTOR_DB:}", - user="${env.PGVECTOR_USER:}", - password="${env.PGVECTOR_PASSWORD:}", - ), - ), - ] - - default_tool_groups = [ - ToolGroupInput( - toolgroup_id="builtin::websearch", - provider_id="tavily-search", - ), - ToolGroupInput( - toolgroup_id="builtin::rag", - provider_id="rag-runtime", - ), - ToolGroupInput( - toolgroup_id="builtin::code_interpreter", - provider_id="code-interpreter", - ), - ] - - default_models = get_model_registry(available_models) - return DistributionTemplate( - name=name, - distro_type="self_hosted", - description="Distribution for running open benchmarks", - container_image=None, - template_path=None, - providers=providers, - available_models_by_provider=available_models, - run_configs={ - "run.yaml": RunConfigSettings( - provider_overrides={ - "inference": inference_providers, - "vector_io": vector_io_providers, - }, - default_models=default_models, - default_tool_groups=default_tool_groups, - default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")], - ), - }, - run_config_env_vars={ - "LLAMA_STACK_PORT": ( - "5001", - "Port for the Llama Stack distribution server", - ), - "OPENAI_API_KEY": ( - "", - "OpenAI API Key", - ), - "GEMINI_API_KEY": ( - "", - "Gemini API Key", - ), - "GROQ_API_KEY": ( - "", - "Groq API Key", - ), - "ANTHROPIC_API_KEY": ( - "", - "Anthropic API Key", - ), - "TOGETHER_API_KEY": ( - "", - "Together API Key", - ), - }, - ) diff --git a/llama_stack/templates/open_benchmark/build.yaml b/llama_stack/templates/open_benchmark/build.yaml deleted file mode 100644 index 367dd1374..000000000 --- a/llama_stack/templates/open_benchmark/build.yaml +++ /dev/null @@ -1,37 +0,0 @@ -version: '2' -distribution_spec: - description: Distribution for running open benchmarks - providers: - inference: - - remote::openai - - remote::anthropic - - remote::gemini - - remote::groq - - remote::together - - inline::sentence-transformers - vector_io: - - inline::sqlite-vec - - remote::chromadb - - remote::pgvector - safety: - - inline::llama-guard - agents: - - inline::meta-reference - telemetry: - - inline::meta-reference - eval: - - inline::meta-reference - datasetio: - - remote::huggingface - - inline::localfs - scoring: - - inline::basic - - inline::llm-as-judge - - inline::braintrust - tool_runtime: - - remote::brave-search - - remote::tavily-search - - inline::code-interpreter - - inline::rag-runtime - - remote::model-context-protocol -image_type: conda diff --git a/llama_stack/templates/open_benchmark/run.yaml b/llama_stack/templates/open_benchmark/run.yaml deleted file mode 100644 index e98c2c708..000000000 --- a/llama_stack/templates/open_benchmark/run.yaml +++ /dev/null @@ -1,364 +0,0 @@ -version: '2' -image_name: open_benchmark -apis: -- agents -- datasetio -- eval -- inference -- safety -- scoring -- telemetry -- tool_runtime -- vector_io -providers: - inference: - - provider_id: openai - provider_type: remote::openai - config: - api_key: ${env.OPENAI_API_KEY:} - - provider_id: anthropic - provider_type: remote::anthropic - config: - api_key: ${env.ANTHROPIC_API_KEY:} - - provider_id: gemini - provider_type: remote::gemini - config: - api_key: ${env.GEMINI_API_KEY:} - - provider_id: groq - provider_type: remote::groq - config: - url: https://api.groq.com - api_key: ${env.GROQ_API_KEY:} - - provider_id: together - provider_type: remote::together - config: - url: https://api.together.xyz/v1 - api_key: ${env.TOGETHER_API_KEY} - vector_io: - - provider_id: sqlite-vec - provider_type: inline::sqlite-vec - config: - db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open_benchmark}/sqlite_vec.db - - provider_id: ${env.ENABLE_CHROMADB+chromadb} - provider_type: remote::chromadb - config: - url: ${env.CHROMADB_URL:} - - provider_id: ${env.ENABLE_PGVECTOR+pgvector} - provider_type: remote::pgvector - config: - host: ${env.PGVECTOR_HOST:localhost} - port: ${env.PGVECTOR_PORT:5432} - db: ${env.PGVECTOR_DB:} - user: ${env.PGVECTOR_USER:} - password: ${env.PGVECTOR_PASSWORD:} - safety: - - provider_id: llama-guard - provider_type: inline::llama-guard - config: {} - 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/open_benchmark}/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/open_benchmark/trace_store.db} - eval: - - provider_id: meta-reference - provider_type: inline::meta-reference - config: {} - datasetio: - - provider_id: huggingface - provider_type: remote::huggingface - config: {} - - provider_id: localfs - provider_type: inline::localfs - config: {} - scoring: - - provider_id: basic - provider_type: inline::basic - config: {} - - provider_id: llm-as-judge - provider_type: inline::llm-as-judge - config: {} - - provider_id: braintrust - provider_type: inline::braintrust - config: - openai_api_key: ${env.OPENAI_API_KEY:} - tool_runtime: - - provider_id: brave-search - provider_type: remote::brave-search - config: - api_key: ${env.BRAVE_SEARCH_API_KEY:} - max_results: 3 - - provider_id: tavily-search - provider_type: remote::tavily-search - config: - api_key: ${env.TAVILY_SEARCH_API_KEY:} - max_results: 3 - - provider_id: code-interpreter - provider_type: inline::code-interpreter - config: {} - - provider_id: rag-runtime - provider_type: inline::rag-runtime - config: {} - - provider_id: model-context-protocol - provider_type: remote::model-context-protocol - config: {} -metadata_store: - type: sqlite - db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open_benchmark}/registry.db -models: -- metadata: {} - model_id: openai/gpt-4o - provider_id: openai - provider_model_id: openai/gpt-4o - model_type: llm -- metadata: {} - model_id: openai/gpt-4o-mini - provider_id: openai - provider_model_id: openai/gpt-4o-mini - model_type: llm -- metadata: {} - model_id: openai/chatgpt-4o-latest - provider_id: openai - provider_model_id: openai/chatgpt-4o-latest - model_type: llm -- metadata: - embedding_dimension: 1536 - context_length: 8192 - model_id: openai/text-embedding-3-small - provider_id: openai - provider_model_id: openai/text-embedding-3-small - model_type: embedding -- metadata: - embedding_dimension: 3072 - context_length: 8192 - model_id: openai/text-embedding-3-large - provider_id: openai - provider_model_id: openai/text-embedding-3-large - model_type: embedding -- metadata: {} - model_id: anthropic/claude-3-5-sonnet-latest - provider_id: anthropic - provider_model_id: anthropic/claude-3-5-sonnet-latest - model_type: llm -- metadata: {} - model_id: anthropic/claude-3-7-sonnet-latest - provider_id: anthropic - provider_model_id: anthropic/claude-3-7-sonnet-latest - model_type: llm -- metadata: {} - model_id: anthropic/claude-3-5-haiku-latest - provider_id: anthropic - provider_model_id: anthropic/claude-3-5-haiku-latest - model_type: llm -- metadata: - embedding_dimension: 1024 - context_length: 32000 - model_id: anthropic/voyage-3 - provider_id: anthropic - provider_model_id: anthropic/voyage-3 - model_type: embedding -- metadata: - embedding_dimension: 512 - context_length: 32000 - model_id: anthropic/voyage-3-lite - provider_id: anthropic - provider_model_id: anthropic/voyage-3-lite - model_type: embedding -- metadata: - embedding_dimension: 1024 - context_length: 32000 - model_id: anthropic/voyage-code-3 - provider_id: anthropic - provider_model_id: anthropic/voyage-code-3 - model_type: embedding -- metadata: {} - model_id: gemini/gemini-1.5-flash - provider_id: gemini - provider_model_id: gemini/gemini-1.5-flash - model_type: llm -- metadata: {} - model_id: gemini/gemini-1.5-pro - provider_id: gemini - provider_model_id: gemini/gemini-1.5-pro - model_type: llm -- metadata: - embedding_dimension: 768 - context_length: 2048 - model_id: gemini/text-embedding-004 - provider_id: gemini - provider_model_id: gemini/text-embedding-004 - model_type: embedding -- metadata: {} - model_id: groq/llama3-8b-8192 - provider_id: groq - provider_model_id: groq/llama3-8b-8192 - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.1-8B-Instruct - provider_id: groq - provider_model_id: groq/llama3-8b-8192 - model_type: llm -- metadata: {} - model_id: groq/llama-3.1-8b-instant - provider_id: groq - provider_model_id: groq/llama-3.1-8b-instant - model_type: llm -- metadata: {} - model_id: groq/llama3-70b-8192 - provider_id: groq - provider_model_id: groq/llama3-70b-8192 - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3-70B-Instruct - provider_id: groq - provider_model_id: groq/llama3-70b-8192 - model_type: llm -- metadata: {} - model_id: groq/llama-3.3-70b-versatile - provider_id: groq - provider_model_id: groq/llama-3.3-70b-versatile - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.3-70B-Instruct - provider_id: groq - provider_model_id: groq/llama-3.3-70b-versatile - model_type: llm -- metadata: {} - model_id: groq/llama-3.2-3b-preview - provider_id: groq - provider_model_id: groq/llama-3.2-3b-preview - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-3B-Instruct - provider_id: groq - provider_model_id: groq/llama-3.2-3b-preview - model_type: llm -- metadata: {} - model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.1-8B-Instruct - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.1-70B-Instruct - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.1-405B-Instruct-FP8 - provider_id: together - provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-3B-Instruct - provider_id: together - provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-11B-Vision-Instruct - provider_id: together - provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.2-90B-Vision-Instruct - provider_id: together - provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo - provider_id: together - provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-3.3-70B-Instruct - provider_id: together - provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Meta-Llama-Guard-3-8B - provider_id: together - provider_model_id: meta-llama/Meta-Llama-Guard-3-8B - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-Guard-3-8B - provider_id: together - provider_model_id: meta-llama/Meta-Llama-Guard-3-8B - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo - provider_id: together - provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo - model_type: llm -- metadata: {} - model_id: meta-llama/Llama-Guard-3-11B-Vision - provider_id: together - provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo - model_type: llm -- metadata: - embedding_dimension: 768 - context_length: 8192 - model_id: togethercomputer/m2-bert-80M-8k-retrieval - provider_id: together - provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval - model_type: embedding -- metadata: - embedding_dimension: 768 - context_length: 32768 - model_id: togethercomputer/m2-bert-80M-32k-retrieval - provider_id: together - provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval - model_type: embedding -shields: -- shield_id: meta-llama/Llama-Guard-3-8B -vector_dbs: [] -datasets: [] -scoring_fns: [] -benchmarks: [] -tool_groups: -- toolgroup_id: builtin::websearch - provider_id: tavily-search -- toolgroup_id: builtin::rag - provider_id: rag-runtime -- toolgroup_id: builtin::code_interpreter - provider_id: code-interpreter -server: - port: 8321