diff --git a/llama_stack/providers/registry/batches.py b/llama_stack/providers/registry/batches.py index de7886efb..a07942486 100644 --- a/llama_stack/providers/registry/batches.py +++ b/llama_stack/providers/registry/batches.py @@ -13,7 +13,7 @@ def available_providers() -> list[ProviderSpec]: InlineProviderSpec( api=Api.batches, provider_type="inline::reference", - pip_packages=["openai"], + pip_packages=[], module="llama_stack.providers.inline.batches.reference", config_class="llama_stack.providers.inline.batches.reference.config.ReferenceBatchesImplConfig", api_dependencies=[ diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py index 541fbb432..8912560cb 100644 --- a/llama_stack/providers/registry/inference.py +++ b/llama_stack/providers/registry/inference.py @@ -75,7 +75,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="vllm", - pip_packages=["openai"], + pip_packages=[], module="llama_stack.providers.remote.inference.vllm", config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig", description="Remote vLLM inference provider for connecting to vLLM servers.", @@ -151,9 +151,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="databricks", - pip_packages=[ - "openai", - ], + pip_packages=[], module="llama_stack.providers.remote.inference.databricks", config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig", description="Databricks inference provider for running models on Databricks' unified analytics platform.", @@ -163,9 +161,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="nvidia", - pip_packages=[ - "openai", - ], + pip_packages=[], module="llama_stack.providers.remote.inference.nvidia", config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig", description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.", @@ -175,7 +171,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="runpod", - pip_packages=["openai"], + pip_packages=[], module="llama_stack.providers.remote.inference.runpod", config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig", description="RunPod inference provider for running models on RunPod's cloud GPU platform.", @@ -207,7 +203,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="gemini", - pip_packages=["litellm", "openai"], + pip_packages=["litellm"], module="llama_stack.providers.remote.inference.gemini", config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig", provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator", @@ -218,7 +214,7 @@ def available_providers() -> list[ProviderSpec]: api=Api.inference, adapter=AdapterSpec( adapter_type="vertexai", - pip_packages=["litellm", "google-cloud-aiplatform", "openai"], + pip_packages=["litellm", "google-cloud-aiplatform"], module="llama_stack.providers.remote.inference.vertexai", config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig", provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator", @@ -248,7 +244,7 @@ Available Models: api=Api.inference, adapter=AdapterSpec( adapter_type="groq", - pip_packages=["litellm", "openai"], + pip_packages=["litellm"], module="llama_stack.providers.remote.inference.groq", config_class="llama_stack.providers.remote.inference.groq.GroqConfig", provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator", @@ -270,7 +266,7 @@ Available Models: api=Api.inference, adapter=AdapterSpec( adapter_type="sambanova", - pip_packages=["litellm", "openai"], + pip_packages=["litellm"], module="llama_stack.providers.remote.inference.sambanova", config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig", provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator", diff --git a/llama_stack/providers/registry/scoring.py b/llama_stack/providers/registry/scoring.py index 79293d888..a4ec54ed2 100644 --- a/llama_stack/providers/registry/scoring.py +++ b/llama_stack/providers/registry/scoring.py @@ -38,7 +38,7 @@ def available_providers() -> list[ProviderSpec]: InlineProviderSpec( api=Api.scoring, provider_type="inline::braintrust", - pip_packages=["autoevals", "openai"], + pip_packages=["autoevals"], module="llama_stack.providers.inline.scoring.braintrust", config_class="llama_stack.providers.inline.scoring.braintrust.BraintrustScoringConfig", api_dependencies=[ diff --git a/pyproject.toml b/pyproject.toml index 0414aafb0..72c4f6f9e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -32,7 +32,7 @@ dependencies = [ "jinja2>=3.1.6", "jsonschema", "llama-stack-client>=0.2.21", - "openai>=1.99.6", + "openai>=1.100.0", # for expires_after support "prompt-toolkit", "python-dotenv", "python-jose[cryptography]", @@ -80,7 +80,6 @@ dev = [ unit = [ "sqlite-vec", "ollama", - "openai", "aiosqlite", "aiohttp", "psycopg2-binary>=2.9.0", @@ -105,7 +104,6 @@ unit = [ # separately. If you are using "uv" to execute your tests, you can use the "--group" flag to specify extra # dependencies. test = [ - "openai>=1.100.0", # for expires_after support "aiosqlite", "aiohttp", "torch>=2.6.0", diff --git a/uv.lock b/uv.lock index 2788c6fef..47b1a3047 100644 --- a/uv.lock +++ b/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 3 +revision = 2 requires-python = ">=3.12" resolution-markers = [ "(python_full_version >= '3.13' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.13' and sys_platform != 'darwin' and sys_platform != 'linux')", @@ -1839,7 +1839,6 @@ test = [ { name = "datasets" }, { name = "mcp" }, { name = "milvus-lite" }, - { name = "openai" }, { name = "psycopg2-binary" }, { name = "pymilvus" }, { name = "pypdf" }, @@ -1865,7 +1864,6 @@ unit = [ { name = "milvus-lite" }, { name = "moto", extra = ["s3"] }, { name = "ollama" }, - { name = "openai" }, { name = "psycopg2-binary" }, { name = "pymilvus" }, { name = "pypdf" }, @@ -1889,7 +1887,7 @@ requires-dist = [ { name = "jsonschema" }, { name = "llama-stack-client", specifier = ">=0.2.21" }, { name = "llama-stack-client", marker = "extra == 'ui'", specifier = ">=0.2.21" }, - { name = "openai", specifier = ">=1.99.6" }, + { name = "openai", specifier = ">=1.100.0" }, { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" }, { name = "opentelemetry-sdk", specifier = ">=1.30.0" }, { name = "pandas", marker = "extra == 'ui'" }, @@ -1959,7 +1957,6 @@ test = [ { name = "datasets", specifier = ">=4.0.0" }, { name = "mcp" }, { name = "milvus-lite", specifier = ">=2.5.0" }, - { name = "openai", specifier = ">=1.100.0" }, { name = "psycopg2-binary", specifier = ">=2.9.0" }, { name = "pymilvus", specifier = ">=2.6.1" }, { name = "pypdf" }, @@ -1984,7 +1981,6 @@ unit = [ { name = "milvus-lite", specifier = ">=2.5.0" }, { name = "moto", extras = ["s3"], specifier = ">=5.1.10" }, { name = "ollama" }, - { name = "openai" }, { name = "psycopg2-binary", specifier = ">=2.9.0" }, { name = "pymilvus", specifier = ">=2.6.1" }, { name = "pypdf" },